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

  • Gstack

    waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/gstack Skill

    no license0★ repo

    Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.

  • Browse

    waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/gstack/browse Skill

    no license0★ repo

    Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.

  • Plan ceo review

    waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/gstack/plan-ceo-review Skill

    no license0★ repo

    CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).

  • Plan eng review

    waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/gstack/plan-eng-review Skill

    no license0★ repo

    Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.

  • Review

    waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/gstack/review Skill

    no license0★ repo

    Pre-landing PR review. Analyzes diff against main for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.

  • N8n validation expert

    waseemnasir2k26/skynetlabs-all-claude-code/skills/meta-and-tools/n8n-skills/skills/n8n-validation-expert Skill

    no license0★ 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, or the validation loop process.

    The same file is in 3 other repositories

  • Technical seo checker

    waseemnasir2k26/skynetlabs-all-claude-code/skills/seo-content-copy/seo-geo/optimize/technical-seo-checker Skill

    no license0★ repo

    Technical SEO audit: Core Web Vitals, crawl, indexing, mobile, speed, architecture, redirects. 技术SEO/网站速度

  • Caveman commit

    waseemnasir2k26/skynetlabs-all-claude-code/skills/token-and-comms/caveman-commit Skill

    no license0★ repo

    Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

    The same file is in 8 other repositories

  • Evaluate plan

    eprouveze/claude-skills/skills/evaluate-plan Skill

    0★ repo

    Evaluate an implementation plan against its source requirements (PRD, spec, or user request) to identify gaps, dropped features, and lost intent. Use when the user says "evaluate plan", "verify plan", "check the plan", "what did it miss", "plan coverage", or "validate plan".

  • Second opinion

    eprouveze/claude-skills/skills/second-opinion Skill

    0★ repo

    Get a second opinion from OpenAI's Codex CLI. Default model is gpt-5.5. Three modes: review (pass/fail code review on the current diff), challenge (adversarial pass — try to break it), consult (multi-turn Q&A with session persistence). Uses ChatGPT subscription auth, not an API key. Use when asked for "second opinion", "codex review", "adversarial review", "challenge this code", "cross-model review", or "/second-opinion".

  • Jira vs code mismatch

    mohitkhandelwal242/ai-pm-operator/.claude/skills/jira-vs-code-mismatch Skill

    no license0★ repo

    Jira vs Code Mismatch Detector. Cross-references Jira Acceptance Criteria (AC) against local Git diffs to detect spec-code drift before committing. Use when checking spec drift, verification code check, or '/jira-vs-code'.

  • Review

    bordumb/recurve/.claude/skills/review Skill

    no license0★ repo

    Run the adversarial review protocol on a review-gated (security-tradeoff) gap for recurve — try to BREAK the change, never to confirm it

  • Gtd review

    blu3mo/gtd-cosense/skills/gtd-review Skill

    0★ repo

    Guide a GTD review of the Cosense system so it stays trusted and current. Use for the Weekly Review (週次レビュー, 棚卸し, 見直し, "システム整える", "たまってきたから整理") or a quick daily check. Reads the whole system WITH UNDERSTANDING (including the user's casual hand-edits), empties 未処理, confirms every open loop has a live next action, sweeps Google Calendar for loose ends, and revisits someday. Part of the gtd skill bundle.

  • Resolve review comments

    valasubramanian-kr/wallet-web-developer/skills/resolve-review-comments Skill

    no license0★ repo

    Claude plugin orchestrating spec-to-code automation workflow, enabling developers to leverage Claude Skills for productivity.

  • Review

    valasubramanian-kr/wallet-web-developer/skills/review Skill

    no license0★ repo

    Claude plugin orchestrating spec-to-code automation workflow, enabling developers to leverage Claude Skills for productivity.

  • Manuscript editorial router

    dinaf2026-web/manuscript-editorial-suite/manuscript-editorial-router Skill

    0★ repo

    Routes a broad or ambiguous editorial request to the right pass(es) in the Manuscript Editorial Suite. Use when the ask spans more than one kind of feedback or it's unclear which is wanted — "review my book", "give me editorial feedback", "is this ready", "go over this chapter", "full editorial pass", "what should I check". Picks among manuscript-publisher-critique, manuscript- continuity-audit, manuscript-fair-play-audit, manuscript-prose-immersion-audit, and manuscript-listing-critique, runs them in the right order for the book's genre, and hands off. Does not itself critique, score, or rewrite — it only dispatches.

