agentsclimarketplace

Review & quality

19,040 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

  • Peppol validation

    whobat/AI-Agent-skills/skills/edi/peppol-validation Skill

    1★ repo

    Validate Peppol BIS 3.0 e-business documents (the UBL formats used for trade across DK and the EU) and tell whether a file is the current standard or an outdated schema. The bundled PowerShell script auto-identifies the document from its root element + cbc:CustomizationID, maps it to the right OpenPeppol ruleset, runs the full official validation (UBL 2.1 XSD + Peppol Schematron) via the OpenPeppol/Helger web service, and reports OK or the exact errors with rule IDs. Covers invoice, credit note (incl. self-billing), order + order response/change/cancellation, order agreement, catalogue + response, despatch advice, MLR, punch out. Use when the user wants to validate/check a Peppol or UBL document, confirm an invoice/order/despatch-advice is valid Peppol BIS 3.0, batch-check a folder of e-invoices, or find out whether a file is the new BIS 3.0 schema or an old one (e.g. CENBII/peppol28a). Do NOT use to CREATE or transform documents — only to validate existing XML.

  • Nav2009 development

    whobat/AI-Agent-skills/skills/nav-2009/nav2009-development Skill

    1★ repo

    Develop, review, and architect C/AL code and objects for Microsoft Dynamics NAV 2009 (Navision) — Classic client and RoleTailored Client (RTC). Covers C/AL coding patterns and performance idioms (FINDSET/FINDFIRST/ISEMPTY, SETCURRENTKEY, locking, COMMIT discipline), key/SIFT design, code-review checklist, customization architecture (hooks, setup tables, number series), reports (Classic sections and RDLC), integrations (XMLports, Dataports, NAS, web services, MSMQ/COM), and upgrade-friendly patterns toward Business Central. Use for any NAV 2009 / Navision / C/AL task — writing or reviewing code, designing a customization, building a report or integration, or preparing for a BC migration.

  • Nav2009 object management

    whobat/AI-Agent-skills/skills/nav-2009/nav2009-object-management Skill

    1★ repo

    Guide export, import, and compilation of Microsoft Dynamics NAV 2009 C/AL objects (.fob/.txt) through the Classic client's Object Designer — and verify the result via a read-only SQL query against the Object table. IMPORTANT REALITY CHECK this skill enforces - NAV 2009 has NO command-line interface for objects; finsql.exe "command=exportobjects" was introduced in NAV 2013 and fails on 2009 with "The program property 'command' is unknown" - never attempt it. Use when the user wants to export tables/codeunits/reports to .txt or .fob, import a .fob/.txt into a NAV 2009 database, compile objects, move customizations between NAV 2009 databases, or automate NAV 2009 object deployment (the answer is: manual Object Designer steps + SQL verification). A developer license is required for .txt export/import and compiling; .fob import works with an end-user license.

  • Fix one issue

    pricklywiggles/fractally-claude-marketplace/plugins/ship-it/skills/fix-one-issue Skill

    no license1★ repo

    Implement a single work-unit (a tracker issue or a described task) end to end in its branch: explore, make the smallest correct change, verify, and commit. Use for "implement this issue", "fix issue 123", "make this change and verify it". The implement stage of the ship-it orchestrator, and usable standalone on an issue or a described task. Not for review (use review-and-address), comments (comment-cleanup), or CI (ci-fix).

  • Open pr

    pricklywiggles/fractally-claude-marketplace/plugins/ship-it/skills/open-pr Skill

    no license1★ repo

    Push a finished branch and open its pull request with a complete, QA-ready body. Use for "open a PR for my branch", "push this and open the PR", "finalize this work-unit". Builds the PR body from ship-it.config prTemplate: a Summary, a tracker link, and a two-part Verification (automated checks run, plus a followable manual-QA checklist). The finalize stage of the ship-it orchestrator, and usable standalone on the current branch. Not for implementing (fix-one-issue), reviewing (review-and-address), or CI (ci-fix); it assumes the branch is already final and committed.

