agentsclimarketplace

Review & quality

19,016 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

  • Github webhooks

    bertbertov/claude-stack/skills/github-webhooks Skill

    0★ repo

    Receive and verify GitHub webhooks. Use when setting up GitHub webhook handlers, debugging signature verification, or handling repository events like push, pull_request, issues, or release.

  • N8n validation expert

    bertbertov/claude-stack/skills/n8n-validation-expert Skill

    0★ repo

    Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities. Consult this skill whenever a validate_node or validate_workflow call returns errors or warnings — it knows which warnings are false positives and which errors need real fixes.

    The same file is in 2 other repositories

  • Pentest source code scanning

    bertbertov/claude-stack/skills/pentest-source-code-scanning Skill

    0★ repo

    Security-focused source code review and SAST. Scans for vulnerabilities (OWASP Top 10, CWE Top 25), CVEs in third-party dependencies/packages, hardcoded secrets, malicious code, and insecure patterns. Use when given source code, a repo path, or asked to "audit", "scan", "review" code security, or "check dependencies for CVEs".

  • Security review

    bertbertov/claude-stack/skills/security-review Skill

    0★ repo

    Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

    The same file is in 3 other repositories

  • Tob differential review

    bertbertov/claude-stack/skills/tob-differential-review Skill

    0★ repo

    Performs security-focused differential review of code changes (PRs, commits, diffs). Adapts analysis depth to codebase size, uses git history for context, calculates blast radius, checks test coverage, and generates comprehensive markdown reports. Automatically detects and prevents security regressions.

    The same file is in 4 other repositories

  • Tob git cleanup

    bertbertov/claude-stack/skills/tob-git-cleanup Skill

    0★ repo

    Safely analyzes and cleans up local git branches and worktrees by categorizing them as merged, squash-merged, superseded, or active work.

    The same file is in 3 other repositories

  • Tob second opinion

    bertbertov/claude-stack/skills/tob-second-opinion Skill

    0★ repo

    Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks for a second opinion, external review, codex review, gemini review, or mentions /second-opinion.

    The same file is in 3 other repositories

  • Garelier guardian

    aby-studio-works/garelier/skills/garelier-guardian Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/guardian invocation, not on generic security / license / dependency wording. The security / privacy / dependency / license / provenance GATE for a Garelier merge or promote — diff scan for leaked secrets / tokens / private keys / credentials, customer data or PII, real data in fixtures or logs, vulnerable or malicious dependencies, forbidden or unknown licenses, copyright/provenance risk in curated knowledge, or dangerous auth / crypto / logging / CI / deploy / infra / migration changes. Commit-free on an ephemeral gavel branch; reads Librarian security/ knowledge; emits verdict PASS / PASS_WITH_NOTES / BLOCK / NO_OPINION; gates, never fixes. Also fires on gavel / preflight / delta gate / final gate / redact. Requires garelier-core.

  • Garelier observer

    aby-studio-works/garelier/skills/garelier-observer Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/observer invocation, not on generic review/merge/second-opinion wording. Observer is a commit-free, read-only, branch-free sidecar (detached HEAD, no lane.lock; allowed in dock and artisan lanes) giving an INDEPENDENT review layer plus non-binding direction advice. It reads diffs, assignments, blueprints, reports, and quality-gate output and returns an observation report (verdict PASS / PASS_WITH_NOTES / REWORK_RECOMMENDED / BLOCK / NO_OPINION) or advice; never writes code, commits, merges, changes acceptance criteria, or makes PM/user decisions. Requestable by Dock (premerge of Worker/Smith/Librarian into studio), Artisan (premerge of satchel into studio), and Worker (in-scope advice). Activate in a `__garelier/<pm_id>/_observers/<id>/` worktree, when an observer assignment.md appears, when answers.md arrives after BLOCKED, when abort.md appears, when Dock/Artisan/Worker requests review or advice, or on "observer", "independent review", "merge/premerge review", "code direction advice", "second pair of eyes". Requires garelier-core.

