Review & quality
19,178 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
kensaurus/cursor-kenji/skills/mobile-emulator-test Skill
8★ repoQA a native Android build end-to-end on the emulator. Use for "test on emulator", "QA Android build", "verify native build", "white screen", "cache rehydration", "Expo dev-client QA", "adb reverse". Pairs Metro/adb walk with Supabase + Sentry MCPs for three-layer CRUD verification.
kensaurus/cursor-kenji/skills/mushi-integration Skill
8★ repoFull end-to-end Mushi Mushi integration smoke test: bug capture → AI triage → story mapping → TDD test generation → approval → execution → PDCA cycle. Use when "test mushi integration", "verify full pipeline", "mushi e2e check", "does mushi work end-to-end", "smoke test mushi", or after deploying changes.
kensaurus/cursor-kenji/skills/plan-input-validation Skill
8★ repoAudit every trust boundary for unvalidated input, injection, and forged-request gaps, then produce a phased hardening plan. Use when the user says "validate my inputs", "is my app injection-safe", "check my forms", "XSS", "dangerouslySetInnerHTML", "my Stripe webhook", "can someone forge requests", or is hardening before launch. AI code has happy-path bias: missing Zod, dangerouslySetInnerHTML without DOMPurify, webhook signature gaps (empty or unchecked signing secrets), raw-body signature mistakes, missing idempotency. Stack-aware for Supabase, Stripe, Next.js. Plan only until each phase is approved. Pairs with plan-rls-audit, plan-security-audit, audit-fe-api. Do NOT use for row access (plan-rls-audit) or secrets (plan-secrets-audit).
kensaurus/cursor-kenji/skills/plan-mobile-readiness Skill
8★ repoAudit a Capacitor/React Native app for App Store and Google Play submission readiness, then produce a phased pre-submission plan. Use when the user says "is my app ready for the App Store", "will Google Play reject this", "pre-submission check", "privacy manifest", "data safety form", or is preparing a mobile launch. Audits PrivacyInfo.xcprivacy, permission/Data-Safety match, IAP via store billing, target API level, demo creds, and placeholder UI. Plan only until approved. Pairs with mobile-capacitor-platform, enhance-capacitor-ui, plan-stub-checker. Do NOT use for perf tuning or screen polish.
kensaurus/cursor-kenji/skills/plan-secrets-audit Skill
8★ repoAudit a codebase and git history for exposed credentials and mis-scoped keys, then produce a phased rotation-and-remediation plan. Use when the user says "check for hardcoded secrets", "are my API keys exposed", "did I commit a key", "secret scan", "is my .env safe", "rotate keys", or is hardening before launch or open-sourcing. Vibe-coded apps ship keys in client bundles; secrets committed once live in git history forever — ROTATE, not just relocate. Scans sk_/pk_/whsec_/service_role, separates safe-client (anon, publishable) from never-client (service_role, secret), flags history needing rotation, checks NEXT_PUBLIC_ exposure and Vercel/AWS env config. Plan only until approved. Pairs with plan-rls-audit. Do NOT use for RLS logic or input validation.
kensaurus/cursor-kenji/skills/plan-stub-checker Skill
8★ repoExhaustive audit for stubs, dead buttons, fake/placeholder components, unwired handlers, dead links, orphans, and severed integrations — produces a burndown and wiring plan with no implementation in this pass. Traces intended backend, Supabase, Sentry, and data-pipeline targets; conservative false-positive filtering. Plan only — user approves before wiring. Uses codebase static analysis + optional Playwright/Sentry/Supabase MCP. Use when asked to "find dead buttons", "stub checker", "fake components", "unwired handlers", "dead links", "orphaned components", "plan stub wiring", "what's not connected", "mock data in prod", "buttons that do nothing", or "stub audit".
kensaurus/cursor-kenji/skills/protocol-browser-anti-stall Skill
8★ repoPrevent browser automation from freezing, stalling, or colliding between parallel agents, and enforce manual, headed, real-user driving (never scripted). Standardizes on the playwright-cli (`npx --yes @playwright/cli@latest`) with named sessions (`-s=<name>`) so multiple agents each get their own isolated browser — replacing the single-instance Playwright MCP, where one shared profile could only be locked by one process at a time. Covers session naming, headed mode, persistent auth profiles, the wait/anti-loop budget, evidence-before-retry, artifact paths, and cleanup. Use BEFORE any browser automation — testing webapps, user-story walkthroughs, QA/UX audits, visual verification, or any task that drives a browser.