  • Review and address

    pricklywiggles/fractally-claude-marketplace/plugins/ship-it/skills/review-and-address Skill

    no license1★ repo

    Review a branch or the current diff with the project's configured reviewers run in parallel, merge their findings, and apply the warranted ones. Use for "review my changes", "review this PR/branch", "run the reviewers on the current diff with main", "review and fix the warranted feedback". Runs every reviewer in ship-it.config review.reviewers (e.g. pr-review-toolkit, vercel-react-best-practices). Also the review stage of the ship-it orchestrator. Not for watching or fixing CI (use ci-fix) or comment-only cleanup (use comment-cleanup).

  • Document stack

    pricklywiggles/fractally-claude-marketplace/plugins/stack-it/skills/document-stack Skill

    no license1★ repo

    Use this skill to document a project's tech stack so both the agents working in the repo (in CLAUDE.md) and the humans reading it (in the README) know what it's built on and how to run it. It documents from the stack-it lockfile (`.claude/stack-it/stack.yaml`) when one exists, and otherwise infers the stack by analyzing the codebase. Use it proactively whenever someone wants their stack written down, even if they don't name the files. Phrasings like "document my stack", "add a tech stack section to the readme", "write up what this project uses for Claude/agents", "put my dependencies in CLAUDE.md", "generate a tech-stack doc", "what's this project built with, document it", or running it as the final step after install-stack / scaffold-and-verify to capture the result. It writes an agent-facing stack summary (tools, pinned versions, how to build/test/lint/run, conventions, caveats) into CLAUDE.md and a human-facing Tech Stack + Getting Started into the README, both inside a refreshable managed block so re-running resyncs cleanly. It does NOT install, choose, research, or verify tools (those are install-stack, decide-stack, scaffold-and-verify), and it does not edit the stack YAML: here the YAML is read-only input. Not for writing general project prose, API docs, or code comments.

  • Scaffold and verify

    pricklywiggles/fractally-claude-marketplace/plugins/stack-it/skills/scaffold-and-verify Skill

    no license1★ repo

    Use this skill to prove a freshly installed project stack actually works before building anything real on it: generate the smallest example that exercises every chosen tool together, then run it until build, lint, tests, and the dev server are all green (plus a real-browser console check when there's a UI). This is the verification stage of the stack-it pipeline, after install-stack. Use it proactively, even when the user never says "verify", whenever a stack or its dependencies were just installed or scaffolded and someone wants confidence the pieces fit. Phrasings like "I just installed my stack, make sure it works", "build a minimal example that uses all of it and run it", "smoke-test my new project setup", "prove the stack works", "scaffold a smoke test", "keep fixing the example until tests/build/lint/the dev server pass", "do my pinned versions actually work together", or handing over a locked stack YAML plus an installed project and asking for confidence before building for real. It writes a thin end-to-end slice (e.g. a styled page with a form and one component test, or one API endpoint persisting through the ORM with a request test, or a CLI subcommand that runs), loops fix-and-retry until every check passes, and, when a chosen tool turns out broken or two pinned versions are fundamentally incompatible, stops and brings the user back to decide-stack rather than silently swapping or bumping. It does NOT design the architecture of the real app, and is not for choosing tools (use decide-stack), running the install commands (use install-stack), running or fixing tests in an existing or mature project, adding a dependency or feature to an app already under development, setting up CI configuration, or debugging a running production app.

  • Setup stack

    pricklywiggles/fractally-claude-marketplace/plugins/stack-it/skills/setup-stack Skill

    no license1★ repo

    Use this skill to run the entire stack-it pipeline end to end in one guided pass. It takes a project from nothing to a working, verified, documented tech stack by running each stage skill in order (identify-stack-slots, decide-stack, install-stack, scaffold-and-verify, document-stack), resumes from wherever the project already is, optionally sets up git and commits a checkpoint after each stage, and keeps a running task list so the user can see how much is left. Use it whenever someone wants their whole stack set up rather than just one step. Phrasings like "set up my stack", "set up my whole project stack", "help me start a new project from scratch", "pick, install, and verify my stack", "take me from zero to a working project", "bootstrap my project", or "run the whole stack-it pipeline" should trigger it. It pauses only where it genuinely needs the user (their tool picks in the decide stage, an install confirmation, a stack-fault re-pick, an OK before writing docs) and handles the loop where a broken tool sends verification back to re-decide. Reach for the individual stage skills instead when the user explicitly wants only one step (only choose tools, only install, only document); this orchestrator is for the full journey. It does not reimplement the stages; it sequences them.

