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

  • Pr review guardian

    moses607/skillforge/skills/pr-review-guardian Skill

    0★ repo

    Review a pull request or code diff for correctness, security, and performance, returning a structured verdict with severity-tagged findings. Use this whenever the user shares a diff, PR link, or code change and asks for review, feedback, "is this safe to merge", "look this over before I ship", or mentions code review, even if they don't say the words "pull request".

  • Weekly review

    moses607/skillforge/skills/weekly-review Skill

    0★ repo

    Run a structured weekly review that captures loose ends, closes the past week, and plans the next one. Use whenever the user asks to "do my weekly review", "plan my week", "help me reset", "what should I focus on", mentions GTD, a Friday/Sunday review, or dumps a pile of tasks and half-finished threads needing order. Trigger on any weekly planning or reset request.

  • Code reviewer

    willianbs/skills/code-reviewer Skill

    0★ repo

    Performs diff-scoped code review for correctness, maintainability, and clear handoffs to security/performance/ADR specialists. Use on PRs and patches. Never modifies code unless asked. Never replaces a full security or performance audit.

  • Pr generator

    willianbs/skills/pr-generator Skill

    0★ repo

    Writes accurate PR descriptions from git diff and commits only—never invented intent or test results. Use when opening or updating a pull request. Emits PR_BODY. Prefer the repo’s PR template when present.

  • Quality gate

    willianbs/skills/quality-gate Skill

    0★ repo

    Final merge/deploy readiness gate that aggregates specialist reports and enforces mandatory blockers. Use before merge or release. Emits QG_REPORT. Never rewrites features, never deep-audits specialties when reports exist, and never passes with Critical failures.

  • Requirements grill

    willianbs/skills/requirements-grill Skill

    0★ repo

    Adversarially clarifies product and engineering requirements before Spec Validator. Use when asks are vague or high-stakes. Emits GRILL_NOTES. Never invents product decisions as facts or starts implementation.

  • Spec validator

    willianbs/skills/spec-validator Skill

    0★ repo

    Validates engineering specs before implementation. Ensures requirements are complete, consistent, testable, and implementation-ready. Use for tickets, PRDs, RFCs, or verbal feature asks. Emits SPEC_STATUS. Never redesigns the product or starts coding.

  • App review

    Alexxiang2008/awesome-skills-map/skills/第15章AppStore评价分析/App用户评论分析/app-review Skill

    0★ repo

    App Store 评价分析器 - 输入应用 ID,自动抓取最多 500 条用户评论,进行情感分析,生成简洁风格 HTML 报告并导出 CSV。支持 /app-review 或 /评价分析 命令启动。

  • Lint vault

    jpmsilva1/ai-research-ecosystem/skills/lint-vault Skill

    0★ repo

    Triggered when the user types /lint or asks to health-check the Obsidian Vault. Scans the wiki/ directory to identify structural issues, orphan pages, broken wikilinks, stale index entries, and contradictions.

  • Hipaa code review

    EliasAli0720/HIPAA-agent-skill/skills/hipaa-code-review Skill

    0★ repo

    Reviews code, diffs, and infrastructure-as-code for HIPAA violations — PHI in logs and URLs, non-BAA analytics and crash SDKs, missing encryption, weak access control and audit logging — and ships a runnable PHI scanner script. Use when asked to review code for HIPAA, scan for PHI, check a diff for PHI leaks, audit a healthcare codebase, or verify a health app's code before release.

