All authors
Claude Skills by yeaight7
github.com/yeaight7200 skills5 installs224 views
- Writing PlansUse when you have a spec or requirements for a multi-step task, before touching code.Votes: 0GitHub stars: 6
- Agent Readable DocsUse when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.Votes: 0GitHub stars: 6
- Api Doc ReviewVerify that API endpoints match their OpenAPI/Swagger specifications.Votes: 0GitHub stars: 6
- Architecture Decision RecordsRecord why an architectural choice was made to prevent agents or humans from unintentionally reverting it.Votes: 0GitHub stars: 6
- Context DocsMaintain short, focused Markdown files per subsystem to provide agents with isolated context.Votes: 0GitHub stars: 6
- Doc Consistency CheckAudit documentation for broken file paths, outdated commands, and renamed variables.Votes: 0GitHub stars: 6
- Readme HardeningEnsure the project README provides immediate, exact commands for setup, testing, and deployment to help agents and humans bootstrap quickly.Votes: 0GitHub stars: 6
- Review Comment Style MiningUse when mining PR review comments and text diffs for reusable writing, documentation, tone, and editorial improvement patterns.Votes: 0GitHub stars: 6
- Gh Address CommentsAddress actionable GitHub pull request review feedback. Use when the user wants to inspect unresolved review threads, requested changes, or inline review comments on a PR, then implement selected fixes.Votes: 0GitHub stars: 6
- Github Ci Failure TriageInspect GitHub PR checks, fetch actionable failure logs, summarize the breakage, and propose a local fix plan before changing code.Votes: 0GitHub stars: 6
- Pr Review Ci LoopRun a review and CI loop around a pull request with explicit approval gates for code changes, remote writes, and follow-up actions.Votes: 0GitHub stars: 6
- Baseline Comparison ReviewEnsure that new complex models actually outperform simple, naive baselines.Votes: 0GitHub stars: 6
- Dataset Split ReviewAudit the methodology used to split data into train, validation, and test sets.Votes: 0GitHub stars: 6
- Experiment Tracking ReviewVerify that all hyperparameters, metrics, and data references are properly logged.Votes: 0GitHub stars: 6
- Ml Leakage CheckIdentify and prevent target leakage in ML preprocessing pipelines.Votes: 0GitHub stars: 6
- Model Evaluation ReportingStandardize the reporting of model metrics to ensure statistical rigor and business relevance.Votes: 0GitHub stars: 6
- Reproducible Training RunsAnalyzes ML training scripts to enforce seed setting, deterministic operations, and environment tracking for exact reproducibility.Votes: 0GitHub stars: 6
- Training Pipeline DebuggingDiagnose NaN losses, out-of-memory errors, and shape mismatches in deep learning or ML pipelines.Votes: 0GitHub stars: 6
- Mcp Server BuilderDesign high-quality MCP servers around workflows, narrow schemas, context-aware outputs, and actionable errors. Use when building or reviewing MCP tools for real agent tasks.Votes: 0GitHub stars: 6
- DefuddleUse when the user provides a URL to a standard web page and clean Markdown extraction with Defuddle would reduce clutter and token cost.Votes: 0GitHub stars: 6
- Graphifyany input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Use when the user wants to build, inspect, or query a cross-file knowledge graph from code, docs, papers, images, or videos with upstream graphify.Votes: 0GitHub stars: 6
- Markitdown File IntakeUse when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.Votes: 0GitHub stars: 6
- Memory Build WorkflowUse when a user needs to build or refresh persistent graph memory from a mixed corpus and the right path may include graphify, incremental update, or helper conversion before ingestion.Votes: 0GitHub stars: 6
- Memory Optimization WorkflowUse when deciding the lowest-cost context path for a mixed corpus, especially when choosing among direct reading, helper conversion, graph build, graph update, or graph query.Votes: 0GitHub stars: 6
- Memory Query WorkflowUse when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.Votes: 0GitHub stars: 6
