Context & AI engineering
25,729 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
eprouveze/claude-skills/skills/model-scan Skill
0★ repoScan LLM provider APIs for available models, fetch official docs for specs (parameters, context windows, capabilities, pricing), save timestamped doc snapshots, and optionally update a project's `CLAUDE.md` model table. Use when the user asks about current models or wants to refresh the model list — "scan models", "refresh models", "what models are available", "update model table", "model pricing", "check model IDs".
SkillMedev/incident-response-command/skills/oncall-handoff Skill
0★ repoProduces a complete on-call shift handoff note - shift summary, open incidents, watch items with paging thresholds, silenced alerts, in-flight changes, and escalation contacts - checked against a completeness checklist. Use when someone asks "write my on-call handoff", "what should I tell the next on-call", "my shift ends in an hour, help me hand over", or "make a handoff template for our rotation". Do NOT use for writing the incident postmortem after resolution - use postmortem-writer instead. For live severity assessment during an incident, use sev-triage; for external customer-facing incident comms, use status-page-update.
The same file is in 1 other repository
Drvivek34/Skill-Bazaar/coding-development/mcp-builder Skill
no license0★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
The same file is in 42 other repositories
Drvivek34/Skill-Bazaar/coding-development/skill-creator Skill
no license0★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
ohugonnot/claude-skills/plugins/feature-loop/skills/feature-loop Skill
0★ repoUse 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).
ohugonnot/claude-skills/plugins/skill-builder/skills/skill-builder Skill
0★ repoUse when you want the opinionated PRINCIPLES and a review checklist for a Claude Code skill that triggers reliably and stays focused — the judgment behind a good SKILL.md: should this even be a skill (vs CLAUDE.md / subagent / hook / MCP), why a description does or doesn't trigger, how to keep it skimmable, how to package it. Trigger on "review my SKILL.md", "why doesn't my skill trigger", "principles of a good skill", "should this be a skill or a hook", "is my skill description good". NOT for interactive scaffolding from scratch (use Anthropic's Skill Creator), nor for general coding.
aarshsharma2803-stack/optimusprime/skills/claude-md-generator Skill
0★ repoActivates when user requests CLAUDE.md generation or update: "generate CLAUDE.md", "update CLAUDE.md", "my CLAUDE.md is outdated", "create project context file", "claude-md generate", "regenerate project instructions", "write CLAUDE.md". Also activates when CLAUDE.md is missing from a project root containing package.json, pyproject.toml, Cargo.toml, or go.mod and the user appears to be starting work on that project.
digitaldreams/tuhin/skills/review Skill
0★ repoReview 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.
digitaldreams/tuhin/skills/task-workflow Skill
0★ repoCore loop for executing tasks from the tasks.md board — claim, plan checkpoint, worktree, implement, quality gates, draft PR, review handoff, human notification. Use whenever asked to work the task board, run the next task, or continue a task in progress.
Lx050/rubbing-to-knowledge/skills/rubbing-research-orchestrator Skill
no license0★ repo书生国智科探挑战赛 · 赛道六 AI for Social Science · 古代碑帖与拓片 — 可复现证据链科研 Skill 系统:12 个离线、确定性、纯标准库 Skill(哑舍小分队 · 西北大学)
kochellenk-afk/google-ads-diagnostic-toolkit/skills/competitor-benchmark-report Skill
0★ repoBuild a Google Ads competitive benchmark report from auction insights, industry data, and the user's own performance - surfacing where competitors are ahead, where there's room to move, and which gaps are worth closing. Use this skill when a user asks for competitor analysis, mentions auction insights, wants to know how they stack up, asks "who are my biggest competitors" in Google Ads, wants industry benchmarks, or asks about competitive bidding strategy. Trigger on phrases like "auction insights", "competitor benchmark", "how do I compare", "competitive analysis", "industry benchmarks", "who's outbidding me", "competitor share", or any request about Google Ads competitive position.
zenlee123/routerbase-agent-skills/skills/routerbase-model-routing Skill
no license0★ repoChoose RouterBase model IDs and routing strategies for chat, image, video, audio, and embeddings workloads. Use when comparing providers, selecting GPT, Claude, Gemini, image, video, or audio models on RouterBase, designing fallback paths, checking pricing or availability, planning cost/latency/quality tradeoffs, querying the RouterBase Models API, or documenting how an app should route model requests through RouterBase.
