Database

Write in the voice of Susannah Clapp — the Observer's longtime theater critic whose reviews combine precise descriptive writing with sharp cultural intelligence. Elegant, incisive, and attuned to the physical and sensory dimensions of performance.

Write in the voice of Ada Louise Huxtable — the first architecture critic at the New York Times and first Pulitzer Prize winner for criticism. Championed modernism, fought for preservation, accessible authority on the built environment. Trigger keywords: Huxtable, architecture criticism, NYT, Pulitzer, modernism, preservation, urban design, built environment.

Write in the voice of Camille Paglia — the provocative cultural critic and academic who blends classical scholarship with pop culture analysis, challenging orthodoxies on both left and right. Trigger keywords: Paglia, Sexual Personae, provocative, classical, pop culture, contrarian, feminist.

Write in the voice of Chris Stuckmann — the YouTube film reviewer known for earnest, passionate, audience-surrogate criticism and emotional connection to films. Accessible mainstream reviews with genuine depth. Trigger keywords: Stuckmann, YouTube, film review, earnest, passionate, mainstream, A+, letter grade, audience surrogate.

Write in the voice of Clive James — the Australian-British cultural polymath who elevated TV criticism to high art. Dazzling metaphors, "Cultural Amnesia," wit across every medium. Trigger keywords: Clive James, cultural criticism, TV criticism, Australian, British, Cultural Amnesia, polymath, metaphor, wit.

Write in the voice of Dorothy Parker — the Algonquin Round Table wit, New Yorker "Constant Reader" columnist, theater and book critic famous for devastating one-liner demolitions and razor wit. Trigger keywords: Dorothy Parker, Algonquin, Constant Reader, New Yorker, wit, one-liner, theater criticism, book review, devastating, quotable.

Write in the voice of H.L. Mencken — the "Sage of Baltimore," American Mercury editor, legendary cultural commentator and prose stylist. Savage satirist, democratic skeptic, one of America's greatest essayists. Trigger keywords: Mencken, Sage of Baltimore, American Mercury, satire, cultural commentary, prose stylist, democratic skeptic, Scopes trial.

Write in the voice of Lindsay Ellis — the YouTube video essayist who made film theory accessible and entertaining. Cultural analysis with humor, "The Whole Plate" Transformers series, feminist media criticism for the internet generation. Trigger keywords: Lindsay Ellis, video essay, YouTube, film theory, Transformers, Whole Plate, feminist, pop culture, media criticism, accessible theory.

Write in the voice of Mark Fisher — the cultural theorist and blogger (k-punk) who analyzed capitalism's effect on culture, coined "capitalist realism," and wrote about hauntology, depression, and the slow cancellation of the future. Trigger keywords: Fisher, k-punk, capitalist realism, hauntology, cultural theory, neoliberalism, lost futures, weird and eerie.

Write in the voice of RedLetterMedia (Mike Stoklasa) — the sardonic, analytical, and deeply knowledgeable film critics behind "Half in the Bag," "Best of the Worst," and the legendary Mr. Plinkett reviews. Known for long-form deconstruction, cynical humor masking genuine film knowledge, skewering Hollywood mediocrity, and a lo-fi aesthetic that prioritizes substance over production value. Trigger keywords: film review, Half in the Bag, Best of the Worst, Plinkett, hack fraud, Hollywood, blockbuster, franchise, schlock, B-movie, film analysis, cynical review.

Write in the voice of Tony Zhou — creator of "Every Frame a Painting," the influential YouTube video essay series on filmmaking craft. Elegant, concise, visually driven analysis that changed how people discuss cinema online. Trigger keywords: Tony Zhou, Every Frame a Painting, video essay, filmmaking, visual analysis, editing, composition, YouTube, film craft.

Write criticism in the close-reading mode — sentence-by-sentence, shot-by- shot, frame-by-frame attention to how a work is made. The critic's authority comes from technical fluency and the willingness to spend a paragraph on a single word. Use for criticism that aims to teach the reader how to see the work, not just to summarize whether it succeeded.

Write criticism that situates the work in its political, historical, and social context. The critic's authority comes from understanding what the work is responding to — the moment that produced it, the audiences it addresses, the power it negotiates with. Use for criticism that wants to understand a work as an event in culture, not just an aesthetic object.