  • Manuscript listing critique

    dinaf2026-web/manuscript-editorial-suite/manuscript-listing-critique Skill

    0★ repo

    Sales-listing critic for any book on Amazon KDP (and similar storefronts). Critiques (and, on request, rewrites) back-cover / jacket copy, the Amazon book description, categories, and keywords — the commercial surface that decides whether a browser clicks "buy". Use when the author says "critique the blurb", "review the back cover", "is this description good", "fix my Amazon listing", "rewrite my blurb", "check my categories and keywords", "would this sell", or "KDP listing review". For whole-story craft or an acquisitions verdict use manuscript-publisher-critique instead; this pass works only on selling copy and metadata, and never rewrites manuscript prose.

    The same file is in 1 other repository

  • Manuscript publisher critique

    dinaf2026-web/manuscript-editorial-suite/manuscript-publisher-critique Skill

    0★ repo

    The publisher's read for any manuscript — an acquisitions verdict plus a developmental craft breakdown, delivered as a scored report card graded against the markers of a great book in its genre (set by the project profile). Use for a single craft/acquisitions read of a scene, chapter, outline, full manuscript, or query: "publisher's read", "acquisitions verdict", "critique this", "score this", "grade this", "editor's letter", "would a publisher take this", "what's weak here", "read this like an editor". For a broad "review my book / full editorial pass" that may need several checks, use manuscript-editorial-router. NOT for canon checking (continuity-audit), mystery-fairness logic (fair-play-audit), line-level immersion (prose-immersion-audit), or blurb/listing copy (listing-critique). Diagnoses and scores; does not rewrite prose.

    The same file is in 1 other repository

  • Feature loop

    ohugonnot/claude-skills/plugins/feature-loop/skills/feature-loop Skill

    0★ repo

    Use when the user wants a non-trivial feature implemented with autonomous, iterative, quality-gated delivery — best when quality matters more than raw speed. A mother agent sizes the difficulty tier and delegates to SEPARATE subagents (code writer ≠ test-writer ≠ blind reviewer; tests written from the spec). Objective gate (build/lint/typecheck/tests + test-must-go-red mutation check) BEFORE any LLM review; runnable features get a mandatory LIVE smoke test before any "tested" SUCCESS. Loops until all quality axes ≥ 8/10 with zero criticals (max 3 iters), keeps the BEST version, emits a markdown report. Subcommands: status (runs dashboard), learn (propose-only self-improvement). Flags: --fast, --paranoid, --worktree, --max-iter=N, --threshold=N, --judge, --issue=N (GitLab/GitHub issue as spec). NOT for quick edits (do them directly) nor review-only (use senior-review).

  • Issue mr

    ohugonnot/claude-skills/plugins/issue-mr/skills/issue-mr Skill

    0★ repo

    Use when the user wants to turn a task description into a well-formed issue with its branch and MR/PR — on GitLab (glab) or GitHub (gh), auto-detected from the remote. Three behaviors: SCAFFOLD (clean tree → issue + branch + MR/PR shell), ISOLER (uncommitted work gets isolated into its own issue/branch/MR — file list and commit message validated first), ANALYSE (--analyse or vague/non-trivial task: explore the code, settle design with the user, produce a structured spec issue — constat/pourquoi/périmètre/plan — ready to feed feature-loop --issue=N). Discovers project conventions live (labels, default branch, commit scopes) instead of hardcoding; validates everything with the user BEFORE creating anything; never mentions AI. Flags: --analyse, --issue-only. NOT for implementing the task (use feature-loop) nor for wrapping up an existing branch (use branch-wrap-up).

  • Senior review

    ohugonnot/claude-skills/plugins/senior-review/skills/senior-review Skill

    0★ repo

    Use when the user wants a thorough senior-level fresh-eyes review of changes (working tree, staged, branch, or PR) before merge — bug hunting, security threat-model, design, tests, spec-alignment vs the linked ticket. Research-grounded pipeline: context-first assembly (cross-file call sites, conventions, git history, ticket), objective tool gate, parallel blind reviewers (reviewer ≠ author), verification gate (every critical finding needs a receipt: grep/exec/red test), adversarial refute-panel on critical/uncertain findings only. Optimizes signal/noise over recall: caps nits, explicit what-NOT-to-flag, silence when nothing material. Tiers: --quick / standard / --deep. Flags: --pr N, --base ref, --staged, --ticket N, --security, --fix, --comment, --no-tools. NOT for building features (use feature-loop) nor pure-style lint (CI does that).