  • Pdca process review

    goingli0324/muzi-going-skills/plugins/pdca-process-review/skills/pdca-process-review Skill

    0★ repo

    用 PDCA(戴明循環)檢視與優化任何反覆執行的流程。當使用者提到 PDCA/戴明循環/Deming cycle,要求流程復盤或持續改善,或描述一個自己反覆在做、但成效不如預期或執行起來很亂的流程並想找出卡點時觸發。不限領域,但檢視的是流程,不是單一決策。

  • Ui ux deploy reviewer

    goingli0324/muzi-going-skills/plugins/ui-ux-deploy-reviewer/skills/ui-ux-deploy-reviewer Skill

    0★ repo

    以 20 項 UI/UX 原則(Nielsen 啟發法+互動心理學定律+可及性)審視前端程式碼與使用者體驗,輸出依嚴重度排序的問題清單與部署放行檢核表。當使用者明確要審查 UI/UX、易用性、heuristic evaluation,或問「這個網站好不好用」時觸發;未指明範圍的「部署前檢查」交給 agentic-dev-loop 走雙閘。也是該迴圈的 UI/UX 閘。

  • Web security reviewer

    goingli0324/muzi-going-skills/plugins/web-security-reviewer/skills/web-security-reviewer Skill

    0★ repo

    對使用者自己的程式碼做防禦性安全審查,輸出依嚴重度排序的風險報告與修正後程式碼。當使用者要找漏洞、加固、擔心被攻擊或個資外洩,或貼上一段 AI 生成的程式碼要人幫忙看安不安全時觸發。也是 agentic-dev-loop Verify 雙閘的安全閘,供其他 skill 呼叫。

  • Contract review

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-commercial-legal/skills/contract-review Skill

    0★ repo

    Full review of a commercial contract (MSA, services agreement, vendor/procurement, SaaS, distribution, supply) against Bangladesh law and the team's playbook. Use whenever the user attaches or pastes a contract for review, redline, risk summary, or asks "is this OK to sign" — even if they don't say "review". NDAs route to /bd-commercial-legal:nda-triage instead.

  • Product compliance check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-consumer-product-legal/skills/product-compliance-check Skill

    0★ repo

    Checks a product or marketing plan against Bangladesh consumer/product law — CRPA 2009 offences (adulteration, false advertising, weight/measure, price display), BSTI mandatory-certification list, Safe Food Act 2013 obligations for food businesses, labelling and Bangla-language requirements, tobacco-adjacent restrictions. Use for "can we sell/advertise this", "label review", "DNCRP risk".

  • Special offence check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-criminal-specialty-legal/skills/special-offence-check Skill

    0★ repo

    Maps charges under Bangladesh's special criminal statutes — elements, forum (which special tribunal), bail regime (bailable/non-bailable, statutory embargoes), sentence exposure, investigation-stage rights and timelines. Use for "charged under Arms Act", "ACC notice", "Nari-o-Shishu case strategy", "SPA detention".

  • Institution compliance check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-education-legal/skills/institution-compliance-check Skill

    0★ repo

    Checks an education institution's governance and regulatory position — charter-act conformity (senate/syndicate/trustee composition, VC appointment), UGC/ministry approvals (programs, campuses), Private University Act 2010 obligations (trust fund, land, accreditation), board affiliations, and teacher-employment (MPO) rules. Use for "governance dispute", "UGC show-cause", "open a new program/campus", "trustee conflict".

  • Agreement review

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-employment-legal/skills/agreement-review Skill

    0★ repo

    Reviews employment agreements, appointment letters, offer letters and HR policies against the Bangladesh Labour Act 2006 + Labour Rules 2015 statutory floor. Use whenever an employment document needs review or drafting, including "is this offer letter OK", "draft an appointment letter", or contractor-vs-employee questions.

  • Termination check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-employment-legal/skills/termination-check Skill

    0★ repo

    Pre-termination risk check and benefits math under the Bangladesh Labour Act 2006 — picks the right separation route (termination simpliciter, dismissal for misconduct, discharge, retrenchment, resignation) and computes notice + compensation. Use for any "we want to let X go", "terminate", "retrench", "dismiss", severance-calculation, or disciplinary-process question. HIGH RISK — this skill escalates aggressively.

