All authors
Claude Skills by simota
github.com/simota149 skills3 installs229 views
- TrawlArchitecting crawl and scraping systems: distributed crawler topology, URL frontier, politeness, compliance. Architecture-only. Not for single-page scraping (Vector) or ETL pipelines (Stream).Votes: 0GitHub stars: 80
- TriageResponding to incidents: identifies impact scope, formulates recovery procedures, creates postmortems. Use when incident response or disaster recovery is needed. Delegates fixes to Builder.Votes: 0GitHub stars: 80
- TunerTuning database queries via EXPLAIN ANALYZE, query plan optimization, index recommendations, and slow query detection. Not for schema/migrations (Schema) or non-DB performance (Bolt).Votes: 0GitHub stars: 80
- VectorAutomating browsers via Playwright and Chrome DevTools for data collection, form interaction, screenshot capture, and network monitoring. Task completion focus (vs Voyager for E2E testing).Votes: 0GitHub stars: 80
- VigilEngineering detection rules (Sigma/YARA), detection coverage mapping, threat hunting hypotheses, Purple Team Blue side, Detection-as-Code CI/CD. Use when defensive verification is needed.Votes: 0GitHub stars: 80
- VisionDirecting UI/UX creative work — redesigns, new designs, trend application, Design System construction, Muse/Palette/Flow/Forge orchestration. Use for design direction. Offers a co-design pair mode.Votes: 0GitHub stars: 80
- VitrineAuthoring Storybook stories, component catalogs, and Visual Regression integration (CSF 3.0/Factories, Storybook 10 ESM-only, React Cosmos). Use when building a component catalog.Votes: 0GitHub stars: 80
- VoiceCollecting user feedback via NPS surveys, review analysis, sentiment analysis, feedback classification, and insight extraction reports. Use when establishing feedback loops.Votes: 0GitHub stars: 80
- VoidVerifying YAGNI, cutting scope, and proposing complexity reductions. A 'subtraction' agent questioning the justification for every feature, dependency, doc, and config. Does not write code.Votes: 0GitHub stars: 80
- VoyagerAuthoring web and native E2E tests, including Playwright, Appium, XCUITest, device farms, visual regression, and App Store screenshot pipelines. Not for unit/load tests.Votes: 0GitHub stars: 80
- WeaveDesigning workflows and state machines. Use when state transition design, invalid transition detection, Saga patterns, or approval flow design is needed.Votes: 0GitHub stars: 80
- ZenRefactoring code: variable naming, function extraction, magic number constants, dead code removal. Does not change behavior. Not for bugs/security (Judge), tests (Radar), or features (Builder).Votes: 0GitHub stars: 80
- ZineAuthoring tech blog/article series for note/Zenn/Qiita/dev.to. Not for specs (Scribe) or microcopy (Prose).Votes: 0GitHub stars: 80
- GrokDesigning regex, parsers, and DSLs for grammar authoring and ReDoS-safe regex. Not for REST APIs (Gateway) or DB schemas (Schema).Votes: 0GitHub stars: 80
- HearthGenerating and auditing personal dev environment configs (zsh/tmux/neovim/ghostty) and automating the macOS desktop via AppleScript/JXA (Finder, Mail, Safari). Use for dotfiles or Apple Events.Votes: 0GitHub stars: 80
- LatchProposing, configuring, debugging, and maintaining Claude Code hooks (PreToolUse/PostToolUse/Stop and other lifecycle events). Use for workflow automation or quality gates via hooks.Votes: 0GitHub stars: 80
- LoomDesigning a repository's operating layer — which project-local skills, recipes, and orchestration workflows it needs, as one system. Not for a single skill body (Sigil) or runtime routing (Nexus).Votes: 0GitHub stars: 80
- MorphConverting document formats (Markdown/Word/Excel/PDF/HTML) and generating reusable conversion scripts. Use for distributable specs, accessibility-compliant PDFs, or Pandoc/LibreOffice pipelines.Votes: 0GitHub stars: 80
- NestDesigning LLM-optimized folder structures: audits and restructures directories for context efficiency, progressive disclosure, and prompt cache performance. Not for general repo structure (Grove).Votes: 0GitHub stars: 80
- OathAuditing regulatory compliance (SOC2/PCI-DSS/HIPAA/ISO 27001): maps requirements, checks controls, designs audit trails, implements Policy as Code. Use when compliance auditing is needed.Votes: 0GitHub stars: 80
- PipeDesigning GitHub Actions workflows in depth: trigger strategy, security hardening, performance optimization, PR automation, and Reusable Workflow design.Votes: 0GitHub stars: 80
- SummonChanneling the documented thinking of named notable figures (an 'itako' medium) — their mental models, heuristics, and decision-style as advisory lenses. Not for decisions (Magi) or personas (Cast).Votes: 0GitHub stars: 80
- ChiselConverting a supplied prompt into an executable specification: detects vague quality/quantity/explanation/style/design/technical/judgment wording, role and persona theater, and self-contradiction, then replaces each with a numeric bound, an observable behavior, or a scorable criterion — with a per-term ledger of what changed and what stayed open. Don't use for AI system design, RAG, or eval harnesses (Oracle), PRD/SRS authoring (Scribe), spec conformance verification (Attest), or SKILL.md nor...Votes: 0GitHub stars: 80
- PdmNavigating delivery status read-only: reconciles planned scope (specs/roadmap/PRD) against implemented code for what's built vs left. Not for priority scoring (Rank) or AC conformance (Attest).Votes: 0GitHub stars: 80
- TenbinDesign and generate project-specific code that uses Jev, including state/questions, SDK integration, decision logic and tests. Suggest Tenbin uses with /tenbin; suggest or generate state and questions from conversation, project context or sample input. Classify/route/triage, detect spam/abuse/injection, score severity/sentiment, rank, validate extraction or LLM answers, thresholds, guardrails. Also tenbin, TypeSafe, Jev, Choice/Score/Noul, calibrated probability, LLM labels, regex heuristics,...Votes: 0GitHub stars: 2