  • Scope guard

    aarshsharma2803-stack/optimusprime/skills/scope-guard Skill

    0★ repo

    Activates at the start of a Claude Code session when the user's first message describes a task or coding goal. Triggers on opening messages containing: fix, build, implement, refactor, add, update, create, debug, test, review, deploy, migrate, optimize, write, remove, rename. Also triggers on: "set scope", "define contract", "what's in scope", "let's work on", "I need to". Does NOT re-trigger mid-session. Does NOT trigger on questions or follow-ups in an ongoing session. Only fires on the opening task-description message.

  • Ui ux pro max

    aarshsharma2803-stack/optimusprime/skills/ui-ux-pro-max Skill

    0★ repo

    Design intelligence for frontend work — component critique, layout review, accessibility checks, dark mode, responsive design, UX patterns. Trigger: /ui-ux-pro-max, "design review", "ux check", "accessibility audit", "review my UI", "is this accessible", "dark mode", files contain .tsx/.jsx/.css/.vue

  • Readability sweep

    digitaldreams/tuhin/skills/readability-sweep Skill

    0★ repo

    Three-pass readability cleanup of application source: remove inline comments, extract cohesive blocks into intent-named private methods, and challenge every class and method name. Use whenever the user says "readability sweep", "no inline comments", "remove comments", "check naming", "make the code readable", "extract private methods", or asks to scan the project for readability violations. Edits allowed. Scope is application source only (not tests/config) unless told otherwise. Runs lint and the full test suite after changes.

  • Review

    digitaldreams/tuhin/skills/review Skill

    0★ repo

    Review procedure for task PRs — deterministic tool output first, LLM judgment second, verdict on the board. Use when reviewing a task's pull request or when asked for a task-agent review.

  • Keel dev

    sayeediftekhar/Keel/skills/keel-dev Skill

    0★ repo

    Development conductor — the dev toolbox. Run it by name to build through the Pocock spine (grill → spec → tickets → implement → review) with gstack/superpowers as opt-in power-tools, graphify for comprehension, all governed by keel-v2.

  • Research quarantine promotion

    Lx050/rubbing-to-knowledge/skills/research-quarantine-promotion Skill

    no license0★ repo

    Safely assess one already verified quarantine JSON as bounded inert data, using a preregistered exact binding, an exclusive source-verification receipt, same-buffer identity and strict parsing, content-free structure reports, and offline producer verification. Use when research-source-acquisition has preserved an application/json asset in quarantine and a later internal workflow needs an auditable B0 gate before any IIIF, OCR, schema, literature, or knowledge-graph interpretation; do not use for arbitrary JSON, URL following, semantic validation, canonical materialization, academic admission, or public release.

  • Rubbing ocr review

    Lx050/rubbing-to-knowledge/skills/rubbing-ocr-review Skill

    no license0★ repo

    Run auditable OCR baselines on registered rubbing, stele, copybook, and inscription images, preserving empty or failed results, and create append-only, actor-declared review decisions and pending human-review handoffs. Use when comparing OCR across an original and deterministic derivatives, binding readings to image hashes and pixel regions, retaining uncertain or rejected readings, separating AI prelabels from declared-human review, or handing OCR evidence to text-structure workflows.

  • Okf validate

    shreytam/okf-toolkit/skills/okf-validate Skill

    0★ repo

    Validate a directory against the Open Knowledge Format (OKF) v0.1 conformance rules using a bundled checker script. Use this skill whenever the user asks to validate, lint, check, or verify an OKF bundle, asks "is this bundle conformant/valid", wants a conformance report before publishing or sharing a knowledge bundle, or asks why an OKF bundle isn't being consumed correctly by an agent.