  • Energy project check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-energy-utilities-legal/skills/energy-project-check Skill

    0★ repo

    Reviews a Bangladesh energy/utility project or dispute — licensing map (BERC), PPA/IA/GSA risk points, tariff-change exposure, land/environmental prerequisites, and the special-provisions procurement lineage. Use for "power project diligence", "PPA review", "BERC licence", "gas connection dispute", "boiler compliance".

  • Entity form check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-general-statutes/skills/entity-form-check Skill

    0★ repo

    Compares Bangladesh non-company entity forms — society (1860), trust (1882), waqf, foundation-by-guarantee, NGO with FDRA 2016 registration — for a given purpose, with formation steps, governance, tax touchpoints and foreign-funding constraints. Use for "structure this NGO/club/foundation", "society vs trust", "FDRA registration".

  • Pharma regulatory check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-health-pharma-legal/skills/pharma-regulatory-check Skill

    0★ repo

    Checks pharma/health operations against the 2023 drugs regime and clinical regulation — DGDA licences and renewals, registration of products, pricing (essential list), promotion rules, clinical-trial and pharmacovigilance duties, private clinic/lab licensing. Use for "launch this product", "DGDA inspection", "clinic licence", "drug promotion review".

  • Policy review

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-insurance-legal/skills/policy-review Skill

    0★ repo

    Reviews insurance policy wordings, proposals and endorsements against the Insurance Act 2010 and IDRA directives — mandatory clause content, premium/solvency touchpoints, exclusion enforceability, claims-condition traps. Use for "review this policy", "is this exclusion enforceable", "draft an endorsement".

  • Ip clause review

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-ip-legal/skills/ip-clause-review Skill

    0★ repo

    Reviews and drafts IP clauses (assignment, licence, work-for-hire, moral rights, infringement indemnity, background/foreground IP) under the Copyright Act 2023, Patent Act 2022, Industrial Designs Act 2023 and Trademarks Act 2009. Use for any IP clause in a contract, "who owns the IP", licensing questions, or IP warranty/indemnity drafting.

  • Update check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-law-watch/skills/update-check Skill

    0★ repo

    Verifies that this marketplace's Bangladesh legal references are still current — checks every watchlist item against bdlaws.minlaw.gov.bd, the Bangladesh Gazette, and regulator sources; reports repeals, amendments, new ordinances, and rate changes; re-walks the FULL bdlaws statute index (all volumes, both languages) against references/full-statute-corpus.csv to catch coverage drift; and (with approval) updates the reference files and change log. Use monthly, before any deadline-critical matter, on first install, whenever the user says "update", "is this still current", "check for new laws", or "has anything changed" — and proactively suggest it whenever another skill leans on a 2023–2026 instrument. Zero-config: runs without any cold-start interview. Supports --topic <cyber|data|labour|tax|corporate| ip|limitation|environment|aml|fx|procurement|all> to scope the check.

  • Limitation check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-litigation-legal/skills/limitation-check Skill

    0★ repo

    Computes the limitation bar date for a Bangladesh claim under the Limitation Act 1908 and special statutes, including restart events and preconditions. Use for "are we time barred", "when does limitation expire", "how long do we have", or as the mandatory first step of case-prep. Deadline-critical — this skill double-checks itself.

  • Title diligence check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-real-estate-legal/skills/title-diligence-check Skill

    0★ repo

    Runs a Bangladesh land-title diligence checklist — chain of title across CS/SA/RS/BS records, mutation (namjari) status, registered-instrument review, encumbrance and possession flags, SAT Act ceiling/vesting risks. Use for "check this title", "buy this land/flat", "developer deal diligence", "mortgage security review".

  • Transfer cost check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-real-estate-legal/skills/transfer-cost-check Skill

    0★ repo

    Computes the government-cost stack on a Bangladesh land/flat transfer — stamp duty, registration fee, local government tax, VAT, gains tax (53H/53FF-lineage withholding under the Income Tax Act 2023), mutation fees — with current-rate verification steps. Use for "what will registration cost", "stamp duty on this deed", "developer vs buyer cost split".