- Ai Regression TestingDeterministic checks first, agent review second, regression test for every real bug fixed or document why not. Targets the blind spot where an agent writes and reviews its own code.Votes: 0GitHub stars: 6
- Change Impact CheckUse before submitting a PR or considering a task done to evaluate the 'blast radius' of your changes.Votes: 0GitHub stars: 6
- Ci Failure ReadoutUse when a CI pipeline fails to extract the actual error from thousands of lines of logs.Votes: 0GitHub stars: 6
- Pre Release VerificationUse before tagging a release or deploying to production to ensure all quality gates have passed.Votes: 0GitHub stars: 6
- Receiving Code ReviewUse when receiving code review feedback, before implementing suggestions — requires technical verification and reasoned pushback, not performative agreement or blind implementation.Votes: 0GitHub stars: 6
- Requesting Code ReviewUse when completing tasks, implementing major features, or before merging to verify work meets requirements.Votes: 0GitHub stars: 6
- Risk Based ReviewUse when reviewing code (or your own plan) to allocate attention based on the danger of the change.Votes: 0GitHub stars: 6
- Test Driven DevelopmentUse when implementing any feature or bugfix, before writing implementation codeVotes: 0GitHub stars: 6
- Agent Config Security AuditAudit agent configuration files for security vulnerabilities and misconfigurations. Covers settings.json, .mcp.json, .codex/config.toml, AGENTS.md, hooks, plugin manifests, and relay config. Classify findings as P0 or P1.Votes: 0GitHub stars: 6
- Filesystem Mcp GuardrailsUse when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.Votes: 0GitHub stars: 6
- Hard Won Skill ExtractorExtract a learned skill from the current conversation manuallyVotes: 0GitHub stars: 6
- Skill Authoring GuideCreate or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.Votes: 0GitHub stars: 6
- Autonomous Delivery PipelineFull autonomous execution from idea to working codeVotes: 0GitHub stars: 6
- Codebase Migration BatchesRun large codebase migrations in reviewable local batches with codemods, checkpoints, and verification. Use when a wide refactor is too risky to ship as one monolithic change.Votes: 0GitHub stars: 6
- Parallel Execution EngineRun independent work in parallel with explicit wave boundaries, lightweight coordination, and bounded verification. Use when latency matters and the work does not need a persistent completion loop.Votes: 0GitHub stars: 6
- Persistent Completion LoopSelf-referential loop until task completion with configurable verification reviewerVotes: 0GitHub stars: 6
- Subagent Team OrchestrationCoordinate multiple subagents through dependency-aware waves, stage handoffs, monitoring, and verification loops. Use when the work is too large or too mixed for a single agent.Votes: 0GitHub stars: 6
- Requirements ClarifierTurn vague implementation requests into testable requirements before coding.Votes: 0GitHub stars: 6
- Browser Automation SafetyUse when validating rendered web pages, local dev servers, browser automation, screenshots, forms, auth sessions, or UI evidence with strict browser safety boundaries.Votes: 0GitHub stars: 6
- Ask ClaudeUse when a Codex or generic local agent needs a focused second opinion from Claude CLI without MCP routing.Votes: 0GitHub stars: 6
- Ask CodexUse when a Claude Code agent needs to delegate a question, subtask, or review to a local Codex instance.Votes: 0GitHub stars: 6
- Ask GeminiUse when a Codex or generic local agent needs a focused second opinion from Gemini CLI without MCP routing.Votes: 0GitHub stars: 6
- Build Fix Minimal DiffFix broken builds, type errors, or test failures with the smallest safe diff — no opportunistic refactors, no cleanup, no unrelated changes.Votes: 0GitHub stars: 6
- Changelog GeneratorTurn commits, PRs, or diffs into user-facing release notes or an internal changelog, with modes for breaking-change scanning.Votes: 0GitHub stars: 6
- Environment DoctorDiagnose local agent and project setup problems — missing commands, broken MCP configs, stale generated assets, bad paths, invalid catalog entries, and missing env vars.Votes: 0GitHub stars: 6