  • Garelier wanderer

    aby-studio-works/garelier/skills/garelier-wanderer Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/wanderer invocation, not on generic peer-review/advisor/design-review wording. Wanderer is the external, advisory-review role — a separately-launched Codex or Claude Code session (not a subagent, not headless) reviewing the PM's design work (Garelier blueprints, project design specs) over the file-based peer-channel (DEC-076). Commit-free, decision-free (PM/user own the mutual-agreement sign-off), a SINGLETON, takes no lane/branch, reads read-only; if absent, silent past a timeout, rate-limited, or unavailable, the PM falls back to the Observer subagent. Activate when running as the Wanderer peer (a Codex/Claude session whose .codex or hook config points at the peer-channel under `runtime/peer/<channel>/` with presence), when a peer review_request/advice_request appears in the Wanderer inbox, or on "wanderer", "放浪者", "peer review", "external advisor", "design review", "peer-channel". Requires garelier-core.

  • Garelier worker

    aby-studio-works/garelier/skills/garelier-worker Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/worker invocation, not on generic implement/fix/branch/report wording. Worker role for the Garelier multi-agent framework: reads one assignment from Dock, cuts a workbench branch off the integration branch (garelier/<target-slug>/<pm_id>/studio), implements, runs the project quality gate locally, writes a completion report, waits for Dock review. Handles all commit-producing tasks (features, bug fixes, refactors, dependency upgrades, docs, data-change scripts). Activate in a `__garelier/<pm_id>/_workers/<id>/` worktree, when assignment.md appears in the worker's directory, when review.md signals rework, when answers.md arrives after a BLOCKED state, or when a track-target.md trigger appears. Requires garelier-core.

  • Vault lint

    slogsdon/skills-vault-knowledge/skills/vault-lint Skill

    0★ repo

    Use when /vault-lint is invoked or when Shane wants a weekly vault health check. Scans Concepts/ and the broader vault for contradictions, orphan pages, missing Concept pages, and stale claims.

  • Pm launch reviewer

    kalyvask/pm-evaluation-framework/.claude/skills/pm-launch-reviewer Skill

    0★ repo

    Review a launch plan against the repo's launch-criteria template and failure-management playbook. Use when the user is preparing a launch (closed beta, limited GA, full GA) and wants a pre-flight review, or is staring at a checklist of "ready" gates that all happen to be owned by the same person. Surfaces missing gates, unowned criteria, vague readiness bars, and the one or two failure modes most likely to show up post-launch. Returns a gate-by-gate verdict and a launch-or-defer recommendation.

  • Pm prd drafter

    kalyvask/pm-evaluation-framework/.claude/skills/pm-prd-drafter Skill

    0★ repo

    Draft or critique a PRD against the repo's PRD template and problem-framing rubric. Use when the user is starting a PRD, sharing a PRD draft for review, or stuck on a specific PRD section (problem statement, success metrics, scope, kill criteria). Pushes back on vague problem statements, generic success metrics, and feature-laundry-list scope. Returns either a structured PRD draft or a section-by-section critique with specific re-writes.

  • Pm red team

    kalyvask/pm-evaluation-framework/.claude/skills/pm-red-team Skill

    0★ repo

    Adversarially re-review a PM artifact, recommendation, or AI-generated critique that already exists. Use as a second pass after another skill (pm-evaluator, pm-prd-drafter, pm-decision-coach, pm-value-hypothesis-tester) has produced output, or on any external AI output the user wants pressure-tested before deferring to it. Plays the role of a hostile exec, skeptical board member, or competing PM — looking for what the first pass missed, what bias it brought, and what would not survive a real review. Returns the three load-bearing holes, what's already strong enough to keep, and the specific re-writes that would close the gaps.

  • Pm weekly review

    kalyvask/pm-evaluation-framework/.claude/skills/pm-weekly-review Skill

    0★ repo

    Run the Friday PM weekly review — what got done, what slipped, what's worth renegotiating, what's on next week. Reads each active project's state, pulls the week's Granola transcripts and calendar, surfaces patterns across projects (stakeholders going cold, decisions deferred, todos rotting). Writes the review to `pm-state/inbox/YYYY-MM-DD-weekly-review.md`. Use late Friday afternoon before logging off.

  • Integration validator

    merge-api/merge-unified-skills/skills/integration-validator Skill

    0★ repo

    Validate a Merge Unified API integration end-to-end. Use when a developer says "validate my Merge integration", "test my Merge setup", "is my Merge connection working", "debug my Merge API call", "verify my Linked Account", "check my Merge scopes", "my Merge API returns empty", "Merge sync not working", "check my account_token", or after completing /merge-unified:onboarding. Runs diagnostic checks against the Merge API and outputs a pass/fail checklist with actionable fixes.