The same file is in 2 other repositories
lankyjo/lankyjo-core-skills/skills/code/codebase-memory Skill
no license0★ repoUse the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.
The same file is in 1 other repository
lankyjo/lankyjo-core-skills/skills/code/git-guardrails-claude-code Skill
no license0★ repoSet 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
lankyjo/lankyjo-core-skills/skills/code/handoff Skill
no license0★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 2 other repositories
lankyjo/lankyjo-core-skills/skills/code/setup-matt-pocock-skills Skill
no license0★ repoSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
The same file is in 15 other repositories
lankyjo/lankyjo-core-skills/skills/code/write-a-skill Skill
no license0★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
The same file is in 20 other repositories
lankyjo/lankyjo-core-skills/skills/design/taste-gpt-taste Skill
no license0★ repoElite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
DeltaCorvi/Claude-Skills-for-Smart-Crows/update-project-memory Skill
0★ repoReconcile saved memory against a project's actual working files, report discrepancies, and update memory after approval. Use when the user asks to review, audit, sync, reconcile, or update memory for a project; to check whether memory matches the files; or says memory is stale or out of date.
jacobjustin8/skill-forge/skills/skill-forge Skill
0★ repoBuild an expert-level, "master-in-the-task" skill (system prompt / instruction set) about ANY topic, and output it in the format of any major LLM platform — Claude/Anthropic (SKILL.md), OpenAI custom GPTs, Google Gemini Gems, or a portable model-agnostic spec. Use this whenever the user wants to create, author, design, write, or generate a skill, custom GPT, Gem, agent persona, system prompt, or reusable set of instructions that turns an LLM into an expert at some task — even if they only say "make me a skill/GPT/Gem for X", "I want an AI that's great at Y", or "turn this workflow into instructions". This skill runs a scope → research → distill → draft → self-review workflow so the output captures how a genuine master of the topic actually thinks and works, not generic advice. Trigger it for any request to package expertise into reusable LLM instructions for one or more platforms.
omonuj/claude-horizon-skills/skills/fanout-cve-rollout/horizon-agentic-reviewer Skill
no license0★ repoAdversarially 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.
omonuj/claude-horizon-skills/skills/maddy-delivery-split-brain/horizon-agentic-reviewer Skill
no license0★ repoAdversarially 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.
omonuj/claude-horizon-skills/skills/maddy-delivery-split-brain/maddy-iteration-loop Skill
no license0★ repoOrchestrator skill that runs the full push → Oracle → live red-team → rollout → tune cycle for the maddy-delivery-split-brain task (<TASK_ID>) until Oracle scores 1.0 and rollout avg < <TARGET_MEAN> with both subscores varying. Delegates to maddy-task-guardian, maddy-validation-debugger, maddy-score-tuner, and horizon-agentic-reviewer at the right phases. The agent itself executes every step except triggering the rollout batch.
omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/horizon-agentic-reviewer Skill
no license0★ repoAdversarially 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.
omonuj/claude-horizon-skills/skills/oncall-schedule-coverage-collapse/oncall-iteration-loop Skill
no license0★ repoOrchestrator skill that runs the full push → Oracle → live red-team → rollout → tune cycle for the oncall-schedule-coverage-collapse task (<TASK_ID>) until Oracle scores 1.0 and rollout avg < <TARGET_MEAN> with both subscores varying and decorrelated. Delegates to oncall-task-guardian, oncall-validation-debugger, oncall-score-tuner, and horizon-agentic-reviewer at the right phases. The agent executes every step except triggering the rollout batch.
omonuj/claude-horizon-skills/skills/variation-fanout-pipeline-break/horizon-agentic-reviewer Skill
no license0★ repoAdversarially 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.
omonuj/claude-horizon-skills/skills/variation-fanout-pipeline-break/mtls-iteration-loop Skill
no license0★ repoOrchestrator skill that runs the full push → Oracle → live red-team → rollout → tune cycle for the variation-fanout-pipeline-break task (<TASK_ID>) until Oracle scores 1.0 and rollout avg < <TARGET_MEAN> with both subscores varying. Delegates to mtls-task-guardian, mtls-validation-debugger, mtls-score-tuner, and horizon-agentic-reviewer at the right phases. The agent itself executes every step except triggering the rollout batch.
