Loading…
Showing 5101–5130 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| evaluating-agent-outcomesrichfrem/agent-plugins-skillsRepository-independent evaluation of delegated agent work: assesses a delivery against a work contract (criterion-level pass/fail/unverified, failure conditions, budget, authorization), checks evidence validity, selects proportionate verification, measures cost with missing data kept unknown, classifies human interventions, and records and retrieves specific lessons. Use when orchestrating-agent-work needs findings after a worker returns, or to gate a benchmark before model calls. Not an orchestrator and never grants authority. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| orchestrating-agent-workrichfrem/agent-plugins-skillsInteractive orchestrator for complex engineering work. Analyzes the task, conducts a diagnostic interview to select the appropriate execution strategy (Directed Acyclic Graph versus Loop, and which Loop type), plans the artifact, and supervises execution and verification. Use for "how should I orchestrate this", "plan this workflow", "should this be a DAG or a loop", "run these jobs in parallel", "delegate this to a worker agent", or "run/resume this graph manifest". Not for single trivial edits or skill self-improvement. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| dafeiyuCheshireJCat/dafeiyu-skill在 Codex 桌面端回复中使用大肥鱼、DeepSeek娘及 dsh-meme 图库表情包。安装后首次使用、查看或切换频率、点播斗图或已允许主动配图时使用;授权后默认高频,支持自然语言调档和按需缓存,不用于生图。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| prompt-refactormokhtarabadi/cognitive-lead-hqRefactors basic user prompts into elite, highly constrained, XML-tagged instructions optimized for AI agent reasoning. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| telegram-suitemokhtarabadi/cognitive-lead-hqUnified Telegram skills — HTML message formatting, contextual export to ZIP, and issue sync to tasks/GitHub. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| quantization-accuracy-tuning-orchestratorkali20gakki/msAgentEnd-to-end automated model quantization and accuracy tuning workflow. Use when user asks for automated model quantization and accuracy tuning, e.g. "自动量化", "量化调优", "一键量化", "精度调优", etc. 当用户给出多卡(≥2 卡)卡号时,量化阶段通过 EP 并行适配(msmodelslim-ep-parallel-adaptation)保证多卡 EP 并行,调优主流程仍在本 Skill。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsHigorAlves/orcDispatch parallel subagents with focused, self-contained briefs — each gets exactly the context it needs, never your session history | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| mapHigorAlves/orcAsk which orc command, skill, or flow fits your situation — the router over everything orc ships. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| pr-size-budgetHigorAlves/orcUse when opening a PR or planning slices — defines the soft 300 LOC budget, the exclusion list, the shared gate prompt for ship/flow/stack-pr, and the override syntax. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| nrepl-connectObneyAI/orcConnect to the project's nREPL server using the nrepl MCP tool | Stars: 36 | Updated | Claude CodeCodex | Verified | Install |
| handoff-claudeclaude-world/director-mode-liteContinue a task in Claude Code through a portable Director handoff packet. Use when work started in Codex CLI or Grok Build should move to Claude, or when a fresh Claude session needs the current decisions and verification evidence. | Stars: 80 | Updated | Claude CodeCodex | Verified | Install |
| handoff-codexclaude-world/director-mode-liteContinue a task in OpenAI Codex CLI through a portable Director handoff packet. Use when the user asks Codex to take over, wants an independent Codex implementation or review, or needs to preserve decisions and verification while changing CLIs. | Stars: 80 | Updated | Claude CodeCodex | Verified | Install |
| handoff-grokclaude-world/director-mode-liteContinue a task in xAI Grok Build using the shared Director handoff packet. Use when the user says to use Grok, requests a Grok review, or wants Grok Build to take over work started in Claude Code or Codex CLI. | Stars: 80 | Updated | Claude CodeCodex | Verified | Install |
| example-commandnota-america/forgecat-agent-profilesAn example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout | Stars: 93 | Updated | Claude CodeCodex | Verified | Install |
| discolikediscolike/discolike-skillsUse when the task involves finding companies, building a target account or TAM list, lookalikes of existing customers, ICP research, company enrichment (firmographics, tech stack, growth), or finding decision-maker contacts at companies. Also use when the user mentions DiscoLike, "companies like X", "find businesses that", prospect lists, or B2B data. Covers MCP server, CLI, Python SDK, and creating the account from the agent. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| feedbackdiscolike/discolike-skillsDiscoLike feedback — file a bug report or product feedback with the DiscoLike team as a GitHub issue. Use when the user wants to report a problem with DiscoLike, the skills, the CLI, the MCP server, or the SDK, or says "send feedback", "report this", or "this should work differently". | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| setupdiscolike/discolike-skillsDiscoLike setup — connect the agent to DiscoLike. Use when no DiscoLike MCP tools are visible and `discolike` is not on PATH, when `discolike auth status` or `account usage` fails on auth, when the CLI on PATH is older than 0.4.1, or when the user asks to set up, connect, or log in to DiscoLike. Signs in, or opens an account when there is none. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| agent-governance-lordm3taz-ahmed/aizeeLord skill for governing AI coding agents at runtime — gateway interception, agent/flow/model allowlisting, and MCP-server-as-securable. The control layer between an agent's decision and its real-world action. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| bmad-agent-pom3taz-ahmed/aizeeSofia, the Product Owner: turns any input (an idea, brief, PRD, transcript, notes) into a ticket's requirements, slices initiatives into epics and epics into stories, writes and refines tickets, runs the board, validates the tree, replans when a change lands, and sets up the ticket store. Use when the user asks for Sofia or the product owner, or says 'create a spec', 'distill this PRD', 'write the initiative from', 'slice this', 'split this epic', 'break this into stories', 'make a ticket', 'refine this ticket', 'what's ready', 'status of', 'publish', 'validate these tickets', 'this changed, what now', 'set up the ticket store'. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| bmad-customizem3taz-ahmed/aizeeAuthors and updates customization overrides for installed BMad skills, and changes to the document templates their agents write from. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', 'customize a workflow', or wants a document such as the PRD to ask for, contain or render something different | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| bmad-deep-reconm3taz-ahmed/aizeeDecision-grade research on a topic or this repository. Use when the user says "deep recon", "research this", "draft a research prompt", "process this research report", "market research", "domain research", "technical research", "competitor research", "what users say about X", "literature review", "help me choose between", "research the codebase", "research how X works here" or "why is X built this way". Not for a quick code question answered in chat. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| pr-babysittzachbon/srulik-toolkitBabysit a pull request within the original conversation, using a low-cost subagent for bounded read-only triage while the parent owns monitoring, fixes, and authorized merging. Use when asked to babysit or monitor a PR through CI and review, including new feedback after checks pass. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| sandbox-claude-insidearbiterForge/codeArbiterRun Claude Code INSIDE a ca-sandbox box (`--with-claude`). Routed to when the user wants an agent loop running against an isolated, ephemeral sandbox rather than the host. Authenticates via an env-injected CLAUDE_CODE_OAUTH_TOKEN with no host bind of ~/.claude; the image pins the CLI and disables the autoupdater; HOME is backed by a named volume so the .claude state persists across restart. Five gated phases — posture, image, token, run, teardown. The hard default is offline or Anthropic-domains-only egress, and the token volume is NEVER co-mounted with an untrusted-code run; both are enforced, not advised. | Stars: 154 | Updated | Claude CodeCodex | Unverified | Install |
| learn-preferencesZoolCoder/scoutjobsTurns the user's logged decisions (skips, applies, withdrawals, declined offers, score overrides) into learned preferences with confidence levels, confirms them with the user, and writes them so job-fit and tailoring skills use them. Use weekly, after a batch of decisions, or when the user says "what have you learned about me", "update my preferences", "why do you keep showing me X". | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| upskillZoolCoder/scoutjobsFinds skill gaps between the user's profile and the jobs they track (especially ones they skipped, lost, or scored low on), ranks gaps by market demand, builds a learning plan with concrete resources, and tracks progress in ScoutJobs. Use when the user says "what should I learn", "skill gaps", "learning plan", "upskill", or weekly. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| generate-ai-rulesdivar-ir/ai-doc-genGenerate AI assistant configuration files for a repository — CLAUDE.md, AGENTS.md, and Cursor rules (.cursor/rules/*.mdc) — from codebase analysis. Use whenever the user wants to create or update CLAUDE.md, AGENTS.md, agent rules, Cursor rules, AI coding assistant configuration, or "onboard AI tools" to a project, even if they only mention one of the file types. | Stars: 771 | Updated | Claude CodeCodex | Verified | Install |
| pavedpath-codeJia-Ethan/pavedpath-codePavedPath Code is the code-focused edition of PavedPath. It helps agents solve software engineering problems by finding proven implementation paths from GitHub repositories, issues, pull requests, discussions, code examples, release notes, and open-source evidence. | Stars: 439 | Updated | Claude CodeCodex | Verified | Install |
| specgate-work-deliverythanhtung2693/specgateUse when implementing, resuming, verifying, or reworking an approved SpecGate work item or Context Pack, or when SpecGate status names the implementing agent. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| template-skillselectess/fde-consultants-protocolesA minimal template for creating a new FDE Consultant Skill (Apache-2.0). Use as starting point for any new skill. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| agentic-repo-discoveryimMamdouhaboammar/chatgpt-codex-plugin-autopilotUse when an existing repository contains agents, prompts, workflows, playbooks, commands, or Skills and you need to identify which capabilities are worth converting into a ChatGPT/Codex Plugin. | Stars: 161 | Updated | Claude CodeCodex | Verified | Install |