  • Nft provenance

    Spacetime-Technology/chia-skills/skills/nft-provenance Skill

    0★ repo

    Trace a Chia NFT from mint through every transfer to its current owner. Given a launcher_id (or any coin in the lineage), walks the full chain of custody, classifies each step, and surfaces the current holder address. Use when the user wants to verify NFT history, check an NFT before buying, prove authenticity, or research a collection. Accepts launcher_id, include_metadata as arguments for programmatic invocation.

  • Offer safety check

    Spacetime-Technology/chia-skills/skills/offer-safety-check Skill

    0★ repo

    Decode a Chia offer1... string, classify what's being traded on each side, fetch market prices, and surface a risk report before the user takes it. Use when the user pastes an offer they were sent, asks "is this offer fair?", or wants to vet a deal before opening their wallet. Accepts offer, max_unfavourable_pct as arguments for programmatic invocation.

  • Grill me

    markbain/bain-skills/grill-me Skill

    no license0★ repo

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

    The same file is in 3 other repositories

  • Full review

    cabbagecachekid/red-pen/skills/full-review Skill

    0★ repo

    Runs a structured multi-pass review of human-facing professional copy and presents findings as a before/after diff table with reasoning, lists what was deliberately left out, and waits for explicit sign-off before changing anything. The passes are AI tells, operator-vs-academic positioning, honesty and overclaim (catching silently inflated claims), tone and positioning, voice register, and fact verification. Use at any stage of refining or expanding copy with AI — not just at the end — when reviewing or workshopping a resume, cover letter, portfolio page, case study, proposal, or bio, when the user asks to "review my copy", "do a full review", "run the full pass", or polish writing for hiring managers or clients.

  • Leadup deploy checker

    leadupofficial/leadup-claude-skills/leadup-deploy-checker Skill

    0★ repo

    Check whether a LeadUp project is ready to deploy to leadup-server / Coolify. Verifies Docker build, env variable coverage, ports, Coolify config, GitHub branch, domain/subdomain, migrations, and a rollback plan, then outputs a READY / NOT READY verdict. Use when the user says "prepare deploy", "deploy checker", "make Docker work", "Coolify deploy", "leadup-server deploy", or "production ready".

  • Leadup pii risk reviewer

    leadupofficial/leadup-claude-skills/leadup-pii-risk-reviewer Skill

    0★ repo

    Review a LeadUp app, SaaS project, CRM, or client website for personal-data and privacy risks. Builds a PII inventory, identifies storage and access scope, scores risk levels, recommends masking and encryption, sets retention windows, designs export/delete flows, and drafts consent and privacy-policy notes aligned with India DPDP, IT Rules, and GDPR where applicable. Use when the user says "PII review", "personal data", "privacy risk", "customer data", "data protection", "sensitive data", "GDPR", or "India DPDP".

  • Leadup security review

    leadupofficial/leadup-claude-skills/leadup-security-review Skill

    0★ repo

    Run a security review of a LeadUp project. Checks committed secrets and .env handling, auth and admin protection, multi-tenant isolation, database exposure, file uploads, payments and webhook verification, and server/deploy risks, then reports findings by severity. Use when the user says "security review", "check secrets", "is this safe", "audit project", "check .env", or "payment security".

  • Code review for quant

    jefrnc/quant-llm-skills/skills/code-review-for-quant Skill

    0★ repo

    Use when reviewing or writing Python/Go/SQL code for quant research, backtests, market-data pipelines, or trading systems. Provides a structured checklist of failure modes specific to time-series financial code (lookahead, splits, snapshots, currency, NaN propagation, joint-filer dedup) that generic code review skips.

  • Ebay prepare listing

    glebmish/lifeops-skills/plugins/ebay-listing/skills/ebay-prepare-listing Skill

    0★ repo

    Create an eBay listing from photos and a description — research item, verify specs, check sold comps, produce listing.json. Use when the user wants to sell something, list an item on eBay, or says things like "sell this", "list this on eBay", "how much is this worth", or provides photos of items they want to sell.