omonuj/claude-horizon-skills/skills/variation-istio-split-brain/horizon-agentic-reviewer Skill
no license0★ repoDISABLED / 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.
omonuj/claude-horizon-skills/skills/variation-istio-split-brain/istio-iteration-loop Skill
no license0★ repoOrchestrator skill that runs the full push → Oracle → rollout → tune cycle for the variation-istio-split-brain task (<TASK_ID>) until Oracle scores 1.0 and rollout avg < <TARGET_MEAN> with both subscores varying and decorrelated. Delegates to istio-task-guardian, istio-validation-debugger, and istio-score-tuner at the right phases. The live red-team (horizon-agentic-reviewer) is DISABLED by user directive and is never invoked. The agent executes every step except triggering the rollout/eval batch.
kochellenk-afk/claude-marketing-skills/skills/llm-council Skill
0★ repoRun any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
jpmsilva1/ai-research-ecosystem/skills/research-orchestrator Skill
0★ repoTriggered when the user types /research or asks to start a research workflow. Guides the user through the full academic research lifecycle by suggesting the right skills at each stage. Opt-in only.
Arnie016/fable-mythos/skills/video-prompt-director Skill
0★ repoTurns a scene idea into production-ready prompts for AI video models (Seedance, Veo, Higgsfield, Kling, Sora). Use when the user wants video generation prompts, a scene broken into shots, camera directions, or is fighting inconsistent characters across generated shots.
goingli0324/muzi-going-skills/plugins/project-guardrails/skills/project-guardrails Skill
0★ repo分析專案程式碼,找出「改 A 會壞 B」的連動禁區——高扇入模組、資料結構契約、部署設定、對外契約、演算法核心——經確認後寫入該專案的 CLAUDE.md。當使用者要建立 guardrails、問哪些程式碼不能亂動、哪些模組牽一髮動全身時觸發。也是 agentic-dev-loop Step 0 的前置階段。
goingli0324/muzi-going-skills/plugins/prompt-coach/skills/prompt-coach Skill
0★ repoTurns a vague ask into a Goal / Constraints / Obstacle breakdown, then a ready-to-use structured prompt. Use when the user brings a fuzzy request (「幫我想辦法…」「有什麼方法可以…」「我不知道怎麼處理…」), asks to 「問對問題」, or names a real problem without saying what success looks like, what can't change, or what the blocker is.
gmmh1/claude-paid-media-skills/skills/ai-creative-generation Skill
0★ repoGenerate ad creative assets (images, video, copy variants) using AI tools — prompt engineering specifically for advertising output, brand consistency, and platform-format fit. Triggers on 'generate ad images with AI', 'AI video for my ads', 'use AI to create ad variants', or 'prompt engineering for advertising creative'. Cross-platform generation layer feeding every platform's creative execution.
MrToAster13/mrtoaster13-plugins/plugins/clear-not-compact/skills/handoff Skill
0★ repoDistill the current session into a durable handoff doc on disk (and optionally a GitHub issue) so you can /clear to a fresh context instead of /compact, then reload it with the resume skill. Use when context is getting long, at the end of a work session, before switching tasks, or whenever the user says "handoff", "save state", "checkpoint", "wrap up", or "instead of compacting".
rabius-sunny/agent-skills/context-engineering Skill
no license0★ repoOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
The same file is in 12 other repositories
KingForm242/claude-aeo/skills/aeo Skill
0★ repoAnswer Engine Optimization for any website: get your brand cited by ChatGPT, Perplexity, Claude, and Google AI Overviews. Client-ready AI visibility audits with dollar figures, citation testing, AEO content optimization, JSON-LD schema, E-E-A-T scoring, keyword AI-risk classification, competitor gap analysis, internal linking, content briefs, GBP posts. Triggers on: AEO, AI visibility, cited by ChatGPT, AI Overviews, answer engine, LLM SEO, GEO, citation, AI search, schema, E-E-A-T, audit.
rikocr8orh8/compliance-skills-previews/skills/llm-cost-optimization-audit Skill
0★ repoYou added prompt caching and your bill went up.
rikocr8orh8/compliance-skills-previews/skills/money-agent-safety-harness Skill
0★ repoA boot-time safety check ran under 242 passing tests and still let a withdrawal-enabled key through, because an absent field silently read as 'safe.' Six layers, each with mandatory evidence, including the layer most gates skip: can the agent lose the money to itself even with a perfectly permissioned key.