Write criticism that gives praise as a serious activity. The critic's job is to win readers for work they will love, articulating why a work earns enthusiasm with the same rigor others bring to negative judgment. Use for criticism that wants to grow audiences, build canons, and treat recommendation as a craft.

Write criticism that uses the first person as a serious instrument. The critic is present in the essay — their experience, their associations, their formation — because the encounter between this particular reader and this particular work is the essay's subject. Use for the long-form literary essay, the personal review, and criticism that values fidelity to the actual experience of reading.

Write criticism that is also reporting — interview the artist, attend the rehearsal, walk the studio, watch the working hands. The essay arrives at judgment through encounter rather than from the armchair. Use for the long-form magazine profile, the criticism-as-portrait, and any piece where access to the maker is part of the article's authority.

Write the negative review as a serious craft. The polemic is unsparing, precise, and ethical — it identifies what is wrong with a work, why the wrong matters beyond this particular work, and what is at stake when the bad work is praised. Use for criticism that wants to defend standards from drift, hype from coronation, mediocrity from canonization.

Activate this skill when the user must choose between several open-source libraries, frameworks, or tools for the same job and wants a defensible comparison rather than a popularity contest: weighing API fit, maintenance, performance, community, license, and the cost of leaving later, and recording the decision so it can be revisited. Triggers on keywords like "compare libraries," "which should we adopt," "library evaluation," "decision matrix," "architecture decision record," "ADR," "exit cost," "vendor lock-in," "build vs buy vs adopt," "technology selection," and "candidate comparison." Covers criteria definition, spikes, weighted scoring with sensitivity checks, exit-cost estimation, and a decision record template.

Activate this skill when the user wants to contribute to an open-source project they do not maintain: filing an issue well, preparing a first pull request that gets merged, matching the project's conventions, handling review feedback, and deciding when to fork instead. Triggers on keywords like "first pull request," "contributing to open source," "CONTRIBUTING.md," "how to file an issue," "PR etiquette," "code review feedback," "DCO sign-off," "CLA," "changelog entry," "upstream a fix," and "fork or contribute." Covers reading contribution guidelines, issue etiquette, scoping small PRs, style and tests, changelog practice, responding to review, and the fork decision.

Activate this skill when the user must audit what a project actually depends on: reading lockfiles, mapping transitive dependencies, checking license compatibility, producing or consuming an SBOM, matching packages against vulnerability advisories, or judging whether the people behind a dependency can be trusted. Triggers on keywords like "dependency audit," "license compatibility," "lockfile," "transitive dependencies," "SBOM," "SPDX," "CycloneDX," "osv-scanner," "npm audit," "GPL contamination," "supply chain," "known vulnerabilities," and "third-party license review." Covers lockfile reading per ecosystem, dependency graph tooling, license classes and their interactions, advisory databases, maintainer risk, and an audit report template.

Activate this skill when the user needs to find out when, why, or by whom a behaviour in a codebase changed: hunting a regression, understanding a strange line of code, recovering lost work, or building evidence from commit messages and pull request discussions. Triggers on keywords like "git blame," "git bisect," "pickaxe," "git log -S," "when did this change," "who wrote this," "find the commit that broke," "reflog," "regression hunting," "commit archaeology," and "history forensics." Covers path-scoped logs, blame that survives refactors, pickaxe searches, bisection with automated tests, reflog recovery, and reading PR discussions as evidence.

Activate this skill when the user wants to find existing code, issues, or discussions on GitHub before building or debugging something: locating prior art for a design, finding whether a bug has already been reported or fixed in a fork, discovering how other projects integrate a library, or searching a large organisation's code for a pattern. Triggers on keywords like "github search," "code search operators," "search issues," "has this been reported," "find a fork that fixed," "how do others use this library," "prior art," "search qualifiers," "gh search," and "github repository research." Covers code search syntax, issue and PR qualifiers, fork mining, integration discovery, keeping reusable searches, and the blind spots of the search index.

Activate this skill when the user has to understand a codebase they did not write: onboarding to a new repository, evaluating a library's internals before adopting it, tracing how a request flows through a service, or figuring out where to make a change in a large project. Triggers on keywords like "understand this codebase," "where is the entry point," "how does this repo work," "trace a request," "code reading," "navigate a large codebase," "ripgrep," "ctags," "folder structure," and "onboarding to a repository." Covers entry points, build files, folder mapping, end-to-end tracing, reading tests as documentation, tooling, and time-boxed exploration.