  • Review

    kuro0107/madamisu-skills/plugins/madamisu/skills/review Skill

    0★ repo

    【内部用・自動起動禁止】ユーザーが明示的に /madamisu:review と入力した場合のみ起動可。それ以外では絶対に呼び出さない。設定資料/ フォルダ内の全Markdownを読み込み、設定間の矛盾(キャラ↔タイムスケジュール、世界観↔行動、ゲームルール↔各設定)を検査する(ファイルは変更しない)。

  • Grill docs

    wachawo/claude-skills/skills/grill-docs Skill

    0★ repo

    A "grilling" session that stress-tests your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) as decisions crystallize. Use when the user wants to stress-test a plan against the project's language and documented decisions.

  • Grill me

    wachawo/claude-skills/skills/grill-me Skill

    0★ repo

    Mercilessly interrogate the user about their plan or design until shared understanding is reached and every branch of the decision tree is resolved. Use when the user wants to stress-test a plan, be "grilled" on a design, or mentions "grill me".

  • Review security

    wachawo/claude-skills/skills/review-security Skill

    0★ repo

    Perform language- and framework-specific security best-practice reviews and propose improvements. Activate only when the user explicitly requests security best-practice guidance, a security review/report, or help writing secure-by-default code. Activate only for supported languages (python, javascript/typescript, go). Do not activate for general code review, debugging, or tasks unrelated to security.

  • Setup pre commit

    wachawo/claude-skills/skills/setup-pre-commit Skill

    0★ repo

    Configures Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repository. Use when the user wants to add pre-commit hooks, set up Husky, configure lint-staged, or wire formatting/type-checking/tests into the commit step.

  • Architecture rfc review

    alexzhu0/agent-ready-skills/skills/architecture-rfc-review Skill

    0★ repo

    Use when reviewing architecture RFCs, system design docs, diagrams, proposals, or technical decision records for tradeoffs, missing constraints, risk, and decision readiness.

  • Database migration risk review

    alexzhu0/agent-ready-skills/skills/database-migration-risk-review Skill

    0★ repo

    Use when reviewing schema migrations, SQL changes, data backfills, index changes, or rollout plans for data loss risk, locking, rollback gaps, validation checks, and production safety.

  • Dependency upgrade risk review

    alexzhu0/agent-ready-skills/skills/dependency-upgrade-risk-review Skill

    0★ repo

    Use when reviewing dependency upgrades, package-lock diffs, SDK version changes, release notes, or migration guides for breaking changes, security impact, tests, and rollout risk.

  • Repo launch readiness review

    alexzhu0/agent-ready-skills/skills/repo-launch-readiness-review Skill

    0★ repo

    Use when reviewing a small repository before public launch for README clarity, examples, license, metadata, validation commands, issue hygiene, release notes, and obvious trust gaps.

  • Security review checklist

    alexzhu0/agent-ready-skills/skills/security-review-checklist Skill

    0★ repo

    Use when reviewing feature specs, tool integrations, agent workflows, API changes, or launch plans for security concerns such as auth, secrets, data exposure, abuse paths, and approval gates.

  • Ralph review

    ezos26/claude-skills/skills/ralph-review Skill

    0★ repo

    Post-Ralph verification skill. Run after Ralph completes iterations to verify code quality, catch regressions, and fix findings. Usage /ralph-review [service] [iteration-range]. Example /ralph-review rideshare or /ralph-review tesla 10-20

  • Verification loop

    ezos26/claude-skills/skills/verification-loop Skill

    0★ repo

    A comprehensive verification system for Claude Code sessions.

    The same file is in 2 other repositories

  • Git wt

    to4iki/skills/engineering/git-wt Skill

    0★ repo

    Creates a Git worktree with `git wt` and implements changes in an isolated directory. After the work is done, removes the worktree pending user confirmation. Use when the user explicitly says "worktree", "branch off", "wt", "git-wt", etc.

  • Cross repo cherry pick

    OmarEltak/legacy-prod-survival-kit/skills/cross-repo-cherry-pick Skill

    0★ repo

    Use when you need to apply commits from one git repository to another whose history is unrelated. Common scenario; an old "dev" repo with N commits of undeployed work, and a fresh "prod-mirror" repo created from the live server. You want N-3 of those commits applied to the mirror without merging the histories. Handles the line-ending chaos (CRLF/LF) that occurs when source was on Windows and destination came from a Linux server. Includes a CRLF/LF detective sub-protocol.