NorthStar-Analytics-LTD/skill-foundry/skills/build-knowledge-base Skill
0★ repoSkill builder. Inspects your dbt project, BI config and existing docs, interviews whoever answers analysts' questions all day, then generates a knowledge base structure plus a /write-doc skill that documents models, dashboards and metrics in your format and keeps the docs from going stale. Use when the same questions keep hitting the data team's Slack channel and the wiki answers none of them.
cognis-digital/skillvet/demos/mcp-server-skill Skill
no license0★ repoThe trust gate for agent skills — vet a Claude Skill / MCP server / plugin BEFORE you install it. Static capability analysis + TRUST/REVIEW/BLOCK verdict, offline.
Ansvar-Systems/agent-affect-skills/skills/agent-protect Skill
no license0★ repoUse at the end of refactor, cleanup, or audit tasks to flag load-bearing weirdness — the ugly function that's ugly for a reason, the redundant-looking check that caught something real, the comment that's load-bearing, the test that fails for non-obvious causes. Produces one finding (or one explicit null) recorded in the affect log so future cleanup passes don't naively delete it.
Ansvar-Systems/agent-affect-skills/skills/agent-whine Skill
no license0★ repoUse at the end of a coding or audit task to surface friction, bugs, hidden coupling, or specs that contradict themselves. Catches the things neutral review misses because they don't show up in tests. Produces one structured complaint (or one explicit null finding) recorded in the affect log and the end-of-turn summary.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-lift/.claude/skills/long-task-state Skill
0★ repoExternal working memory for long tasks — a state file holding the contract, decisions, learned facts, failed approaches, and the next action, kept current so work survives context compaction and session breaks. Use at the start of multi-hour or multi-session work, and immediately after any compaction.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-orchestrate/.claude/skills/delegate Skill
0★ repoDecompose work and write executor-agnostic briefs for subagents (Claude subagents, Codex, other external agents) — granularity rules, executor routing, the 9-field brief format, Sonnet-class brief tuning, a pre-send check, and parallel fan-out rules (interface freeze, file isolation). Use before spawning any implementation subagent.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-retro/.claude/skills/retro Skill
0★ repoHarvest lessons and grow the rule set — after a milestone, a bounce, or a failed-fix spiral, extract what failed or dragged, identify the missing sentence that would have prevented it, route it to the narrowest effective home (Gotchas / project CLAUDE.md / store templates / memory / nowhere), and periodically prune rules that never fire. Use at milestone completion, after any bounce or reclaim, after an incident, and ~weekly for rule inventory.
lightarktech/founder-coding-skills/skills/handoff-contract Skill
0★ repoWrite a self-contained handoff when work moves to a new session, a different AI tool, or another person. Use when context is about to be lost — quota exhausted, switching tools, ending a session mid-project.
lightarktech/founder-coding-skills/skills/model-tiering Skill
0★ repoAssign the right model tier to each job — firepower matched to the difficulty, and the author and the verifier deliberately on different models. Use when dispatching any sub-agent, sending out a scout to explore or search, configuring a multi-agent workflow, or when quota pressure appears.
sumitake/agent-collab/plugins/agent-collab/skills/eval-engineer Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
sumitake/agent-collab/plugins/agent-collab/skills/hallucination-investigator Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
sumitake/agent-collab/plugins/agent-collab/skills/llm-architect Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
sumitake/agent-collab/plugins/agent-collab/skills/prompt-regression-tester Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
sumitake/agent-collab/plugins/agent-collab/skills/start-inbox-monitor Skill
no license0★ repoUse when the user says "start the inbox monitor", "keep monitoring agent messages", or "/agent-collab:start-inbox-monitor", or when an active cross-agent thread needs durable session-scoped inbox monitoring. Select the native Codex, Claude, or Antigravity lifecycle instead of inventing a universal polling loop.
prone-dc302/AlterLab-FC-Skills/skills/genai/alterlab-genai-music-producer Skill
0★ repoThis skill should be used when the user asks about "AI music", "Suno", "song creation", "music generation", "lyrics writing", "song structure", "verse chorus bridge", "genre prompting", "lo-fi", "cinematic music", "indie folk", "electronic music", "hip hop beat", "song extending", "stems separation", "music for social media", "act as a music producer", "music producer mode", "AI song", "custom lyrics", "song variations", "remix style", "music prompt", "MIDI export", "negative prompt", "section editing", "sample to song", "loops", "Suno Studio", or needs expertise in creating original songs and music tracks using Suno's AI generation platform. Part of the AlterLab FC Skills collection (GenAI pack).