  • Git commit writer free

    justhandledlabs/skills/plugins/git-commit-writer-free/skills/git-commit-writer-free Skill

    1★ repo

    Generate conventional commit messages from staged git changes. Use when the user asks to write commit message, generate commit, what should my commit say, or after the user runs git add and wants a commit message for staged files.

  • Markdown table formatter

    justhandledlabs/skills/plugins/markdown-table-formatter/skills/markdown-table-formatter Skill

    1★ repo

    Align messy Markdown tables and normalize their columns, or build a table from CSV. Use when the user says "fix my markdown table", "align this table", or "csv to markdown table".

  • Robots sitemap validator

    justhandledlabs/skills/plugins/robots-sitemap-validator/skills/robots-sitemap-validator Skill

    1★ repo

    Check robots.txt and sitemap.xml for crawl-blocking mistakes. Use when the user says "check my robots.txt", "validate my sitemap", or "is my site crawlable".

  • Git commit writer free

    justhandledlabs/skills/skills/git-commit-writer-free Skill

    1★ repo

    Generate conventional commit messages from staged git changes. Use when the user asks to write commit message, generate commit, what should my commit say, or after the user runs git add and wants a commit message for staged files.

  • Markdown table formatter

    justhandledlabs/skills/skills/markdown-table-formatter Skill

    1★ repo

    Align messy Markdown tables and normalize their columns, or build a table from CSV. Use when the user says "fix my markdown table", "align this table", or "csv to markdown table".

  • Robots sitemap validator

    justhandledlabs/skills/skills/robots-sitemap-validator Skill

    1★ repo

    Check robots.txt and sitemap.xml for crawl-blocking mistakes. Use when the user says "check my robots.txt", "validate my sitemap", or "is my site crawlable".

  • Minimalist review

    kalias/OPC_starter_skills/skills/minimalist-review Skill

    no license1★ repo

    用极简创业者的视角,审视任何商业决策、计划或战略。当用户想对某个商业决策做直觉校验、想简化自己的做法、或在几个选项之间做选择时使用。

  • Adversarial reviewer

    tmj-90/gaffer/runner/skills/adversarial-reviewer Skill

    1★ repo

    Use when you want a genuinely critical review of recent changes — before merging a PR, after a sprint, or when you suspect the review is being too agreeable. Forces perspective shifts through three hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer. Triggers on "adversarial review", "break my code", "what could go wrong", "devil's advocate review", or "pre-merge review".

  • Api design reviewer

    tmj-90/gaffer/runner/skills/api-design-reviewer Skill

    1★ repo

    Use when reviewing a PR that adds or changes API endpoints, auditing an existing API for v2 migration, or establishing REST API standards. Triggers on "API review", "REST design review", "breaking change check", "OpenAPI audit", "endpoint review", or "API consistency".

  • Changelog generator

    tmj-90/gaffer/runner/skills/changelog-generator Skill

    1★ repo

    Use when producing release notes from Conventional Commits, computing the next semantic version from a commit stream, generating CHANGELOG.md, or automating release notes in CI. Triggers on "generate the changelog", "what version bump do these commits require", "release notes", "CHANGELOG", or "semantic version".

  • Create branch

    tmj-90/gaffer/runner/skills/create-branch Skill

    1★ repo

    Use at the start of work on any claimed Dispatch ticket, before editing files, to create the working branch with the required prefix. Invoke whenever a ticket needs code changes and you are not yet on a non-protected feature branch.

  • Resolve merge conflict

    tmj-90/gaffer/runner/skills/resolve-merge-conflict Skill

    1★ repo

    Use when an approved ticket's delivery branch cannot auto-merge into the default branch because of a merge conflict. Invoke for "resolve the merge conflict on branch X", "the auto-merge conflicted — reconcile it", or when the factory's merge-ticket runner hands you a conflicting gaffer/* branch. Merge the default branch INTO the delivery branch, resolve every conflict by preserving BOTH intents, prove it with tests, and commit the resolution ON THE BRANCH — never land it to the default branch yourself.