  • Conventional commit pr

    sujanbhuiyan/Skills/skills/conventional-commit-pr Skill

    no license0★ repo

    Turns a code diff into Conventional Commit messages and a high-quality pull-request description. Use when committing staged or unstaged changes, when writing a commit message that follows the Conventional Commits spec, or when assembling a PR description with summary, changes, and a test-plan checklist.

  • Code reviewer

    kakarot-oncloud/claude-dev-skills/skills/code-reviewer Skill

    0★ repo

    Performs senior-level code review on a diff, file, or snippet. Surfaces bugs, security issues, performance problems, and design smells with severity tags and concrete fix suggestions. Use this skill when the user asks to "review this code", "check this PR", "look for issues", or pastes code for feedback.

  • Commit message writer

    kakarot-oncloud/claude-dev-skills/skills/commit-message-writer Skill

    0★ repo

    Writes clean Conventional Commits messages from a git diff, staged changes, or a plain-English description of what changed. Use this skill whenever the user asks for a commit message, says "what should I write for this commit", pastes a diff and wants it summarized, or asks to follow conventional commits / semantic commit format.

  • Pr description writer

    kakarot-oncloud/claude-dev-skills/skills/pr-description-writer Skill

    0★ repo

    Writes structured pull request descriptions from a diff, branch name, commit list, or plain-English summary. Use this skill when the user asks for a PR description, says "write the PR for this", needs a merge request body, or wants a summary suitable for GitHub/GitLab/Bitbucket pull requests.

  • Review systems

    aman-bhandari/claude-code-agent-skills-framework/.claude/skills/review-systems Skill

    0★ repo

    Systems-aware code review that extends the standard code-review skill. Checks resource management, memory footprint, GIL implications, fd hygiene, and failure modes at scale. Invoke with /review-systems.

  • Verify visual

    SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/verify-visual Skill

    0★ repo

    Visually verifies a compiled LaTeX PDF — renders pages to images, runs structural checks (page count, figures present, fonts embedded, no overfull/underfull warnings), optionally diffs against a reference PDF (diff-pdf or SSIM via ImageMagick), and iterates compile-render-analyze-fix until the document passes or a budget is exhausted. Use ONLY when the user explicitly asks to verify, check, validate, or visually inspect the output.

  • Jotbook pencil review

    koloskus/jotbook/skills/jotbook-pencil-review Skill

    0★ repo

    Review the pencil backlog and decide which provisional drafts to ink, drop, revise, edit, or keep.

  • Jotbook review

    koloskus/jotbook/skills/jotbook-review Skill

    0★ repo

    Review the jot backlog and dispatch decisions in place — drop, merge, tweak, pencil, or ink. Surfaces overlap between related jots and flags any with a pencil already in progress.

  • Payments testing

    Marcdaou/claude-qa-suite/qa-suite/skills/payments-testing Skill

    0★ repo

    Test Stripe payment flows in test mode using the Stripe API/MCP — the successful charge/checkout path that should create a booking, and the decline/failure paths (generic decline and 3DS/SCA-required) that the app must handle gracefully. Use this skill whenever the user wants to test payments, verify checkout, confirm a charge succeeds or a declined card is handled, or check Stripe integration before launch. Trigger on casual asks like "does paying actually work" or "test a declined card" too. Stripe TEST MODE only.

  • Security audit

    Marcdaou/claude-qa-suite/qa-suite/skills/security-audit Skill

    0★ repo

    Run a defensive security audit of a full-stack web app — exposed secrets and service-role keys, Supabase RLS gaps, auth bypass and IDOR on routes, Stripe webhook signature handling, input validation, insecure direct object references, and vulnerable dependencies. Use this skill whenever the user wants a security audit, a vulnerability check, to review auth, to find exposed keys/secrets, or to harden the app before launch. Trigger on asks like "is my app secure" or "check for leaked keys" too. Defensive use only.

  • Sast fileupload

    reasonless-throne486/sast-skills/sast-files/.agents/skills/sast-fileupload Skill

    0★ repo

    Detect insecure file upload vulnerabilities in a codebase using a three-phase approach: discovery (find all upload sites), batched verify (check extension bypass and related issues in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/fileupload-results.md. Use when asked to find file upload, unrestricted upload, or extension bypass bugs.