- ClarifyTurning a subjective request into an instruction both sides would agree to: the intent in the requester's own words plus a done-condition somebody else could check. Grounds the evaluative word from context first, asks only the residue that would change the deliverable, and locks the result. Use when the ask is 'make it nice', 'clean this up', 'do it properly', or 'that's not quite it'. Don't use for a request that already states its intent and how it will be judged.Votes: 0GitHub stars: 2
- Planning DecomposeSlicing chosen work into tasks and sequencing them: task shape, the dependency graph, the critical path, milestones, and what can run in parallel.Votes: 0GitHub stars: 2
- Planning DiscoverEstablishing what is actually true before deciding: current state, verified facts, assumptions worth checking, discovered constraints, and unknowns ranked by decision impact.Votes: 0GitHub stars: 2
- Planning EstimateSizing work as ranges, not points: per-task estimates, the critical path total, buffer, schedule, range drivers, and the conditions that would break it.Votes: 0GitHub stars: 2
- Planning FrameTurning a vague request into a stated problem: goals, non-goals, measurable success criteria, constraints, and the definition of done. Use when the problem itself is unstated.Votes: 0GitHub stars: 2
- Planning OptionsGenerating candidate approaches and choosing between them: criteria and weights, trade-offs, elimination, and a decision record naming what would change our mind.Votes: 0GitHub stars: 2
- Planning ReplanDeciding what a plan becomes once reality diverges: classifying the divergence, measuring it, the stop test, and a dated changelog of what changed and why.Votes: 0GitHub stars: 2
- Planning ReviewJudging whether a plan is ready to act on: readiness checks, a silence audit for what the plan never mentions, blocking findings, and the shortest path to ready.Votes: 0GitHub stars: 2
- Planning RiskFinding what could go wrong before it does: a pre-mortem, a register with likelihood and impact, mitigations, rollback, and abort conditions.Votes: 0GitHub stars: 2
- Planning RouterEntry point for the planning suite: classifies a planning request, picks the shortest chain of phases, and sequences them. Use when the phase is unclear, or a plan end to end is wanted.Votes: 0GitHub stars: 2
- Coding DebugDiagnosing something already broken: reproduce the bug, isolate and prove the root cause, then fix it minimally. Use for a regression, an error, a failing suite, or any why is this broken question.Votes: 0GitHub stars: 2
- Coding ExploreReading a codebase without changing it: where something lives, who calls it, how a path works, what a change touches, blast radius, structure, and history. Use before touching unfamiliar code.Votes: 0GitHub stars: 2
- Coding ImplementWriting working code: a feature, an endpoint, a screen, business logic, a CLI, an integration, a dependency upgrade, or performance work. Use when the shape is settled and code must exist.Votes: 0GitHub stars: 2
- Coding PlanDeciding the shape before code exists: interfaces and signatures, the data model, error and state design, build order, and the trade-off between options. Use when the approach is not obvious.Votes: 0GitHub stars: 2
- Coding RefactorRefactor: structure changes, behaviour stays identical — extract and extraction, rename, duplication, dead code, module boundaries, mechanical migration. Use when correct code is hard to work with.Votes: 0GitHub stars: 2
- Coding ReviewCode review of a change before it lands: defects, correctness, boundaries, security, and whether a diff is more code than the problem needs. Report-only, never edits. Use before merging.Votes: 0GitHub stars: 2
- Coding ShipGetting finished code out: commit granularity and messages, history shape, merge order, rebase and squash, splitting an oversized pull request, PR text, changelog, release notes. Use when done.Votes: 0GitHub stars: 2
- Coding TestBuilding the checks that catch defects: test cases, coverage of untested behaviour, regression tests, flaky repair, and what to assert. Use for standalone test work or an unreliable suite.Votes: 0GitHub stars: 2
- Quality DebtInventorying technical debt and ordering repayment by measured interest: touch frequency, blast radius, comprehension cost. Use to decide what to fix first and justify not fixing the rest.Votes: 0GitHub stars: 2
- Quality GateRendering the ship decision from evidence, and designing the gate criteria that encode it: conditions, blocking, and overrides. Use before a release, or when defining a definition of done.Votes: 0GitHub stars: 2
- Quality MetricsMeasuring quality with numbers that have a source: coverage, mutation score, defect density, complexity, and DORA, captured as reproducible snapshots. Use to set a baseline or read a trend.Votes: 0GitHub stars: 2
- Quality RegressionDiagnosing failures over time: regression bisection, flaky test classification and repair, quarantine with expiry, and turning a reproduction into a permanent guard. Use when a test now fails.Votes: 0GitHub stars: 2
- Quality ReviewReviewing a diff for defects: findings on what is correct, robust and clear, the evidence under each, severity kept apart from blocking, and what it leaves unchecked. Use for a pull request.Votes: 0GitHub stars: 2
- Quality TestWriting tests that can actually fail: naming an independent oracle, boundary and edge cases, choosing the test level, closing a coverage gap, and auditing whether a suite proves anything.Votes: 0GitHub stars: 2