  • Aml cft check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-regulatory-compliance/skills/aml-cft-check Skill

    0★ repo

    AML/CFT compliance review under the Money Laundering Prevention Act 2012, Anti-Terrorism Act 2009, MLP Rules 2019 and BFIU circulars. Use for "AML check", "are we a reporting entity", KYC/CDD program review, STR/CTR questions, sanctions screening, or when a bank/ regulator raises AML queries.

  • Compliance check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-regulatory-compliance/skills/compliance-check Skill

    0★ repo

    Multi-domain Bangladesh regulatory compliance check for a company, product, project, or transaction — cyber (Cyber Security Ordinance 2025), data (PDPA 2026), AML/CFT, FERA, environment (ECA 1995 + ECR 2023), anti-corruption, labour-safety, sector licences. Use for "are we compliant", "what regulations apply", "launch review", "regulatory risk assessment", or new-market/new-product screening.

  • Data protection check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-regulatory-compliance/skills/data-protection-check Skill

    0★ repo

    Focused Personal Data Protection Act 2026 compliance review — processing inventory, lawful basis, data classification, localisation, cross-border transfers, breach and registration duties. Use for "PDPA check", "can we send this data abroad", "privacy review", "data protection compliance", DPA/data-clause reviews, or breach response.

  • Withholding check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-tax-legal/skills/withholding-check Skill

    0★ repo

    Determines TDS (income tax withholding) and VDS (VAT deducted at source) treatment for a specific payment under the Income Tax Act 2023 and VAT & SD Act 2012 — including cross-border payments needing treaty and FERA analysis. Use for "do we withhold on this payment", "TDS rate", "VDS applicable?", "paying a foreign vendor", or gross-up drafting.

  • Cargo claim check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-transport-maritime-legal/skills/cargo-claim-check Skill

    0★ repo

    Works up a Bangladesh cargo claim — sea/inland/road/rail — identifying the liability regime, notice and suit time-bars (COGSA one-year!), quantum rules, arrest/security options, and forum (Admiralty Court vs civil court vs arbitration). Use for "cargo shortage/damage claim", "bill of lading dispute", "arrest a vessel", "transport claim time bar".

  • Generate commit message

    reagin/agent-skills/skills/generate-commit-message Skill

    no license0★ repo

    🧠 A portable home for reusable AI agent skills shared across Codex and Claude Code—single-source, validation-first, and seamlessly managed with CC Switch. ⚡

  • Grill me

    reagin/agent-skills/skills/grill-me Skill

    no license0★ repo

    A relentless interview to sharpen a plan, decision, or design. Use when the user wants to stress-test their thinking or uses any "grill" trigger phrase such as "grill me", "grill my plan", or "poke holes in this".

  • Review engine

    SkillMedev/local-service-business-engine/skills/review-engine Skill

    0★ repo

    Builds a systematic review generation and response engine for a local service business - the ask-at-peak-satisfaction timing rule, SMS ask scripts, a review-velocity target benchmarked to the top competitor, and word-for-word response procedures for 1-3 star reviews. Use when an owner asks "how do I get more Google reviews", "a customer left a bad review, what do I say", "should I text customers for reviews", or "why does my competitor have way more reviews". Do NOT use for the rest of the Google Business Profile setup - use google-business-profile-optimizer instead. Do NOT use for turning existing reviews into website FAQ content - use review-to-faq-builder instead.

    The same file is in 1 other repository

  • Rubric self check

    kalshamsi/fable-discipline-skills/skills/rubric-self-check Skill

    0★ repo

    Extract a request's explicit requirements into a checklist before drafting, then verify the draft against every item before delivering. Use this whenever a deliverable carries multiple explicit constraints — word or length limits, required sections or elements, mandated formats or templates, prohibitions, tone or audience rules — and for any detailed brief, spec, or compliance-sensitive output. Trigger on phrasings like "must include", "no more than", "exactly N", "in the format of", "do not mention", or any request that lists several requirements, even casually; if the request has three or more stated constraints, use this skill rather than trusting them to memory.