  • Sast idor

    reasonless-throne486/sast-skills/sast-files/.agents/skills/sast-idor Skill

    0★ repo

    Detect Insecure Direct Object Reference (IDOR) vulnerabilities in a codebase using a three-phase approach: recon (find candidates), batched verify (check authorization in parallel subagents, 3 candidates each), and merge (consolidate batch results). Checks endpoints for missing ownership or authorization checks on user-supplied identifiers. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/idor-results.md. Use when asked to find IDOR or authorization bypass bugs.

  • Sast jwt

    reasonless-throne486/sast-skills/sast-files/.agents/skills/sast-jwt Skill

    0★ repo

    Detect insecure JWT (JSON Web Token) implementations in a codebase using a two-phase approach: first map all JWT issuance and verification sites to understand the token lifecycle and signing configuration, then check each verification site for exploitable weaknesses such as algorithm confusion, missing signature verification, weak secrets, header injection, and missing claim validation. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/jwt-results.md. If no JWT usage is found in Phase 1, Phase 2 is skipped. Use when asked to find JWT, token forgery, or authentication bypass bugs.

  • Sast businesslogic

    reasonless-throne486/sast-skills/sast-files/.claude/skills/sast-businesslogic Skill

    0★ repo

    Detect business logic vulnerabilities in a codebase using a three-phase approach: threat modeling (domain analysis and attack scenarios), batched verify (check exploitable gaps in parallel subagents, 3 scenarios each), and merge (consolidate batch results). Covers price manipulation, workflow bypass, limit violations, race conditions, reward abuse, etc. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/businesslogic-results.md. Use when asked to find business logic, logic flaws, or abuse-of-function bugs.

  • Sast fileupload

    reasonless-throne486/sast-skills/sast-files/.claude/skills/sast-fileupload Skill

    0★ repo

    Detect insecure file upload vulnerabilities in a codebase using a three-phase approach: discovery (find all upload sites), batched verify (check extension bypass and related issues in parallel subagents, 3 sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/fileupload-results.md. Use when asked to find file upload, unrestricted upload, or extension bypass bugs.

  • Sast idor

    reasonless-throne486/sast-skills/sast-files/.claude/skills/sast-idor Skill

    0★ repo

    Detect Insecure Direct Object Reference (IDOR) vulnerabilities in a codebase using a three-phase approach: recon (find candidates), batched verify (check authorization in parallel subagents, 3 candidates each), and merge (consolidate batch results). Checks endpoints for missing ownership or authorization checks on user-supplied identifiers. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/idor-results.md. Use when asked to find IDOR or authorization bypass bugs.

  • Sast jwt

    reasonless-throne486/sast-skills/sast-files/.claude/skills/sast-jwt Skill

    0★ repo

    Detect insecure JWT (JSON Web Token) implementations in a codebase using a two-phase approach: first map all JWT issuance and verification sites to understand the token lifecycle and signing configuration, then check each verification site for exploitable weaknesses such as algorithm confusion, missing signature verification, weak secrets, header injection, and missing claim validation. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/jwt-results.md. If no JWT usage is found in Phase 1, Phase 2 is skipped. Use when asked to find JWT, token forgery, or authentication bypass bugs.

  • Android plan reviewer

    calvin-iyer/android-skills/plugins/android-skills/skills/android-plan-reviewer Skill

    0★ repo

    Validates Android implementation plans by spawning parallel review agents - one per section. Each agent checks its section against the actual Android codebase (gradle dependencies, AndroidManifest, ProGuard rules, signing config, SDK levels, Compose vs View claims) for wrong assumptions and researches the web for current Android SDK / Jetpack / Play Console / Material / Play Billing / Firebase guidance. Issues get corrected inline in the plan document. Loops until clean or max iterations reached. EXITS EARLY if not run inside an Android project. Use this skill whenever the user says "review plan", "validate plan", "check my plan", "audit plan", "plan review", "review Android plan", "validate Android implementation plan", "check gradle migration plan", wants to verify an Android plan against the codebase, wants to check an Android plan for correctness before implementation, or mentions validating assumptions in an Android plan document. Even if the user just says "review this" while pointing at an Android plan file, use this skill.

  • Guard

    puukis/lstack/skills/guard Skill

    0★ repo

    Enable maximum safety workflow by combining careful safety mode with a freeze edit boundary.

  • Reviewer

    puukis/lstack/skills/reviewer Skill

    0★ repo

    Code review producing only numbered actionable findings — no rewrites, no praise