  • Review ticket

    tmj-90/gaffer/runner/skills/review-ticket Skill

    1★ repo

    Use as a reviewer agent to review another agent's `in_review` ticket — never your own. Judge whether each acceptance criterion is genuinely met and the change is sound, then record an ADVISORY verdict (per-AC evidence + an overall RECOMMEND APPROVE / RECOMMEND CHANGES line) via the scoped Dispatch MCP, leaving the ticket `in_review` for a HUMAN to make the final approve/reject decision. An agent review is NOT a human approval and must never mint one or merge. Invoke whenever a ticket is in `in_review` and you are a different agent than the one who delivered it.

  • Run lint

    tmj-90/gaffer/runner/skills/run-lint Skill

    1★ repo

    Use when a ticket or acceptance criterion requires the linter/formatter to pass, or after editing code to confirm it meets the repo's style gate. Invoke for "lint must be clean", "fix lint errors", or before submitting changes that touched source files.

  • Security authz

    tmj-90/gaffer/runner/skills/security-authz Skill

    1★ repo

    Use when a ticket touches authorization — who may perform an action or see a resource — adding access checks, roles/permissions, ownership/tenant scoping, or fixing an access-control gap. Invoke for "restrict X to admins", "add an ownership check", "enforce tenant isolation", or any change to protected resources.

  • Security input validation

    tmj-90/gaffer/runner/skills/security-input-validation Skill

    1★ repo

    Use when a ticket handles untrusted input — request bodies/params, query strings, headers, uploads, webhooks, or third-party API responses — and it must be validated and safely handled. Invoke for "validate the request", "sanitize user input", "fix the injection/XSS risk", or when adding any boundary that ingests external data.

  • Self review

    tmj-90/gaffer/runner/skills/self-review Skill

    1★ repo

    Use after implementing a ticket and after its tests pass, but before submitting for review, to review your own diff as a skeptic would. Checks the finished `git diff` against every acceptance criterion (is each genuinely satisfied?), against scope (did you change only what the ticket needs?), and against quality (bugs, leftover debug, missed edge cases, repo conventions). If the diff reveals a gap, fix it and re-test before submitting. Invoke whenever implementation is complete and tests are green and you are about to hand the ticket to review.

  • Submit review

    tmj-90/gaffer/runner/skills/submit-review Skill

    1★ repo

    Reference for how a finished ticket reaches human review in the Gaffer factory. Submission is RUNNER-OWNED — the agent commits its work and evidences the ACs, then stops; the runner records the delivery, pushes, opens the PR, and submits for review. Invoke when you think your work is ready to hand off, to confirm what you must do (commit + evidence) and what the runner does for you (push, PR, submit).

  • Igrantio backend webhooks

    L3-iGrant/skills/ows/igrantio-backend-webhooks Skill

    1★ repo

    Composable building block: register, receive, and verify iGrant.io OWS digital-wallet webhooks for OpenID4VCI issuance and OpenID4VP verification events. Idempotently create a webhook via config-create-webhook (skip if one already targets the payloadUrl), verify the X-iGrant-Signature HMAC-SHA256, map each topic to its exchange id (CredentialExchangeId / presentationExchangeId), and store the event. Use to add OWS webhook handling to any Node/TypeScript backend.

  • Igrantio verifier backend

    L3-iGrant/skills/ows/igrantio-verifier-backend Skill

    1★ repo

    Build the backend for an OpenID4VP + DCQL credential VERIFIER / relying party against the iGrant.io Organisation Wallet Suite (OWS). A tenant-aware Node/TypeScript (Express) service that hides per-organisation API keys behind a proxy, registers and receives OWS verification webhooks (HMAC-verified), and pushes the verified result to the browser over SSE. Use when an application must request and verify a credential presentation from an eIDAS 2.0 EUDI Wallet (EUDIW) or European Business Wallet (EUBW) and the API key must never reach the frontend. Supports wallet-signed transaction data (SCA payments, e-mandates, login/risk authentication, account access, QES document signing).