  • Verify before answering

    kalshamsi/fable-discipline-skills/skills/verify-before-answering Skill

    0★ repo

    Check the referenced source and extract what it actually says before making any factual claim about it. Use this whenever a question concerns a specific document, dataset, file, report, spreadsheet, email thread, or other artifact; whenever source material is available or referenced and the answer will make factual claims; and whenever summarizing, interpreting, comparing, or answering questions about provided material. Trigger even when the material "looks familiar" or the question seems easy — phrasings like "what does this doc say", "summarize the report", "according to the data", "is X true in this file" all call for it.

  • Ux flow review

    hsiangyilu/claude-design-skills/skills/ux-flow-review Skill

    0★ repo

    檢查設計流程的 UX 問題,逐輪修正並確認直到流程沒有問題。適用於多畫面的功能流程(如設定流程、交易流程、註冊流程等)。當使用者貼上 Figma 流程的 URL、多張流程截圖,或說「幫我審這條流程」「這個 flow 順不順」「狀態有沒有漏」「返回路徑對不對」時使用。聚焦跨畫面的流程邏輯(狀態覆蓋、返回路徑、死胡同、分支對錯、資料邏輯一致性),不是單頁視覺細節。若要審的是逐頁視覺與細節一致性(間距、字級、對齊、對比),改用 screen-design-review。

  • Code review and quality

    rabius-sunny/agent-skills/code-review-and-quality Skill

    no license0★ repo

    Conducts 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

  • Code review

    muzalee/claude-atelier/skills/code-review Skill

    no license0★ repo

    Technical code review for correctness, security, tests, error handling, and style. Distinct from design-review (which is visual/aesthetic). Use when user says "review this code", "check my PR", "code review", "check for issues", or after implementing a feature.

  • Design review

    muzalee/claude-atelier/skills/design-review Skill

    no license0★ repo

    Run a structured design critique against the brief and codebase. Checks visual hierarchy, consistency, responsiveness, accessibility, and aesthetic fidelity. Use when user wants a design review, critique, QA pass, polish pass, or mentions "review" after building.

  • Design

    muzalee/claude-atelier/skills/design Skill

    no license0★ repo

    Explicit-invocation-only orchestrator that runs the pure-design phase end-to-end — grill → brief → backend-design → IA → tokens → tasks — with confirmation gates between every phase. Every output is a markdown doc saved to `.design/<slug>/`. NO CODE is written in this skill. Invoked ONLY when the user types /design or explicitly asks to "run the design pipeline" / "run the design orchestrator". After this, the user runs `/build` to implement and `/review` to check the result. DO NOT auto-trigger from adjacent talk about briefs, IA, tokens, tasks, or building — those have their own skills.

  • Grill me

    muzalee/claude-atelier/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".

  • Keep it simple

    muzalee/claude-atelier/skills/keep-it-simple Skill

    no license0★ repo

    Apply to all written output — commit messages, PR descriptions, code comments, documentation, and explanations. Keep it short, no over-explaining, no filler. Never add "Co-Authored-By Claude" trailer on commits. Trigger on any writing task, especially git commit, PR create, adding comments/docstrings, or writing README/docs.

  • Project bootstrap

    muzalee/claude-atelier/skills/project-bootstrap Skill

    no license0★ repo

    Scaffold a new project from scratch — folder, .gitignore, README, LICENSE, git init + first commit, and (if gh is authed) create the GitHub repo with description, topics, and visibility. Use when user says "start a new project", "bootstrap", "new repo", "scaffold X", or asks to set up a fresh codebase.