kensaurus/cursor-kenji/skills/test-qa Skill
8★ repoGeneric webapp QA fallback — use only when no project-specific QA skill applies (project-local QA skills take precedence; use mobile-emulator-test for native builds). For unit tests use test-unit. Drives a visible (headed) browser manually through the Playwright MCP like a real user — clicking and typing one action at a time, never via scripts or test runners. Auto-discovers pages, entities, and auth from the codebase, generates user stories, performs real CRUD with data-pipeline verification (FE -> API -> DB -> FE), audits UX quality, tests edge cases, and produces a pass/fail report. Use when asked to "QA the app", "test the app", "find bugs", "run QA", "test CRUD", "smoke test", "check for dead buttons", or "test like a real user" AND no project-specific QA skill matches the repo.
kensaurus/cursor-kenji/skills/workflow-environment-ready Skill
8★ repoProve the working environment is actually runnable before starting a long or autonomous task, so a multi-hour run does not fail at the finish line on a missing tool, dependency, service, or credential. Detect the stack, verify runtimes and package installs, confirm required services and env vars are reachable (without printing secrets), and confirm the real verification commands execute. Use when "set up the environment", "is this ready to run", "before we start the big task", "preflight the repo", "why won't the tests run", or at the start of any burndown / complete-everything / long agent run.
kensaurus/cursor-kenji/skills/workflow-git-commit Skill
8★ repoGenerate clear, descriptive commit messages following conventional commits format. Use when committing code, writing commit messages, or when the user asks for help with git commits.
kensaurus/cursor-kenji/skills/workflow-launch-ready Skill
8★ repoFull launch preparation sweep for a new app or major release. One entry point that sequences enhance-web-seo, enhance-pwa, audit-bundle-size, audit-i18n, workflow-quality-gate, deploy-verify, and iterate-post-launch. Produces a launch checklist with all open items and a launch-readiness verdict. Use when "prepare for launch", "launch week", "everything before going live", "is the app launch-ready?", "pre-launch sweep", or "ship it to the world".
kensaurus/cursor-kenji/skills/workflow-quality-gate Skill
8★ repoPre-release quality gate that sequences test-red-team, audit-security, audit-bundle-size, audit-performance, and test-unit into a single sweep. Produces a go/no-go verdict with a ranked defect list. Use when "is this ready to ship?", "quality gate", "pre-release checklist", "what do I need to fix before launch?", "ship-readiness check", or before any production release.
kabirnarang39/skillci/skills/skillci-guardrails Skill
8★ repoUse this skill whenever you create, edit, or review a Claude Skill — any SKILL.md file, or the eval cases/config next to one. Most SKILL.md files today are written or edited by an agent, not typed by hand, so this closes the loop by having the agent that just wrote the skill also author it defensively and verify it, the same way a linter and test suite run after any other code change. Trigger phrases include "write a skill", "create a SKILL.md", "add a new skill", "edit this skill", "update the skill's frontmatter/description/triggers", or any diff that touches a SKILL.md path.
cbdreamer11/CB-loop-kit-claude-plugin/skills/loop-verify Skill
8★ repoRuns this project's verification contract and decides honestly whether something is verified, a gap, or a lie. Use before calling anything done, and whenever a report says "should work".
ericluo04/claude-academic-workflow/skills/council Skill
no license8★ repoSpawn five independent critic subagents in parallel on any target (research idea, draft, R&R strategy, grant, experimental design, pre-analysis plan, talk plan, IRB protocol, or a SKILL.md), then a separate synthesis pass ranks findings by how load-bearing they are, never by vote count. Default roster is tuned for quantitative marketing; --chef-skill swaps in a skill-design roster. TRIGGER on "council", "spawn critics", "parallel critique", "kitchen cabinet", "panel review", "stress-test this", "poke holes in this", "what would five experts say". Use review-paper for a complete manuscript, slide-review for an existing deck, and preregister to draft (not critique) a prereg.
ericluo04/claude-academic-workflow/skills/review-paper Skill
no license8★ repoRun a full referee review of a manuscript, six agents in parallel (spelling and style, internal consistency, unsupported claims, math and notation, tables and figures, adversarial top-journal referee), findings triaged CRITICAL/MAJOR/MINOR against a named target journal (MKSCI, JMR, JCR, MS, AER, QJE, JPE, Econometrica, REStud, AEJMacro, JME, RED, JF, JFE, RFS, JFQA). Writes a dated pre-submission report on your own draft, or with --referee a submittable referee report for a journal. Includes a buried-contribution desk-reject gate and a --quick pass. TRIGGER on "review my paper", "referee my draft", "is this ready to submit", "what would a referee say", "desk reject risk", "read this like Reviewer 2", "referee this for [journal]", "write my referee report", "I'm reviewing this submission", or any request to critique a full paper or PDF.