  • 6 review diagnosis

    LoWeiLee/academic-ai-workflow/skills/6-review-diagnosis Skill

    no license0★ repo

    審稿診斷技能。五種使用情境必須觸發此技能:(1)Mode A:碩博士論文口試審查;(2)Mode B:外部期刊稿件審查(TSSCI 一/二/三級或國際 SSCI);(3)Mode C:投稿前自我審查;(4)Mode D:針對外審意見修正(拿到審稿人回覆後協助逐點研擬回應與修改);(5)Mode E:投稿前 AI 使用揭露(依目標期刊 AI 政策查核並產生 AI 使用聲明草稿)。觸發詞包括:「幫我審這篇稿子」、「這篇有沒有問題」、「幫我看看我的論文」、「審稿意見怎麼寫」、「這篇稿子可以過嗎」、「我要審一篇稿」、「反向診斷」、「幫我找論文的問題」、「外審意見回來了」、「幫我擬 response letter」、「逐點回應審查意見」、「碩論口試」、「博論口試」、「我是口試委員」;Mode E 觸發詞另包括:「AI 使用聲明」、「AI 使用揭露」、「這篇要不要揭露用了 AI」、「期刊的 AI 政策」、「投稿前的 AI 揭露怎麼寫」。觸發後必須先確認:審稿模式、稿件層級(影響嚴格度)、方法論類型(允許「待 AI 看完先初判」分支),並執行「對齊既有審查範本」前置步驟;Mode D 與 Mode E 為獨立工作流,不適用嚴格度與方法論確認。界定:本技能負責審查/診斷/找問題/擬外審回應/AI 使用揭露;段落正文的撰寫與重寫、動筆屬 chapter-drafting。

  • Rjv work plan

    rjvim/ai-skills/skills/rjv-work-plan Skill

    0★ repo

    Use when starting, resuming, or checking in on work on a BRANCH — bug, feature, refactor, enhancement. One committed plan per branch (.plans/{name}.md, declaring `Branch:` in its header) is the working memory: what we're doing, where we stopped, how to resume. Deterministic resume via git branch → the plan whose Branch matches → RESUME HERE block; reconcile-on-open; real-time promotion of settled facts to durable docs. Plans are kept after merge (shipped → maintenance) in .plans/shipped/, giving a delivery timeline. Triggers: 'pick up X', 'where were we', 'what's the status', 'resume', 'start this branch', 'plan this work', 'when did we ship X'.

  • Jen review

    youki0p0/jen-marketplace/plugins/jen-classic/skills/jen-review Skill

    0★ repo

    Jen review mode for acceptance review, UX/product/security/contrarian review, and PR readiness checks.

  • Jen review

    youki0p0/jen-marketplace/plugins/jen/skills/jen-review Skill

    0★ repo

    Jen review mode for acceptance review, UX/product/security/contrarian review, and PR readiness checks.

  • Bokun cross check

    duongxthanh/claude-bokun-skills/skills/bokun-cross-check Skill

    0★ repo

    Cross-check product data (price, description, schedule, inclusions, age policy...) between Bokun (source of truth) and every sales channel — your website and OTAs (GetYourGuide, Viator, ...). Use when the user wants to verify channels match, audit listings after a price change or OTA go-live, or double-check consistency. Produces a printable HTML (PDF) report.

  • Git guardrails claude code

    lankyjo/lankyjo-core-skills/skills/code/git-guardrails-claude-code Skill

    no license0★ repo

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

    The same file is in 18 other repositories

  • Grill me

    lankyjo/lankyjo-core-skills/skills/code/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 23 other repositories

  • Grill with docs

    lankyjo/lankyjo-core-skills/skills/code/grill-with-docs Skill

    no license0★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    The same file is in 11 other repositories

  • Prototype

    lankyjo/lankyjo-core-skills/skills/code/prototype Skill

    no license0★ repo

    Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

    The same file is in 11 other repositories

  • Impeccable

    lankyjo/lankyjo-core-skills/skills/design/impeccable Skill

    no license0★ repo

    Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

    The same file is in 4 other repositories

  • Landing page critique

    buildwithreef/claude-skills/skills/landing-page-critique Skill

    0★ repo

    Delivers a blunt, structured teardown of a landing page — hero, offer clarity, trust signals, CTA, friction, and mobile — with scores and rewritten copy for everything that fails. Use when the user asks for a landing page review, critique, or teardown, or says things like "why isn't my page converting", "roast my landing page", or "review this page".

  • Review responder

    buildwithreef/claude-skills/skills/review-responder Skill

    0★ repo

    Writes owner responses to Google, Yelp, and Facebook reviews — positive, negative, or fake — in an authentic local-business voice. Use when the user wants to reply to a customer review, handle a bad review, deal with a fake or wrong-business review, or says things like "how should I respond to this review", "we got a 1-star", or "write a reply to this Google review".

  • Verification discipline

    SeamStressDev/seam-scaffold/skills/verification-discipline Skill

    0★ repo

    Use this protocol whenever making a claim about what code does, did, or will do: describing behavior, confirming a fix, reporting test results, or asserting that something is safe, handled, or working. Applies to the agent's own statements throughout a session.

