发现 Skills

Use when encountering ANY bug, test failure, error message, performance issue, or unexpected behavior, BEFORE proposing fixes. Forces root-cause investigation before any code change. Iron law - no fixes without evidence. TRIGGER on "this is broken", "test is failing", "why is X doing Y", "it crashed", "production issue", or any unexpected output. Cross-refs test-driven-development for writing the regression test, bug-hunt chain for the canonical fix pipeline.

Mark tasks and phases complete after verification. Use when finishing tasks, closing phases, or marking work done. Ensures all work verified before completion.

Manage backlog and archive completed work. Use for backlog operations, archiving phases, or keeping active plan focused. Curates plan organization.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Creates a complete REST endpoint (CRUD) for a given resource. Includes validation, pagination, error handling, tests.

In an authorized laboratory or penetration testing environment, use arpspoof, Ettercap, and Scapy to simulate ARP spoofing attacks to demonstrate man-in-the-middle risks, test network detection capabilities, and validate ARP detection countermeasures.

During authorized security testing, assess GraphQL API endpoints for introspection leakage, injection attacks, authorization flaws, and denial-of-service vulnerabilities.

Design a model routing strategy that selects the right LLM for each task type. Balance cost, latency, and quality tradeoffs across models. Use when building agents that call multiple LLMs, optimizing token costs by routing simple tasks to cheaper models, or designing fallback chains.

Use when the user asks to "Organize the Scratch Book" or "Process my inbox" to promote unprocessed captures into TODOs and create GitHub issues.

Enforces a 7-stage development workflow: Discover (Socratic questioning) → Explore (codebase scan) → Spec (acceptance criteria) → Eval (write tests FIRST) → Implement → Verify → Iterate. Supports deterministic tests (Playwright, unit), fuzzy evals (screenshot + LLM-as-judge), integration evals, QA dogfood, and regression suites. Strong nudge enforcement — agents are pressured to follow each stage but can override with justification. Trigger on "eval driven," "test first," "write tests first," "TDD," "eval," "acceptance criteria," "spec first," "workflow," "development process," "how should I build this," or any new feature request. Hooks into my-stack for skill routing and dogfood-complete for QA/test generation.

Skill imported from KlebersonCollab/skills

Control Philips Hue lights and scenes via the OpenHue CLI.

Docker multi-stage build templates, image security, and docker-compose patterns. TRIGGER when: writing a Dockerfile, composing services, or hardening a container image. SKIP: CI pipeline definitions (use github-actions-template); runtime monitoring (use monitoring-observability).

Ultra-compressed communication mode. Reduce token usage by ~75% by speaking like a caveman while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Run the Contact Department responsibility set from the current SCAS runtime profile. Use when Codex needs target-company stakeholder mapping, buyer-firm contact discovery, contact qualification, seniority assessment, or outreach angles for a target-company briefing.

PHP debugging and analysis tools using Xdebug. Use when asked to trace, debug, profile, or analyze coverage of PHP code.

Interact with a self-hosted GARAgE distributed object storage instance — including bucket management, access key management, object operations, cluster administration, and layout configuration. Use this skill whenever the user mentions garage, GARAgE, object storage, S3-compatible storage, bucket operations, storage keys, uploading or downloading files to their self-hosted storage, or managing their Deuxfleurs/GARAgE cluster. Also use when the user wants to list, create, delete, or configure buckets or access keys on their storage VM.

Use this Skill when a user wants to track AI search traffic in GA4 or Google Search Console (GSC). Also apply it when the user mentions "AI traffic," "ChatGPT referral," "Perplexity traffic," "AI Overviews," "GA4 AI sources," "AI search analytics," "track AI referrals," "AI search traffic," "Claude traffic," or "how to track AI traffic." For AI SEO strategy, use generative-engine-optimization.

When the user wants to create, optimize, or audit glossary page content and structure. Also use when the user mentions 'glossary', 'definitions', 'terminology', 'industry terms', 'glossary page', 'term definitions', 'vocabulary', 'glossary SEO', or 'definition page'. For definitions at scale, use programmatic SEO.

When the user wants to create or optimize a refund or return policy page. Also use when the user mentions "refund policy," "return policy," "money-back guarantee," "returns and refunds," "refund page," "return process," "refund terms," or "satisfaction guarantee." For legal overview, use legal-page-generator.

When the user wants to run an SEO audit, technical SEO audit, or site health check. Also use when the user mentions SEO audit, technical audit, site audit, crawl audit, indexing audit, SEO health, or fix SEO issues. For prioritization and organic strategy, use seo-strategy. For GSC data analysis, use google-search-console.

Output quality A/B for an existing skill — generate variants with different output traits, run them blind against the same test prompts, present side-by-side to the user, capture preference (A / B / both / neither). Each iteration is human-judged; no LLM ratchet on taste-sensitive outputs. Constitution honored as floor (variants violating MUST clauses auto-rejected before user sees them); preference log accumulates as an RLHF-lite dataset; an H4 self-trained judge replaces the LLM-judge once the log is dense enough. Use when the user wants to improve a skill's output style, quality, voice, or tone, explore variant phrasings, or accumulate preference signal for taste-sensitive skill work. Triggers: improve skill output / A/B variants / output quality / style optimization / run A/B tests / try different phrasing / taste-sensitive skill. Do NOT use for token- or structure-refactors that must preserve output (use dev-workflow:skill-refactor), structural redesigns (use dev-workflow:skill-creator-advance), creating a new skill (use dev-workflow:skill-creator-advance), or deterministic/mechanical skills where output is binary correct/incorrect (no taste dimension for A/B). Skill output A/B · human-judged · preference log.

Implement typeclasses with curried signatures and dual APIs for both data-first and data-last usage