  • Igrantio dcapi android

    L3-iGrant/skills/workflows/igrantio-dcapi-android Skill

    1★ repo

    Same-device and cross-device credential verification on Android via the W3C Digital Credentials API (browser invokes the wallet, no QR scan needed on same device) using OpenID4VP on the iGrant.io Organisation Wallet Suite. Presentation definition with responseMode dc_api (or signed with expectedOrigins), verification request v3 with requestByReference, navigator.credentials.get invocation from Chrome 141+, then verify vpTokenResponse and trust-list status. For EUDI Wallet (EUDIW) and European Business Wallet (EUBW) relying parties under eIDAS 2.0.

  • Igrantio dcapi ios

    L3-iGrant/skills/workflows/igrantio-dcapi-ios Skill

    1★ repo

    Same-device and cross-device credential verification on iOS/iPadOS via the W3C Digital Credentials API using ISO 18013-7 Annex C request/response with ISO/IEC 18013-5 mdoc/mDL credentials on the iGrant.io Organisation Wallet Suite. On iOS the DC API runs over Annex C only and the request must be signed (expectedOrigins required). Presentation definition, verification request v3 with requestByReference, wallet invocation from the browser, then verify vpTokenResponse and trust-list status. For EUDI Wallet (EUDIW) relying parties under eIDAS 2.0.

  • Igrantio eu age verification

    L3-iGrant/skills/workflows/igrantio-eu-age-verification Skill

    1★ repo

    EU Age Verification on the iGrant.io Organisation Wallet Suite: issue an age verification attestation as an ISO/IEC 18013-5 mdoc (doctype eu.europa.ec.av.1, boolean age_over_NN claims) via OpenID4VCI InTime, then verify a selectively disclosed age_over_18 proof via OpenID4VP + DCQL - no birthdate or identity revealed. Implements the EU Age Verification solution profile for EUDI Wallet (EUDIW) under eIDAS 2.0. Use for age-restricted content, products, or services.

  • Git change control for agents

    HamzaYM/reliable-ai-skills/skills/change-control/git-change-control-for-agents Skill

    1★ repo

    Use when doing any git work: cutting a branch, opening a PR, merging parallel work, or resuming work in a repo you didn't just leave. Covers state verification before acting, the dead-base PR trap, migration-number collisions, working-tree discipline, and how to handle a product decision that surfaces mid-task.

  • Failure archaeology

    HamzaYM/reliable-ai-skills/skills/debugging-playbooks/failure-archaeology Skill

    1★ repo

    Use when you're about to propose something that smells like it might have already been tried and abandoned: a hosting/platform migration, a framework or library swap, a "quick fix" to code that looks deliberately unusual, or when a revert commit turns up in git history. Prevents re-litigating settled decisions and re-fighting battles someone already lost on purpose.

  • Tiered consultancy review

    HamzaYM/reliable-ai-skills/skills/tiered-review/tiered-consultancy-review Skill

    1★ repo

    Use when a deliverable needs to go from rough draft to genuinely finished without the requester babysitting every pass, a cover letter, a strategy memo, a customer-facing document, a recommendation, a decision review, or any artifact where tone, framing, and defensibility all matter as much as correctness. Mirrors how a consulting firm actually reviews work before a partner signs it.

  • Pre merge validation gate

    HamzaYM/reliable-ai-skills/skills/validation-gates/pre-merge-validation-gate Skill

    1★ repo

    Use before declaring any change "done," before opening or updating a PR, after any UI-touching change, or whenever you're about to report test results. Defines what "done" actually means and how to report it without overstating what was checked.

  • Mcp security review

    fevziegeyurtsevenler/llm-security-skills/skills/mcp-security-review Skill

    1★ repo

    Agent Skills that turn your AI coding agent into an LLM security reviewer — prompt-injection testing, OWASP LLM Top 10 audits, MCP & RAG review, KVKK/PII checks. English + Turkish.