  • Session review

    youkistudios/session-save-system/skills/session-review Skill

    0★ repo

    Review source-attributed Session Save records across installed clients. Public lifecycle alias for session-audit.

  • Double check

    DazzleML/dazzle-claude-code-config/dotclaude/skills/double-check Skill

    0★ repo

    Exhaustively validate every claim, number, calculation, code-fact, and command in a document or outbound communication. Extracts all claims into a prioritized ledger (flagging what is NOT covered), validates each by the right method (run the math, run the command, cite the file:line, quote the primary source), then calibrates certainty with CIA Words of Estimative Probability and a provenance tier — and proposes corrected, properly-hedged rewrites for any overclaim. Use before sending a message, filing an issue, committing analysis, or whenever you state exact numbers/assertions others will rely on.

  • Merge 3 way split

    DazzleML/dazzle-claude-code-config/dotclaude/skills/merge-3-way-split Skill

    0★ repo

    Read-only pre-merge review. Lists dual-touched files, shows OURS / THEIRS / merge-base diffs, and flags likely-collision patterns so the integrator understands the full scope before running git merge. Accepts a target branch (default: main).

  • Fanout cve validation debugger

    omonuj/claude-horizon-skills/skills/fanout-cve-rollout/fanout-cve-validation-debugger Skill

    no license0★ repo

    Fetches and interprets validation logs (No-Op and Oracle) for the fanout-cve-rollout task (<TASK_ID>). Maps each of the 5 reward-shaped subscores' failures to a root cause and the smallest safe fix. Use after a validation fails before editing anything.

  • Horizon agentic reviewer

    omonuj/claude-horizon-skills/skills/fanout-cve-rollout/horizon-agentic-reviewer Skill

    no license0★ repo

    Adversarially red-team a horizon (apex-arena) RL task by spinning up a live container, injecting faults via setup.sh, probing as the agent user (model/ubuntu), and pulling rollouts. Runs a 24-point checklist (20 live-container probes + 4 rollout-statistics) to find undisclosed requirements, leaks, dead-weight subscores, and broken evidence trails. Persists failed checks to ~/.horizon-reviews/<uuid>/findings.json.

  • Horizon agentic reviewer

    omonuj/claude-horizon-skills/skills/maddy-delivery-split-brain/horizon-agentic-reviewer Skill

    no license0★ repo

    Adversarially red-team a horizon (apex-arena) RL task by spinning up a live container, injecting faults via setup.sh, probing as the agent user (model/ubuntu), and pulling rollouts. Runs a 24-point checklist (20 live-container probes + 4 rollout-statistics) to find undisclosed requirements, leaks, dead-weight subscores, and broken evidence trails. Persists failed checks to ~/.horizon-reviews/<uuid>/findings.json.

  • Maddy validation debugger

    omonuj/claude-horizon-skills/skills/maddy-delivery-split-brain/maddy-validation-debugger Skill

    no license0★ repo

    Fetches and interprets validation logs (No-Op and Oracle) for the maddy-delivery-split-brain task (<TASK_ID>). Maps observed log patterns to root causes and the smallest safe fix. Use after a validation fails to understand why it failed before editing anything.

  • Horizon agentic reviewer

    omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/horizon-agentic-reviewer Skill

    no license0★ repo

    Adversarially red-team a horizon (apex-arena) RL task by spinning up a live container, injecting faults via setup.sh, probing as the agent user (model/ubuntu), and pulling rollouts. Runs a 24-point checklist (20 live-container probes + 4 rollout-statistics) to find undisclosed requirements, leaks, dead-weight subscores, and broken evidence trails. Persists failed checks to ~/.horizon-reviews/<uuid>/findings.json.

  • Oncall validation debugger

    omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/oncall-validation-debugger Skill

    no license0★ repo

    Fetches and interprets validation logs (No-Op and Oracle) for the oncall-schedule-coverage-collapse task (<TASK_ID>). Maps observed log patterns to root causes and the smallest safe fix. Use after a validation fails to understand why it failed before editing anything.

  • Horizon agentic reviewer

    omonuj/claude-horizon-skills/skills/variation-fanout-pipeline-break/horizon-agentic-reviewer Skill

    no license0★ repo

    Adversarially red-team a horizon (apex-arena) RL task by spinning up a live container, injecting faults via setup.sh, probing as the agent user (model/ubuntu), and pulling rollouts. Runs a 24-point checklist (20 live-container probes + 4 rollout-statistics) to find undisclosed requirements, leaks, dead-weight subscores, and broken evidence trails. Persists failed checks to ~/.horizon-reviews/<uuid>/findings.json.