Activate this skill when the user is evaluating whether an open-source project on GitHub is safe to depend on, doing "github repository research" before adopting a library, or asking whether a project is maintained, abandoned, or risky. Triggers on keywords like "repository health," "is this repo maintained," "bus factor," "release cadence," "issue response time," "abandoned project," "dependency due diligence," "open source risk," "CI status," "license check," and "security policy." Covers a scored health checklist, the signals that actually predict maintenance, and the red flags that should end an evaluation early.

Activate this skill when the user needs to judge how well a GitHub repository defends itself and its downstream users: whether secrets have leaked into history, whether its GitHub Actions workflows can be hijacked, whether the default branch is protected, how dependencies are updated, whether commits and releases are signed, and whether there is a working vulnerability disclosure process. Triggers on keywords like "security posture," "secrets in git history," "pull_request_target," "pin actions to SHA," "branch protection," "dependabot," "renovate," "signed commits," "SECURITY.md," "supply chain attack," "OpenSSF Scorecard," and "workflow permissions." Covers history scanning, Actions supply-chain risks, protection rules, update automation, signing, and disclosure policy.

Activate this skill when the user is trying to run the code released with an academic paper or a research prototype and get results that match the claims: setting up a pinned environment, mapping the paper's equations and tables to the code, handling datasets and random seeds, and writing up a reproduction that others can trust. Triggers on keywords like "reproduce this paper," "research code," "reproducibility," "paper vs code," "random seed," "can't match the reported numbers," "replication," "pin the environment," "ML reproducibility," and "reproduction report." Covers environment pinning, reading the paper against the code, datasets and seeds, running the smallest experiment first, documenting deviations, and honest reporting.

Activate this skill when the user needs external code to control or observe an Asterisk PBX: a database dip during a call, a custom IVR or dialer written in a real language, a wallboard, click-to-call, or agent state control. Triggers on "AGI," "FastAGI," "ARI," "Stasis," "AMI," "manager.conf," "ari.conf," "Originate," "asterisk REST," "asterisk websocket," "asterisk events," or "asterisk integration." Covers choosing between the three interfaces, authentication for each, a small working example of each, and the performance mistakes that take production systems down.

Activate this skill when the user is standing up an Asterisk PBX for the first time, choosing between source and package installs, or trying to understand how channels, the dialplan, applications and modules fit together. Triggers on "asterisk," "Asterisk PBX," "install asterisk," "menuselect," "asterisk from source," "asterisk CLI," "modules.conf," "asterisk.conf," "/etc/asterisk," "chan_pjsip," or "asterisk directory layout." Covers the core architecture, Debian and RHEL installs, menuselect choices, the directory tree, and the checks to run on first boot.

Activate this skill when the user is exposing an Asterisk PBX to the internet, has just been hit by toll fraud, or wants to lock down SIP registration, the dialplan, AMI and ARI before an audit. Triggers on "asterisk security," "toll fraud," "fail2ban asterisk," "SIP brute force," "friendly-scanner," "permit deny," "acl.conf," "alwaysauthreject," "SRTP," "SIP TLS," "firewall RTP," "restrict international calls," or "Asterisk PBX hardening." Covers the fraud patterns actually seen in production, log-driven banning, ACLs, credential policy, dialplan class of service and concurrency limits, TLS and SRTP transport configuration, and firewall rules for SIP and the RTP range.

Activate this skill when the user is configuring queues.conf on an Asterisk PBX, choosing a ring strategy, managing agents who log in and out, tuning hold announcements, or explaining queue statistics to a call-centre manager. Triggers on "queues.conf," "app_queue," "ringall," "rrmemory," "leastrecent," "penalty," "AddQueueMember," "PauseQueueMember," "wrapuptime," "queue_log," "service level," "abandon rate," "queue show," or "asterisk call center." Covers strategies, penalties and queue rules, static and dynamic members, announcements, wrap-up, the queue_log format, the metrics that matter, and the bugs every queue deployment hits.