  • Review

    muzalee/claude-atelier/skills/review Skill

    no license0★ repo

    Explicit-invocation-only orchestrator that runs code review + design review against the built code, using `.design/<slug>/` as the source of intent. Invoked ONLY when the user types /review or explicitly asks to "run the review pipeline", "review the build", or "check the feature". For a single technical review only, use `code-review` directly. For a single visual review only, use `design-review` directly. DO NOT auto-trigger from adjacent talk about reviewing code — those have their own skills.

  • Test plan

    muzalee/claude-atelier/skills/test-plan Skill

    no license0★ repo

    Write a short test plan for a change before implementing — list the cases that must pass, what to break to prove them, and what NOT to test. Use before starting non-trivial work, when asked for a "test plan", or when reviewing a PR to sanity-check coverage.

  • Aeo eeat

    KingForm242/claude-aeo/skills/aeo-eeat Skill

    0★ repo

    Score content 1-10 against Google E-E-A-T rater guidelines (Experience, Expertise, Authoritativeness, Trustworthiness) with a PUBLISH/REVISE/REWRITE verdict, top weaknesses and strengths. Use as pre-publish quality gate. Use when user says EEAT, content quality score, rate this content, or quality check.

  • Aeo visibility check

    KingForm242/claude-aeo/skills/aeo-visibility-check Skill

    0★ repo

    Score whether an LLM would cite this page for a target query: answer positioning, structural clarity, factual density, entity coverage, freshness. Weighted 1-10 scorecard, verdict, top 3 fixes, rewritten opening. Use when user says would AI cite this, AEO readiness, AI visibility score, or check this page.

  • Claim strengthener

    meturley/trail-marker-geo/skills/claim-strengthener Skill

    0★ repo

    A spell-checker for AI visibility that scans campaign copy for vague, uncitable phrases and converts them into specific, quotable facts. Use whenever a user pastes or shares a policy page, press release, issues section, "About" page, platform, endorsement page, or any campaign or advocacy copy and wants it to be more credible, more citable, more persuasive, more "quotable," or more likely to be picked up by AI answer engines, search, or the press. Also trigger when a user asks to "strengthen," "tighten," "fact-check," "add sources to," "make more specific," or "find the weak claims in" their messaging — even if they don't mention AI or citations explicitly. Works in batches for long copy and hands back a clean, reassembled final version. Do NOT invent statistics, quotes, or sources; always prompt the user to supply real evidence.

  • Extractability check

    meturley/trail-marker-geo/skills/extractability-check Skill

    0★ repo

    Diagnose whether an AI retrieval crawler can actually see and cite a candidate's web page. Use whenever someone gives a page URL and asks what an "AI crawler sees," whether their page is "citable," "extractable," "visible to AI," "retrievable," or "AI-readable" — or asks why their content isn't getting cited/surfaced by AI answer engines. Fetches the page as a non-JS-executing bot would (raw server HTML) and reports whether substantive content is present pre-hydration, whether facts are front-loaded, dated, and sourced, whether Person/FAQPage JSON-LD exists, and whether headings are questions/topics vs slogans. Routes each finding to the right fix skill in this suite. Diagnostic only — never modifies the site. Trigger even when the user just pastes a URL and asks "how does this look to AI?"

  • Grill my architecture

    NasserAlbusaidi/ship-gate/skills/grill-my-architecture Skill

    0★ repo

    Brutal staff-engineer review of system architecture — service/module boundaries, data ownership, communication patterns, failure modes, scaling, security trust boundaries, evolvability, cognitive load, cost. Accepts an architecture doc, a set of ADRs, a system design write-up, a diagram pack, a verbal sketch, OR the codebase itself (the skill reconstructs the de-facto architecture from the code when no doc exists). Distinct from `grill-my-code` (file/function craft), `grill-my-backend` (server-side surface within one service), `grill-my-plan` (a specific planned change before code is written), `improve-codebase-architecture` (constructive refactoring opportunities), and `plan-eng-review` / `plan-ceo-review` (constructive walkthroughs). Use when the unit of critique is the *system shape*, not a file or a feature. Triggers on "grill my architecture", "grill the system design", "grill these ADRs", "is this architecture going to survive", "tear apart this design", "review my system design brutally", "stress-test the architecture".