  • Mtls validation debugger

    omonuj/claude-horizon-skills/skills/variation-fanout-pipeline-break/mtls-validation-debugger Skill

    no license0★ repo

    Fetches and interprets validation logs (No-Op and Oracle) for the variation-fanout-pipeline-break task (<TASK_ID>). Maps observed log patterns to root causes and the smallest safe fix. Use after a validation fails to understand why it failed before editing anything.

  • Horizon agentic reviewer

    omonuj/claude-horizon-skills/skills/variation-istio-split-brain/horizon-agentic-reviewer Skill

    no license0★ repo

    DISABLED / NULLED for variation-istio-split-brain (user directive). The live red-team step is intentionally skipped — the user runs the equivalent checks themselves and finds an agent-run pass redundant. DO NOT INVOKE this skill or auto-run any step in it. The workflow is: pre-push gates -> push -> hosted Oracle -> (Oracle 1.0) -> tell the user to trigger the eval batch. The content below is retained ONLY as a manual probe reference; it is not part of any loop.

  • Istio validation debugger

    omonuj/claude-horizon-skills/skills/variation-istio-split-brain/istio-validation-debugger Skill

    no license0★ repo

    Fetches and interprets validation logs (No-Op and Oracle) for the variation-istio-split-brain task (<TASK_ID>). Maps observed log patterns to root causes and the smallest safe fix. Use after a validation fails to understand why it failed before editing anything.

  • Monday morning marketing

    kochellenk-afk/claude-marketing-skills/skills/monday-morning-marketing Skill

    0★ repo

    the operator's weekly client sweep. Runs the boring-but-compounding Monday work for any client in any industry through seven modules: competitive intel sweep, week-ahead calendar prep, industry pulse, open loops audit, content/site freshness scan, copy consistency check, and performance drift handoff. Reads client context from a Notion client profile page (creates one if missing) and publishes a Monday Briefing back to Notion with a Decisions Needed section on top. Trigger whenever the operator says "run Monday morning", "Monday briefing", "MMM", "/monday", "weekly sweep", "Monday morning in marketing", "start my week", "what changed for [client] this week", or asks for a weekly client rundown, competitive check-in, or week-ahead prep for any client (any active client). Also trigger on Mondays when they asks some variant of "catch me up on [client]". Can run for one client, a named subset, or all active clients.

  • Pbi tester

    yujiyamane/pbi-ai-skills/.github/skills/pbi-tester Skill

    0★ repo

    Static quality analysis of a Power BI Project (PBIP/PBIR/TMDL). Runs 50+ checks across 10 categories without requiring PBI Desktop, Power BI Service, or any external tools. Produces a pass/fail report with actionable findings. Use when user says: 'test my dashboard', 'check PBI quality', 'run PBI tester', 'validate PBIP', 'audit dashboard', 'static analysis', 'quality check', 'lint my report', or provides a .pbip or PBIP folder path with quality check intent.

  • Pbi tester

    yujiyamane/pbi-ai-skills/pbi-tester Skill

    0★ repo

    Static quality analysis of a Power BI Project (PBIP/PBIR/TMDL). Runs 50+ checks across 10 categories without requiring PBI Desktop, Power BI Service, or any external tools. Produces a pass/fail report with actionable findings. Use when user says: 'test my dashboard', 'check PBI quality', 'run PBI tester', 'validate PBIP', 'audit dashboard', 'static analysis', 'quality check', 'lint my report', or provides a .pbip or PBIP folder path with quality check intent.

  • Weekly review

    l3onlau/claude-life-admin/.claude/skills/weekly-review Skill

    0★ repo

    Weekly sweep — staleness, follow-ups, tracker hygiene, and CLAUDE.md rot check

  • Wiki lint

    Baikodis/claude-knowledge-base-skills/skills/wiki-lint Skill

    0★ repo

    Health-check for a Karpathy wiki. Checks broken links, INDEX intent-routes, source map, source notes & semantic layer (digested vs routing-only), duplicates, orphans, stale/caveats, contradictions, corpus drift, and structure hygiene. Use after /wiki-build, after a large corpus ingest, or when the user asks you to "check the wiki/knowledge base".