Desenvolvimento

Analyze pharmaceutical batch production records for yield optimization, process parameter tuning, deviation trending, and cycle time reduction under cGMP compliance. USE THIS SKILL WHEN: user mentions batch records, pharma manufacturing, yield optimization, cGMP, process parameters, deviation analysis, batch production, pharmaceutical cycle time, process capability (Cpk), or drug manufacturing qua

Prepare for fundraising due diligence — runs CTO, CFO, CPO, sales, and codebase health reviews to produce a consolidated investor brief with scorecard, red flags, and strengths. Use before Series A, seed round, acqui-hire evaluation, or board presentation.

Evaluate survey data pipelines and research methodology. Analyzes response bias detection (speeders, straight-liners, bots), statistical significance testing (t-test, chi-square, ANOVA with Bonferroni correction), sentiment and theme extraction from open-ended responses, conjoint analysis (CBC/ACA with Hierarchical Bayes estimation), MaxDiff best-worst scaling, survey design quality, weighting met

Self-referential loop until task completion with configurable verification reviewer

Generative Engine Optimization (GEO) / Answer Engine Optimization (AEO) — make a site citable by ChatGPT, Perplexity, Claude, Gemini, and Google AI Overviews. Generates llms.txt and llms-full.txt, fills schema.org coverage gaps (Organization, Person/Author, Article, Product, FAQPage, HowTo, BreadcrumbList), audits entity density (target 15+ recognized entities per pillar page → 4.8x AI Overview se

Audit game narrative systems for technical quality -- branching dialogue trees, state/flag tracking, quest systems, choice-consequence mapping, localization pipelines, voice-over integration, and cinematic scripting. Supports Ink, Yarn Spinner, Twine, Articy Draft, Dialogue System for Unity, and custom engines. Use when reviewing dialogue branching logic, debugging quest state machines, validating

Pre-commit quality gate. Invoke before every git commit, after /flagrare:staleness-audit. Six checks — plan gaps, use-case coverage gaps, missing test scenarios, test philosophy violations (Kent Dodds Testing Trophy), SOLID violations, Clean Code violations. Each check is delegated to a parallel subagent. Surfaces findings before they land in history. Also invoke when the user says review this, am

Envie o plano atual para a CLI do OpenAI Codex para revisão iterativa. Claude e Codex interagem até que o Codex aprove o plano.

Generate complete workshop materials for teaching AI skills -- outlines, exercises, slides, and facilitator guides.

Use when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.

Pull the latest flagrare skills from GitHub. Use when the user says 'update skills', 'refresh skills', 'pull latest skills', 'update flagrare', or 'sync skills'.

Use when code needs restructuring without changing observable behavior.