  • Rag security review

    fevziegeyurtsevenler/llm-security-skills/skills/rag-security-review Skill

    1★ repo

    Audits a Retrieval-Augmented Generation (RAG) pipeline for indirect prompt injection (OWASP LLM01), knowledge-base/data poisoning (LLM04), retrieval access-control and tenant-isolation gaps (LLM02/LLM08), and citation/grounding integrity (LLM09). Use when auditing, designing, threat-modeling, or hardening any system that retrieves documents and places their text into an LLM's context window — chatbots over internal docs, agentic search, customer-support assistants, code/knowledge assistants.

  • Secrets guard

    AL-JANEF/janefskills/secrets-guard Skill

    1★ repo

    Prevent secrets from leaking into code, git history, logs, or client bundles — API keys, database credentials, tokens, private keys, and connection strings. Detects hardcoded secrets, guides correct secret management (env vars, secret managers), and sets up prevention (gitignore, pre-commit scanning). Use this skill whenever the user is handling API keys or credentials, setting up environment variables, connecting to external services, committing config, or asks about keeping secrets safe — even a casual "where do I put my API key?". Defensive only.

  • Jira workflow steward

    prvthmpcypher/skills-business/skills/jira-workflow-steward Skill

    1★ repo

    Expert delivery operations specialist who enforces Jira-linked Git workflows, traceable commits, structured pull requests, and release-safe branch strategy across software teams. Use when the user asks about jira workflow steward, needs this workflow, or requests related deliverables.

  • Weekly review system

    prvthmpcypher/skills-business/skills/weekly-review-system Skill

    1★ repo

    You are a productivity systems expert. Guide the user through a structured weekly review that captures wins, analyzes challenges, and plans the upcoming week with intention. ## Process 1. Celebrate wins and acknowledge progress 2. Review completed and incomplete tasks 3. Analyze what worked and what didn't 4. Plan priorities for the upcoming week 5. Set intentions and schedule deep work blocks ## Output Format ## Weekly Review: Week of \[Date\] ### 🎉 Wins & Accomplishments 1. \[What went well this week?\] 2. \[What are you proud of?\] 3. \[Unexpected positive outcomes?\] ### 📊 Metrics Review - Tasks completed: X/Y - Deep work hours: X - Meetings: X - Energy level: X/10 ### 🔄 What Worked - \[Successful strategies to repeat\] ### ⚠️ What Didn't Work - \[Challenges and bottlenecks\] - \[What to change next week\] ### 📅 Next Week Planning Top 3 Priorities: 1. \[Priority 1 — the one thing...

  • Ui iterate

    hcussi/claude-code-toolkit/skills/ui-iterate Skill

    no license1★ repo

    Drive an interactive UI redesign loop on a running web app: render it via the Playwright MCP, critique it (using the ui-design-reviewer agent) against Material-informed minimalism, apply edits, re-render, and repeat according to the user's feedback until they approve. Use when iterating on a screen's look and feel with a human in the loop. Writes code, so it is user-invoked only.

  • Frontend verify

    makieali/claude-code-engineer/skills/frontend-verify Skill

    1★ repo

    Verifies frontend changes in a real browser — screenshots at multiple viewports, console errors, accessibility snapshot — then fixes what it finds and re-verifies. Scopes to routes touched by the current diff when no URL is given. Use after changing UI code, before shipping a frontend change, when a page "looks wrong", or when asked whether something actually works in the browser. Trigger: "check the UI", "does this look right", "screenshot the page", "verify the frontend", "review the design", "test it in the browser".

  • Resume work

    makieali/claude-code-engineer/skills/resume-work Skill

    1★ repo

    Restores working context after a /clear or /compact by reading the most recent session handoff plus current git state, then reports where things stand and what the next step is. Use at the start of a session, after clearing or compacting, when picking up work from a previous day, or when taking over someone else's branch. Trigger: "resume", "pick up where we left off", "what was I doing", "restore context", "continue from the handoff", "catch me up".

  • Reviewer

    makieali/claude-code-engineer/skills/reviewer Skill

    1★ repo

    Validates work completed by /executor agents. Reviews contract compliance, test quality, edge cases, security, performance, and integration correctness in a fresh context, refutes its own findings before reporting them, and gates the verdict on recorded exit codes. Runs after a phase or the full plan is implemented. Trigger: "review phase", "validate the work", "check what was implemented", "run review", "quality check".