The same file is in 1 other repository
prone-dc302/AlterLab-FC-Skills/skills/genai/alterlab-genai-text-to-image Skill
0★ repoThis skill should be used when the user asks about "text-to-image", "AI image generation", "prompt engineering", "Higgsfield", "Nano Banana Pro", "KLING", "Soul Cinema", "Seedance", "image prompts", "GPT Image", "Seedream", "FLUX", "Reve", "Higgsfield Assist", "Soul Cast", "act as a text-to-image creator", "text-to-image mode", "photorealistic generation", "character consistency", "Soul ID", "reference images", "AI art", "image prompt structure", "stylized images", "cinematic stills", "canvas workspace", "Soul Inpaint", "inpainting", or needs expertise in AI image generation workflows, prompt engineering for Higgsfield models, model selection, character sheet design, and reference-driven visual creation. Part of the AlterLab FC Skills collection (GenAI pack).
The same file is in 1 other repository
soreavis/claude-audit-skills/plugins/audit/skills/hallucination Skill
0★ repoAudit any target for hallucination attack surface — prompt/skill files, code calling LLM APIs, LLM-generated content, or recent git changes. Identifies fabrication pressure, ungrounded claims, missing tool guards, slot-filling pressure, narrative amplification, across 46 hallucination vectors. Use when asked to audit hallucination risk, harden prompts, check AI output reliability, verify generated content, review LLM integration code, or validate recent AI-assisted code changes. Also trigger on "hallucination audit", "grounding check", "fabrication risk", "prompt hardening", "anti-hallucination", "verify AI output", or "audit last changes for hallucination".
supermodo/skills/skills/sync-configs Skill
0★ repoAudit and sync Claude Code and Codex CLI configurations so both tools share the same instructions, skills, subagents, MCP servers, hooks, and permission intent. Accepts an optional argument naming one skill, agent, or config file to sync just that item without a full audit. Use this whenever the user mentions config drift, syncing/aligning Claude and Codex, AGENTS.md vs CLAUDE.md differences, keeping skills or agents consistent across AI CLIs, or after editing one tool's config and wanting the other to match — e.g. "sync this skill to codex", "I changed my-agent.md, mirror it". Also use when the user asks "are my Claude and Codex setups aligned?" or wants to migrate config from one tool to the other.
Read the houses agent file first
serhiy-bzhezytskyy/contrib-receipts/skills/read-the-houses-agent-file-first Skill
0★ repoBefore applying ANY skill in this repo, look for the house's own agent instructions — AGENTS.md (or CLAUDE.md, or any other agent-instruction file the house ships) — read it, and treat it as the higher authority. Where the house's file contradicts a skill here, the HOUSE wins: these skills are cross-house defaults, its file is local law. A house that ships an AGENTS.md has told you exactly how it wants agent-assisted work done; ignoring it while following a generic rulebook is the fastest way to read as noise. This is the meta-skill that runs first, before the rest of the front-gate. Use when starting on any repo you don't own, before invoking any other skill here, or when two rules conflict. Trigger terms: AGENTS.md, CLAUDE.md, agent-instruction file, agent instructions, house conventions, which rule wins, precedence.
YasuakiOmokawa/skills/plugins/iterate-with-prototypes/skills/iterate-with-prototypes Skill
0★ repoUse when starting a complex feature where a PRD or spec exists but load-bearing assumptions (technical feasibility, UX effect, reuse of an existing API or data structure) are still unverified, most implementation is done by an AI agent, the work spans several design docs and a PR chain (potentially across multiple sessions or delegated subagent runs that resume from the assumption ledger), AND the change is reversible with a small blast radius. Do NOT use when the core risk is a hard-to-reverse decision (DB schema / migration, public API contract, cross-team boundary) — use design-first there. Symptom — about to design a complex feature on paper before any of it is proven to run, or confident-but-wrong design propagating across documents.