ericluo04/claude-academic-workflow/skills/slide-review Skill
no license8★ repoRender a Quarto reveal.js deck, screenshot every slide in a real browser, and review the pictures for overflow, unreadable type, low contrast, broken figures, failed math, and a weak argument, on a light talk deck or a dark lecture deck, and check that an offline-variant deck still works with no network. TRIGGER on "review my slides", "check my deck", "audit my slides", "pre-talk check", "pre-flight my deck", "am I ready to present", "are my slides readable", "will this deck work offline", "does my math render", "is anything cut off", "did my slides overflow", or before a seminar, job talk, conference talk, or lecture. Works on .qmd or an already-rendered .html; handles Yale talk and lecture themes. macOS toolchain: quarto, deck-check.mjs on node 22, Playwright MCP, pdfread.py.
ericluo04/claude-academic-workflow/skills/tikz-iterate Skill
no license8★ repoCompile a TikZ diagram, rasterize it to PNG with ghostscript, have the tikz-reviewer subagent actually look at the image, apply the surgical fixes it returns, and repeat until APPROVED or 5 rounds elapse. TRIGGER when asked to polish, fix, debug, or iterate on a TikZ figure, a Beamer diagram, a .tikz or .tex snippet, or a DiD / parallel-trends / event-study / DAG / coefficient-plot figure whose labels overlap or that "looks wrong", and on "compile and review this tikz". macOS toolchain: latexmk from MacTeX plus gs.
Dental evidence report artifact
Tuminha/dental-ai-skills/dental-evidence-report-artifact Skill
8★ repoUse when the user asks to turn a completed dental evidence review, paper critique, retrieval log, or statistical forensics audit into a polished HTML, PDF-ready, journal-club, teaching, or shareable report artifact. This skill formats already-completed analysis; it must not invent evidence, citations, effect sizes, or conclusions.
Tuminha/dental-ai-skills/research-critic Skill
8★ repoUse when the user asks to critique, peer-review, appraise, assess the credibility of, or evaluate the methodology, statistics, or bias of a single dental or oral-health research paper. Use for RCTs including split-mouth, cluster, and crossover designs; observational studies; diagnostic accuracy studies; systematic reviews and meta-analyses; animal studies; in-vitro dental studies; abstracts; and preprints. Do not use as the primary skill when the user asks what the body of evidence says or whether to change practice.
0xMassi/claude-skills/github-standards Skill
8★ repoGitHub repository standards and workflow rules. Use when creating repos, opening PRs, pushing code, setting up CI, creating branches, writing READMEs, or reviewing repo hygiene. Covers commit format (complements git-commit skill), PR message template, sensitive data pre-commit checks, repo naming, README requirements, branch naming, .gitignore baseline, release tagging, and CI/CD baseline. Derived from conventions across 22+ repositories.
mcmespinaa/folder-structure-protocol/.claude/skills/stage-review Skill
no license8★ repoReviews a completed pipeline stage before advancing to the next one. Verifies all declared outputs exist, runs the stage's Review Checkpoint criteria, checks quality against the Process intent, and confirms downstream readiness. Use when: reviewing stage output, checking if ready to advance, verifying stage completion.
jpoindexter/nd-skills/skills/nd-hyperfocus-guard Skill
8★ repoDetect and name hyperfocus sessions that have gone deep on a rabbit hole. Surface the original goal and offer a structured way back.
jpoindexter/nd-skills/skills/nd-selfmonitor Skill
8★ repoBefore destructive or hard-to-reverse operations, pause to verify the action matches the stated goal. A one-sentence pre-flight check, not a gate.
jpoindexter/nd-skills/skills/nd-velocity-check Skill
8★ repoTrack and surface the ratio of ideas captured vs items shipped. Warn when the capture:ship ratio is high — the ideas-rich/finish-poor pattern made visible.
Dragoon0x/taste-skills/skills/articulation/critique-vocabulary Skill
8★ repoPrecise language for design feedback. Ban vague words. Name what you actually see. Use when giving design feedback, running critiques, or training teams to communicate about quality.
Dragoon0x/taste-skills/skills/articulation/written-critique Skill
8★ repoWrite a structured design review that someone can act on without follow-up questions. Use when giving async design feedback, writing portfolio case studies, or documenting design decisions.