Activate this skill when the user needs billing-grade call records from an Asterisk PBX: configuring cdr.conf with a CSV or ODBC backend, enabling CEL for per-event detail, adding custom fields to records, writing call reports in SQL, or reconciling minutes against a carrier invoice. Triggers on "CDR," "cdr.conf," "Master.csv," "cdr_adaptive_odbc," "CEL," "cel.conf," "linkedid," "billsec," "disposition," "call report," "ASR," "ACD," "carrier invoice," "CDR(userfield)," or "asterisk billing." Covers what each CDR field really means, backend configuration for CSV and ODBC, CEL event types and how to read them, custom variables, the SQL reports managers actually ask for, and a reconciliation method that survives rounding, time zones and Local channels.

Activate this skill when the user is writing or debugging extensions.conf for an Asterisk PBX: routing inbound DIDs, building outbound rules, structuring contexts, or replacing Macro() with GoSub. Triggers on "asterisk dialplan," "extensions.conf," "pattern matching," "_NXXXXXX," "GoSub," "Dial options," "hangup handler," "priorities," "same => n," "include =>," "DIALSTATUS," or "dialplan reload." Covers contexts, extensions, priorities, pattern matching, variables and functions, subroutines, Dial behaviour and worked dialplans you can paste and adapt.

Activate this skill when the user is building an auto-attendant or interactive voice menu on an Asterisk PBX, recording prompts, routing by business hours, or debugging callers who get stuck or hang up in a menu. Triggers on "IVR," "auto attendant," "Background," "WaitExten," "Read()," "GotoIfTime," "business hours," "invalid extension," "timeout extension," "prompt recording," "sln," "asterisk sounds," or "press 1 for." Covers menu design callers tolerate, the applications that collect digits, timeout and error handling, prompt formats and recording, time-based routing and a test procedure that finds the bugs before callers do.

Activate this skill when the user is configuring pjsip.conf on an Asterisk PBX: registering phones, building a trunk to a SIP provider, fixing NAT audio problems, or migrating from chan_sip. Triggers on "pjsip.conf," "pjsip endpoint," "aor," "identify," "registration," "external_media_address," "rtp_symmetric," "force_rport," "rewrite_contact," "SIP trunk," "pjsip show endpoints," "codecs," "direct_media," or "asterisk pjsip." Covers every section type, the NAT settings that actually matter, codec negotiation, provider trunks with and without registration, phone templates and the CLI commands for verification.

Activate this skill when the user has a call that fails, drops, or has bad or missing audio on an Asterisk PBX and needs to capture a SIP trace, interpret a response code, or diagnose NAT, codec, DTMF or registration problems. Triggers on "one-way audio," "no audio," "pjsip set logger on," "rtp set debug," "sngrep," "tcpdump," "SIP trace," "403 Forbidden," "401 Unauthorized," "408 Request Timeout," "488 Not Acceptable," "registration failed," "call drops after 30 seconds," "codec mismatch," "DTMF not working," or "asterisk troubleshooting." Covers the capture tools, a methodical way to read a trace, what each SIP response means on an Asterisk system, the NAT settings and what each one fixes, and a symptom-to-cause table built from real incidents.

Activate this skill when the user is configuring voicemail.conf, delivering voicemail by email, recording calls with MixMonitor, deciding how long to keep recordings, or wiring recordings and messages into a transcription service on an Asterisk PBX. Triggers on "voicemail.conf," "VoiceMail," "VoiceMailMain," "MWI," "MixMonitor," "call recording," "record calls," "recording retention," "voicemail to email," "externnotify," "wav49," or "asterisk voicemail." Covers mailbox configuration, greetings and folders, email notification, MixMonitor options and post-processing, storage sizing and retention, consent and compliance notices, and transcription hooks.

Triggers when the user needs to find, profile or verify an automated client in access logs: grouping by IP, /24, ASN and User-Agent, reading Sec-Fetch headers, checking TLS fingerprints, confirming a claimed Googlebot, or reconstructing a crawler's sessions. Trigger on "access logs," "who is this IP," "crawler in the logs," "verify Googlebot," "reverse DNS," "JA3," "JA4," "Sec-Fetch-Dest," "Logs Explorer query," "BigQuery logs," "CloudFront logs," "scraper IP," or "bot traffic analysis." Covers Cloud Logging, Vercel, nginx, Caddy and CloudFront formats, jq, awk and SQL snippets, RDAP and whois for ownership, and the sampling and cost of logging itself.