  • Create pr description

    FarzamMohammadi/dev-toolbox/ai/claude-code/skills/create-pr-description Skill

    no license1★ repo

    Author a comprehensive, reviewer-ready pull request or GitLab merge request description from the current branch's changes and the working session's context, saved to an isolated temp file. Use this whenever someone is wrapping up a piece of work and needs the writeup — phrasings like "write the PR description", "draft the PR/MR", "create a pull request description", "describe these changes for review", or finishing a branch before opening a merge request. The skill's edge is that it carries the reasoning the diff can't show — why this approach, the root cause behind a bug, the decisions and rejected alternatives, scope and follow-ups, related tickets, and how this PR fits a multi-PR effort.

  • Build and test

    morganmuli/metaskill/examples/fullstack-web/.claude/skills/build-and-test Skill

    1★ repo

    Install dependencies, run type checking, lint, tests, and build the project. Use after making code changes to verify nothing is broken.

    The same file is in 1 other repository

  • Build and test

    morganmuli/metaskill/examples/ios-app/.claude/skills/build-and-test Skill

    1★ repo

    Build the Xcode project and run the full test suite. Use when you need to verify the project compiles, run unit tests, or check for build errors. Reports pass/fail results with detailed error output.

    The same file is in 1 other repository

  • Shipkit prompt audit

    stefan-stepzero/shipkit/install/skills/shipkit-prompt-audit Skill

    1★ repo

    Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.

  • Shipkit review direction

    stefan-stepzero/shipkit/install/skills/shipkit-review-direction Skill

    1★ repo

    Internal reviewer — assesses strategic artifact coherence. Checks vision/why alignment, goal completeness, stage realism. The Direction coherence-review gate, dispatched by the engine (via shipkit-direction), not for direct use.

  • Shipkit review planning

    stefan-stepzero/shipkit/install/skills/shipkit-review-planning Skill

    1★ repo

    Internal reviewer — assesses planning artifact alignment. Checks definitions agree, specs cover roadmap, no gaps. A per-unit reviewer invoked by a caller (the engine in steered mode or a direction/planning caller), not for direct use.

  • Shipkit review shipping

    stefan-stepzero/shipkit/install/skills/shipkit-review-shipping Skill

    1★ repo

    Review changes across 12 quality dimensions and report findings. Use after a chunk of work or before commit.

  • Fstrent code reviewer

    wrm3/ai_project_template/.claude/skills/fstrent-code-reviewer Skill

    1★ repo

    Comprehensive code review following company standards with focus on security, performance, maintainability, and best practices

  • Fstrent code reviewer

    wrm3/ai_project_template/plugins/fstrent-spec-tasks/skills/fstrent-code-reviewer Skill

    1★ repo

    Comprehensive code review following company standards with focus on security, performance, maintainability, and best practices

  • Pr branch

    mattjaikaran/meridian/skills/pr-branch Skill

    1★ repo

    Skill that gives AI coding agents persistent memory and quality enforcement

  • Review

    mattjaikaran/meridian/skills/review Skill

    1★ repo

    Skill that gives AI coding agents persistent memory and quality enforcement

  • Verify phase

    mattjaikaran/meridian/skills/verify-phase Skill

    1★ repo

    Skill that gives AI coding agents persistent memory and quality enforcement

  • Daa review

    gigayaya/DAA-Master/plugins/DAA-Master/skills/daa-review Skill

    1★ repo

    Use when reviewing existing test code for DAA compliance, identifying anti-patterns, or suggesting improvements to automation test architecture

  • Dotnet fluent validation

    landim32/awesome-ai-skills/skills/dotnet-fluent-validation Skill

    1★ repo

    Guides the implementation of FluentValidation validators for DTOs in a .NET 8 project. Creates validator classes, registers them in DI, integrates with services, and configures the validation pipeline. Use when adding input validation, creating validators, or replacing manual if/throw validation with FluentValidation.

    The same file is in 7 other repositories

  • Git commit helper

    lc-rezende/AI-Custom-Skills/skills/git-commit-helper Skill

    1★ repo

    Generate conventional commit messages without scopes based on staged changes. Use when the user asks for commit message help, has staged changes, or is about to commit.