Dragoon0x/taste-skills/skills/team-practice/design-critique Skill
8★ repoRun taste-informed design reviews using Observation > Principle > Question. Use when facilitating design critiques, improving feedback quality on a team, or building a shared vocabulary for quality.
matematicsolutions/awesome-matematic-skills-pl/dev-mcp/skills/matematic-patron-pr-review-pl Skill
8★ repoPolish hub of legal-AI skills - 41 skills in 8 Claude Code / Cowork bundles (LLM output verification, PL/EU case law, DOCX redline, AI Act audit bundle). GDPR-safe, vendor-neutral, MIT.
matematicsolutions/awesome-matematic-skills-pl/fundament-weryfikacyjny/skills/adversarial-legal-review-pl Skill
8★ repoPolish hub of legal-AI skills - 41 skills in 8 Claude Code / Cowork bundles (LLM output verification, PL/EU case law, DOCX redline, AI Act audit bundle). GDPR-safe, vendor-neutral, MIT.
matematicsolutions/awesome-matematic-skills-pl/jakosc-tresci/skills/marko-pl-content Skill
8★ repoPolish hub of legal-AI skills - 41 skills in 8 Claude Code / Cowork bundles (LLM output verification, PL/EU case law, DOCX redline, AI Act audit bundle). GDPR-safe, vendor-neutral, MIT.
sgomez/developer-skills/skills/review-pr Skill
8★ repoReviews a change (PR/MR) diff against main, posts inline review comments and a summary, then marks it ready for review. Tracker- and host-agnostic — GitHub via gh is the factory default; docs/agents/code-host.md overrides. Use when user says "review pr", "review this pr", "/review-pr", or wants to run automated review on a pull request.
stark-ai-de/agent-skills/incubator/skills/productivity/grill-plan Skill
8★ repoRelentlessly question a plan, design, migration, release, or repo maintenance proposal until assumptions, risks, constraints, and decision branches are clear. Use when the user wants to be grilled before implementation or wants a plan challenged.
stark-ai-de/agent-skills/incubator/skills/repo-maintenance/dependency-update-review Skill
8★ repoReview dependency updates, package manager changes, lockfile diffs, version bumps, and dependency risk. Use when the user asks whether dependency updates are safe, wants to upgrade packages, or needs a dependency PR reviewed.
stark-ai-de/agent-skills/incubator/skills/repo-maintenance/pr-review Skill
8★ repoReview pull requests for correctness, maintainability, tests, security, docs impact, release risk, and agent-induced failure modes. Use when the user asks for a PR review, diff review, merge readiness check, or maintainer feedback.
stark-ai-de/agent-skills/incubator/skills/repo-maintenance/release-manager Skill
8★ repoPrepare repository releases. Use when the user asks to draft release notes, update changelog, check semver, verify CI, create a release checklist, or decide whether a public repo is ready to tag and publish.
stark-ai-de/agent-skills/incubator/skills/repo-maintenance/security-baseline-review Skill
8★ repoReview public repository security hygiene at a baseline maintainer level. Use when the user asks for secret-leak checks, SECURITY.md review, dependency hygiene, GitHub settings checklist, CI safety, or public release security readiness.
stark-ai-de/agent-skills/incubator/skills/skill-maintenance/skill-authoring-review Skill
8★ repoCreate or review Agent Skills with correct SKILL.md frontmatter, trigger descriptions, concise workflow design, progressive disclosure, references, scripts, assets, safety rules, and installability. Use when writing a new skill, improving an existing skill, or validating a public skills repo.
stark-ai-de/agent-skills/skills/codex-operations/codex-spec-interviewer Skill
8★ repoInterview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
quivly/skills/customer-engineering/customer-health-review Skill
8★ repoPerforms a structured customer health review using usage data, support interactions, renewal signals, and stakeholder sentiment. Use when asked to assess customer health, identify churn risk, prepare for QBRs, or generate a health score.
Google analytics data api basics
hamzabellouch/agent-skills/AI API and Agent Platform/google-analytics-data-api-basics Skill
8★ repoManages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized analytics reports, query metrics (like activeUsers, screenPageViews) and dimensions (like city, date), check metrics and dimensions compatibility, or verify API enablement.
Academic academic paper reviewer
hamzabellouch/agent-skills/Academic and Scientific Research/academic-academic-paper-reviewer Skill
8★ repoMulti-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy, 審查論文, 論文審查, 模擬審查, 同儕審查, 幫我審這篇, 以審查人角度評估, 審查者校準, 논문 심사, 동료 심사, 모의 심사, 심사자 관점에서 평가, 심사자 보정.
hamzabellouch/agent-skills/Academic and Scientific Research/academic-academic-pipeline Skill
8★ repoOrchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow, 연구부터 논문까지, 연구 주제 설정부터 논문 완성까지, 논문 전체 워크플로.
hamzabellouch/agent-skills/Academic and Scientific Research/academic-deep-research Skill
8★ repoUniversal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, WHY HOW WHAT papers, 3W literature scan, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 三段式文獻掃描, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題, 심층 연구, 문헌 조사, 체계적 문헌고찰, 메타분석, 사실 확인, 연구 방향을 잡아줘, 연구 주제 정하는 것을 도와줘.