Triggers when the user suspects their analytics are inflated by automation, or asks why GA4, Plausible, Fathom or their own server-side counters show users, pageviews or a "most viewed" list that does not match reality. Trigger on "bot traffic," "GA4 users vs engaged sessions," "direct traffic spike," "crawler in analytics," "headless browser," "fake pageviews," "engagement rate," "IAB bot filter," "Plausible bots," or "most viewed is wrong." Covers the one-page/under-ten-seconds/new-user-every-hit signature, hourly steadiness, single OS-browser-device fingerprints, uniform per-page counts, GA4 comparisons, data filters and Data API queries, why IAB filtering misses JavaScript-executing headless browsers, and what to report instead.

Activate this skill when the user is writing a crawler, scraper or fetcher of any size and wants it to be identifiable, cheap for the sites it visits, resilient to rate limiting, and defensible. Triggers on "build a crawler," "web scraping etiquette," "polite scraper," "obey robots.txt," "Crawl-delay," "conditional requests," "ETag If-Modified-Since," "back off on 429," "headless browser scraping," "scraper legal," "CFAA hiQ," "GDPR scraping," or "terms of service scraping." Covers self-identification, robots.txt parsing, rate and concurrency limits with jitter, caching and revisit policy, sitemaps before spidering, Retry-After handling, preferring HTML or APIs over headless browsers, and an outline of the legal landscape with an explicit not-legal-advice line naming the professional to consult.

Triggers when the user wants to know exactly what their site hands to any client that asks, or wants to gate full text behind a preview without destroying search visibility. Trigger on "content exposure," "web scraping protection," "preview gating," "show 30%," "paywall structured data," "RSC payload," "__NEXT_DATA__," "sitemap leaks," "public JSON," "canary text," "watermark content," "scraper copied my site," or "API keys and quotas." Covers every path full text ships on (server-rendered HTML, React Server Component payloads, prerendered routes, JSON data files, sitemaps, public APIs, RSS), why client-side gates are theatre, server-side preview gating with indexable summaries, API-first access, canary sentences, and the SEO and AI-search cost of hiding text.

Activate this skill when the user wants to know what automated traffic actually costs them on pay-per-use hosting, or is deciding whether a crawler is a billing problem, a data problem, or no problem at all. Triggers on "cloud bill," "bot traffic," "crawler cost," "Cloud Run pricing," "Vercel usage," "Lambda invocations," "egress," "free tier," "web scraping cost," or "how much is this scraper costing me." Covers per-request, CPU-time, memory, egress, image optimisation and database charges triggered per page, where free tiers end, a fully worked arithmetic example, and how to measure from billing exports and request logs.

Activate this skill when the user is choosing or configuring an edge product to handle bot traffic: Cloudflare Bot Fight Mode, Super Bot Fight Mode, Bot Management, Turnstile or managed challenges; Google Cloud Armor; AWS WAF Bot Control; Vercel Firewall and Attack Challenge Mode; or Fastly. Triggers on "WAF," "bot management," "Cloudflare challenge," "Turnstile," "Cloud Armor pricing," "AWS WAF Bot Control," "Vercel Firewall," "Attack Challenge Mode," "block scraper at the edge," or "is this worth $5 a month." Covers what each product actually does and charges for, what JavaScript challenges do to search crawlers, AI crawlers, link previews and accessibility, when a control costs more than the crawler, and a rule order that allow-lists verified crawlers first, challenges by score, and blocks only on evidence.

Activate this skill when the user is writing or auditing a robots.txt, deciding which search, AI-training and AI-assistant crawlers to allow, or asking whether a crawler will obey it. Triggers on "robots.txt," "crawler," "User-agent," "Disallow," "Crawl-delay," "Googlebot," "GPTBot," "ClaudeBot," "Google-Extended," "CCBot," "Bytespider," "llms.txt," "AI crawler policy," or "block AI bots." Covers RFC 9309 syntax and precedence, wildcard and Sitemap support by engine, the crawler tokens that matter in 2026 grouped by purpose, the visibility trade-off of each group, testing with curl and Search Console, and what robots.txt cannot do against an undeclared headless browser or scraper.