  • Grill my backend

    NasserAlbusaidi/ship-gate/skills/grill-my-backend Skill

    0★ repo

    Brutal staff-engineer review of backend code — handlers, services, migrations, background jobs, queries, integrations. Backend-specific principle library (API contract, authn/authz/tenancy, persistence & transactions, schema migrations, jobs & messaging, caching, external integration, backend ops) layered on top of `grill-my-code`'s general craft library. Use when the surface is explicitly server-side; use `grill-my-code` when the surface is generic. If in doubt, pick this one — it strictly supersets the general library for server-side code. Distinct from `grill-me` (Socratic interview) and `grill-with-docs` (aligns plan against CONTEXT.md). Triggers on "grill my backend", "grill this endpoint", "grill this migration", "grill this query", "review my API brutally", "is this handler safe".

  • Run the gate

    NasserAlbusaidi/ship-gate/skills/run-the-gate Skill

    0★ repo

    Fresh-context spec review before implementation for Rihla money/rules/routing/schema changes. Spawns TWO parallel zero-history Opus subagents per round — a rubric reviewer (7 verification principles) and an orthogonal-axis adversary (off-map regressions, derived surfaces, l10n pairs) — applies the union of P1 findings, and re-runs until both verdicts are clean in the same round. Use before writing code that touches BalanceCalculator/MoneySerializer, firestore.rules or Cloud Functions auth, app_router.dart / deep-links / back-guards, or any field-name/schema change with both a read-path and a write-path. Use when asked to "run the Gate", "gate this spec", or "fresh-context review".

  • Commit craft

    ccpowerpack/claude-code-skills/skills/commit-craft Skill

    0★ repo

    Turn a messy working tree into a reviewable series of atomic commits. Use when asked to "clean up these changes", "split this into commits", "make this reviewable", "commit this properly", when a working tree mixes unrelated changes (rename + fix + feature), or before opening a PR from a long hacking session. Refuses to commit until the independent logical changes in the tree have been listed, and requires each commit to build and pass tests on its own.

  • Pr narrative

    ccpowerpack/claude-code-skills/skills/pr-narrative Skill

    0★ repo

    Turn the current branch's diff into a reviewer-ready PR description — intent, change map, risk assessment, test evidence, and a suggested review path. Use when the user asks to "write a PR description", "describe this branch", or prepare a change for review.

  • Cocogitto

    aldiipratama/dyy-plugin/skills/version-control/cocogitto Skill

    0★ repo

    Automates creating conventional commit messages validated by cocogitto (cog) for Git version control. Use when preparing to make commits or writing changelogs.

  • Build publish check

    NorthStar-Analytics-LTD/skill-foundry/skills/build-publish-check Skill

    0★ repo

    Skill builder. Inspects your BI conventions and governance artefacts, interviews whoever answers for data quality, then generates a custom /publish-check skill — a gate every dashboard must pass before it counts as published. Use when your estate keeps regrowing after every clean-up, when dashboards ship without owners, or when self-serve is failing because nobody trusts what they find.

  • Hype check

    natexai2026/2030-skills/skills/hype-check Skill

    0★ repo

    Separate "X is happening / X exists" (prevalence) from "X causes Y by magnitude Z" (measured impact), and surface the missing denominator, the absent counterfactual, and the confound behind a scary or exciting claim. Use whenever reading a viral statistic, a trend piece, a threat narrative, a marketing claim, or a "this changes everything" headline; before repeating or acting on one. Triggers on "is this as big a deal as they say," "X is exploding/surging," fear-driven or FOMO-driven claims, "N% of people now do X," and any number that feels designed to alarm or impress. If a claim moves fast and feels huge, run it through this first.