The same file is in 2 other repositories
hamzabellouch/agent-skills/Academic and Scientific Research/academic-nature-nature-figure Skill
8★ repoCreate, revise, audit, and export submission-grade scientific figures for Nature-family and other high-impact venues in Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap), including multi-panel plots, figures4papers-style work, and journal-ready SVG/PDF/TIFF outputs. Use for paper or scientific plots, manuscript data visualization, 论文配图、学术写作配图、科研绘图、科研作图、画图、作图、出图、论文图表、可视化. Define the conclusion, evidence logic, data integrity, template compatibility, export needs, and reviewer risks before plotting; honor or persist the Python/R backend choice. Also use the separate OpenRouter GPT Image 2 route for explicit AI-generated graphical abstracts, mechanism diagrams, concept schematics, 论文示意图、机制示意图、图形摘要; this route skips backend choice and treats outputs as drafts. Do not use for interactive dashboards, statistics-only analysis, data cleaning, literature review, code debugging, pure photo editing, or Illustrator/Figma-first infographics without manuscript-figure intent.
Academic nature nature reviewer
hamzabellouch/agent-skills/Academic and Scientific Research/academic-nature-nature-reviewer Skill
8★ repoSimulate a Nature-style reviewer assessment from the referee perspective rather than an author rebuttal. Use when the user wants a pre-submission review, reviewer report, peer-review style critique, novelty/significance/technical soundness assessment, reviewer-style manuscript evaluation, 审稿人视角评估, 预审稿意见, or Nature reviewer report. Return 3 reviewer reports plus a cross-review synthesis, grounded only in the local Nature reviewer source basis. Also trigger on general pre-submission review requests during academic writing even without the word "Nature", such as getting a mock peer review for any journal, critiquing a draft as a reviewer would, assessing novelty/rigor before submission, and Chinese phrasings like 审稿人视角、模拟审稿、预审、帮我审一下论文、投稿前自审、审稿意见模拟、找论文问题.
Supply chain security sbom slsa
hamzabellouch/agent-skills/DevSecOps and Supply Chain Security/supply-chain-security-sbom-slsa Skill
8★ repoComprehensive framework for software supply chain security incorporating Software Bill of Materials (SBOM) generation/validation, SLSA (Supply-chain Levels for Software Artifacts) provenance compliance, image signing with Cosign/Sigstore, and automated pipeline verification.
Gws recipe review meet participants
hamzabellouch/agent-skills/Google Workspace Automation/gws-recipe-review-meet-participants Skill
8★ repoReview who attended a Google Meet conference and for how long.
The same file is in 2 other repositories
Gws recipe review overdue tasks
hamzabellouch/agent-skills/Google Workspace Automation/gws-recipe-review-overdue-tasks Skill
8★ repoFind Google Tasks that are past due and need attention.
The same file is in 2 other repositories
hamzabellouch/agent-skills/Software Engineering and Workflows/code-review-and-quality Skill
8★ repoConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
The same file is in 5 other repositories
hamzabellouch/agent-skills/Software Engineering and Workflows/git-workflow-and-versioning Skill
8★ repoStructures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.
The same file is in 2 other repositories
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-caveman-cavecrew Skill
8★ repoDecision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
The same file is in 7 other repositories
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-caveman-cavecrew/cavecrew Skill
8★ repoDecision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
The same file is in 7 other repositories
Workflow caveman caveman commit
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-caveman-caveman-commit Skill
8★ repoUltra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
The same file is in 2 other repositories
Workflow caveman caveman review
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-caveman-caveman-review Skill
8★ repoUltra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
The same file is in 11 other repositories
Workflow superpowers finishing a development branch
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-superpowers-finishing-a-development-branch Skill
8★ repoUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
The same file is in 5 other repositories
Workflow superpowers receiving code review
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-superpowers-receiving-code-review Skill
8★ repoUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
The same file is in 6 other repositories
Workflow superpowers requesting code review
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-superpowers-requesting-code-review Skill
8★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
The same file is in 4 other repositories
Workflow superpowers using git worktrees
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-superpowers-using-git-worktrees Skill
8★ repoUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
The same file is in 5 other repositories
Workflow superpowers verification before completion
hamzabellouch/agent-skills/Software Engineering and Workflows/workflow-superpowers-verification-before-completion Skill
8★ repoUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
The same file is in 40 other repositories