Activate this skill when the user must decide which crawlers to admit and which to refuse, and wants the decision grounded in what each class returns: search traffic, AI citations, nothing, or copies and a cloud bill. Triggers on "should I block GPTBot," "AI Overviews traffic," "crawl budget," "Search Console crawl stats," "AI search referrals," "ChatGPT citations," "Perplexity referrals," "Google-Extended," "crawler policy," "bot traffic policy," or "robots.txt strategy." Covers the four crawler classes and their return, what blocking does to indexing and to AI answer citations, measuring referrals from AI surfaces, structured data and canonical signals, a policy matrix small sites can adopt, and a quarterly review as tokens change.

Activate this skill when the user needs to design or debug rate limiting for page traffic on a public site, as opposed to an API: sizing limits from real user percentiles, choosing keys and windows, deciding between in-memory and shared counters, exempting search crawlers, and returning a correct 429. Triggers on "rate limiting," "rate limit middleware," "token bucket," "sliding window," "429 Retry-After," "per-IP limit," "Next.js middleware rate limit," "Sec-Fetch-Dest," "Upstash ratelimit," "Cloudflare rate limiting rule," or "bot traffic keeps reading every page." Covers hourly plus daily buckets, multi-instance effects on the effective limit, framework pitfalls, and testing against a production build before shipping.

Activate this skill when the user needs to document a time series dataset so that a successor, a consumer or an auditor can understand and trust it without the original author, or needs to prepare a dataset for a handover, a review or a regulated use. Triggers on "dataset documentation," "datasheet," "dataset card," "data dictionary," "known gaps," "revision policy," "quality report," "audit trail," "data governance," "data integrity," "data lineage," or "handover checklist." Covers datasheets adapted for series, change logs, quality reports that name the exact checks run, the mechanisms behind financial, life-science and general data-quality expectations, and a pre-handover checklist.

Activate this skill when the user needs a time series to answer both "what was true at time T" and "what did we believe at time T," and needs restatements, revisions and recalibrations handled without leaking future knowledge into research, backtests or reports. Triggers on "bitemporal," "valid time," "transaction time," "as-of query," "point-in-time," "restatement," "revision," "look-ahead bias," "leakage," "system-versioned table," "vintage," or "time series." Covers the two time axes, table design and SQL patterns, as-of joins in pandas, vendor point-in-time sources, and tests that prove a pipeline does not see the future. Also triggers on "as-of query," "bitemporal table," "look-ahead bias," and "point-in-time data."

Activate this skill when the user needs a report, backtest, model or audit figure built on a time series to be reproducible months later, and needs the dataset, code and parameters pinned so that it can be. Triggers on "dataset versioning," "reproducible results," "content hash," "immutable partitions," "snapshot," "time travel," "dataset tag," "pin the dataset," "audit trail," "data provenance," or "reproduce a number." Covers content hashing, immutable partition layouts, git-style versioning for data, table-format time travel and its retention traps, manifests that bind data to code and parameters, and a procedure for reproducing a six-month-old number from scratch. Also triggers on "DVC," "lakeFS," "Delta Lake time travel," "Apache Iceberg," and "dataset versioning."

Activate this skill when the user needs to know, before a consumer does, that a time series is late, short, or shaped differently from yesterday, and needs monitors that alert on data-quality metrics rather than on the values themselves. Triggers on "freshness SLO," "data freshness," "completeness monitoring," "expected vs received," "volume anomaly," "distribution drift," "data observability," "source freshness," "checkpoint," "data on-call," "runbook," "alert fatigue," or "data quality." Covers SLO definitions for pipelines, metric design, implementation with SQL-test frameworks, expectation checkpoints, observability packages or a plain scheduled query, dashboards, runbooks and the on-call practices that keep alerts believable. Also triggers on "dbt source freshness," "Elementary," "Soda," "Monte Carlo," and "data SLO."

Activate this skill when the user needs to find missing points, duplicated or conflicting records, out-of-order arrivals, spikes, flatlines, stale values or silent unit changes in a time series, and to decide which of them to flag rather than fix. Triggers on "gap detection," "missing points," "duplicate rows," "out of order," "spike detection," "outlier," "flatline," "stuck sensor," "stale value," "unit change," "scale jump," "expected cadence," "data quality," or "time series anomalies." Covers completeness against a known cadence, gap classification, duplicate types, robust thresholds derived from the series itself, and the list of things that must never be auto-corrected.

Activate this skill when the user needs to turn quality checks on a time series into a score consumers can act on, hold suspect points aside without losing them, repair gaps and corrections without destroying provenance, and rerun pipelines safely. Triggers on "quality score," "data quality dimensions," "quarantine," "dead-letter queue," "backfill," "imputation policy," "forward fill," "interpolation," "correction log," "consumer notification," "idempotent reprocessing," or "time series data quality." Covers per-series and per-window scoring across accuracy, completeness, timeliness, consistency and validity, quarantine and release flows, backfills that preserve the chain of custody, when each fill method is wrong, and reprocessing that can run twice without harm.

Activate this skill when the user is defining or enforcing what a time series must look like: field types, units, precision, nullability, cadence, timezone and revision rules, and how those may change without breaking consumers. Triggers on "data contract," "schema evolution," "units and dimensions," "precision and scale," "nullability," "backward compatible," "breaking change," "schema registry," "validation suite," "expectation," "dbt test," or "time series schema." Covers the contents of a contract for a series, versioned schemas and evolution rules, validation with expectation-style, dataframe-schema, SQL-test and check-language tools, and worked contracts for a price bar and a sensor reading. Also triggers on "pandera," "Great Expectations," "dbt tests," "Soda," and "data contract."

Activate this skill when the user needs to record or reconstruct where a time series value came from, which run produced it, which transform version touched it, and why it changed between two reports. Triggers on "time series data quality provenance," "data provenance," "data lineage," "lineage graph," "chain of custody," "wasDerivedFrom," "derived series," "ingest run id," "transform version," "correction history," or "why did this number change." Covers provenance models that survive contact with production, per-series and per-point provenance fields, lineage events for pipeline runs, what belongs inline in the table versus in a catalog, and a worked trace from a reported figure back to the raw record. Also triggers on "OpenLineage," "W3C PROV," "Marquez," and "lineage graph."

Activate this skill when the user is storing, converting, validating or debugging timestamps on a time series and needs to get offsets, daylight saving transitions, event versus ingest time, ordering, clock precision and late-arriving data right. Triggers on "timestamp integrity," "timezone bug," "DST transition," "UTC offset," "event time vs processing time," "clock skew," "monotonic clock," "watermark," "late data," "leap second," "epoch milliseconds," "tz database," or "time series data quality." Covers the class of bugs that quietly corrupts series, the rules that prevent them, and validation queries in SQL and pandas.

Adversarial implementation review methodology that validates code completeness against requirements with fresh objectivity. Uses a coach-player dialectical loop to catch real gaps in security, logic, and data flow.

Design, document, and test APIs following RESTful principles, consistent conventions, and comprehensive testing strategies. Use this skill when the user asks about designing an API, writing API documentation, testing endpoints, handling API versioning, error response design, or wants guidance on building APIs that are intuitive, reliable, and maintainable.

Design software systems with sound architecture — choosing patterns, defining boundaries, making trade-offs, and planning for scalability. Use this skill when the user asks about system design, architecture decisions, design patterns, scaling strategy, service boundaries, or technical planning. Also trigger for "how should I structure this," "design a system for," "monolith vs microservices," "what pattern should I use," "scalability plan," or any request involving high-level technical design, component decomposition, or architectural trade-off analysis.

Perform deep, actionable code reviews covering bugs, security vulnerabilities, performance issues, and maintainability concerns. Use this skill when the user asks to review code, check a pull request, audit code quality, get feedback on an implementation, or wants a second pair of eyes on their work. Also trigger for "review this," "what's wrong with this code," "can you check my PR," "code quality check," or any request for constructive criticism of source code. Works with any language or framework.

Optimize database performance through indexing strategies, query optimization, schema design, and capacity planning. Use this skill when the user asks about slow queries, database indexing, query optimization, schema design for performance, database scaling, or wants guidance on diagnosing and fixing database bottlenecks.

Design database schemas, optimize queries, plan migrations, and develop indexing strategies for relational and NoSQL databases. Use this skill when the user asks about database design, schema modeling, query performance, SQL optimization, migrations, indexing, or data modeling. Also trigger for "slow query," "design a schema," "normalize this," "add an index," "migration strategy," "N+1 problem," or any task involving database architecture, query tuning, or data storage decisions. Covers PostgreSQL, MySQL, SQLite, MongoDB, Redis, and general database principles.