Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,409 skills from 2,375 repositories · updated 3 minutes ago
48,362 skills
- shipevo-hq/evoLand the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remote, otherwise merge into the working branch. Distills the best-scoring experiment down to the minimal diff that reproduces its behaviour, shaped for the qualities a maintainer merges on (scope discipline, test integrity, style adherence), then attaches an advisory mergeability report. Use when the user invokes /evo:ship, asks to land/merge/ship the best result, or wants to turn a finished optimization into a pull request.TestingNo warnings★ 1.5K↓ —Also in 1 other repo
- book-inithashgraph-online/awesome-codex-pluginsPhase 0: Onboarding. Define genre, reader, language, scope, and voice; capture the author's voice fingerprint; index source material; generate PRD.md and STYLE.md.PlanningNo warnings★ 1.5K↓ —
- run-workhashgraph-online/awesome-codex-pluginsExecute a work unit end-to-end: sequence tasks by dependency, implement, test between tasks, commit, and track progress. Use to deliver a complete feature in one session. Invoked as /agiflow:run-work <work-unit>. Uses get_work_unit, list_tasks, update_task, get_work_unit_progress.TestingNo warnings★ 1.5K↓ —
- delegate-to-aimohitagw15856/pm-claude-skillsDecide what in your workload to hand to AI and what to keep yourself — like managing a fast, capable, but unreliable new hire — so you get leverage without offloading the things that need you. Use when asked what should I delegate to AI, what can AI take off my plate, where should I use AI in my work, or what should I keep doing myself. Produces a sort of your tasks into delegate-fully / delegate-with-review / keep-human, the reasoning behind each line, how to brief the AI on the delegated ones, and where your judgment is the actual value — a delegation map that frees your time without giving away your edge.EngineeringNo warnings★ 1.5K↓ —
- 01-auto-arenaagentscope-ai/OpenJudgeAutomatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.TestingNo warnings★ 1K↓ —
- ui-demohashgraph-online/awesome-codex-pluginsRecord polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.DesignNo warnings★ 1.5K↓ —
- creating-agent-skillsAgentWorkforce/relayUse when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rulesPlanningNo warnings★ 1.1K↓ —
- social-listening-briefScrapeCreators/social-media-research-skillsUse when the user wants a social listening report about what people are saying about a brand, person, product, topic, category, or niche across public social platforms. Produces cited themes, sentiment caveats, notable posts, and recommended actions.OtherNo warnings★ 5.4K↓ —
- ap-synthesizerSpielewoy/autoprompt-skillReport the compatibility redirect to `ap-roadmap-author`; this retired role cannot perform new work.PlanningNo warnings★ 1.2K↓ —
- relay-80-100-workflowAgentWorkforce/relayUse when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.ProductivityNo warnings★ 1.1K↓ —
- finetuningevo-hq/evoThis skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.DesignNo warnings★ 1.5K↓ —
- env-linthashgraph-online/awesome-codex-pluginsValidate .env files against .env.example without printing valuesOtherNo warnings★ 1.5K↓ —
- relay-80-100-workflowAgentWorkforce/relayUse when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite for in-memory Postgres testing, mock sandbox patterns, test-fix-rerun loops, verify gates after every edit, and the full lifecycle from implementation through passing tests to commit.ProductivityNo warnings★ 1.1K↓ —
- oma-scmNewfirst-fluke/oh-my-agentManage Git branches, merges, conflicts, commits, and release baselines. Use for repository history and change-management operations.EngineeringNo warnings★ 1.4K↓ —
- create-prhashgraph-online/awesome-codex-pluginsCreate a GitHub pull request from the current branch. Use when the user says 'create a pr', 'open pr', 'push and open a pr', 'create pull request', or wants to open a PR from their branch.EngineeringNo warnings★ 1.5K↓ —
- ad-creative-testingNewhashgraph-online/awesome-codex-pluginsTurn one winning ad into a creative testing plan for TikTok and Meta. Decodes why an ad won (hook, argument, buyer, format), plans concepts that Meta's Andromeda and TikTok treat as genuinely different (buyer × angle × format × first frame, not caption swaps), sets how many creatives to launch, the budget per test and when to judge, writes file and ad names that make results readable, reads hook rate, hold rate, CTR and CPA to find which part failed, and says when to kill, iterate or scale. Use when someone asks how many ads to test, how to make ad variants, why their variants all perform the same, whether an ad is fatigued, when to kill an ad, or how to scale a winner. NOT for producing the videos (use ecommerce-video-ads, ecommerce-video-edit or product-video-hooks) or for media-buying account setup.TestingNo warnings★ 1.5K↓ —
- django-q2hashgraph-online/awesome-codex-pluginsUse when adding, changing, testing, or debugging Django Q2 background tasks, scheduled jobs, qcluster workers, Redis broker configuration, or ORM broker fallback in Django projects.TestingNo warnings★ 1.5K↓ —
- followup-sweepmohitagw15856/pm-claude-skillsSweep the user's REAL mail and calendar for dropped balls — threads awaiting their reply, promises they made, and replies they're owed — then draft the nudges. Use when asked what am I forgetting, what have I not replied to, who owes me a reply, or chase my open threads in Cowork. Reads sent/received mail via the Gmail connector and recent events via Calendar, finds the open loops, and produces a follow-up-list artifact plus ready-to-send draft nudges.ProductivityNo warnings★ 1.5K↓ —
- publish-pcf-companionmicrosoft/power-platform-skillsDeploy the dispatcher PCF for a third-party `.ppmplugin` control to a Power Platform environment via `pac pcf push`. The dispatcher PCF is the Studio-side control that dispatches the composite key `<name>/<receiver>` over the wrap shell's `SendMessagePlugin` bridge to the control's native module. Verifies deploy prereqs (Node.js 20+ with npm, .NET SDK, and active `pac auth`), then three confirmation gates — publisher prefix (2–8 chars; defaults to `pamext` or the last-used value from `.extension-state.md`), version bump (patch / minor / major / no-bump), target environment URL (from `pac org who`). Builds the PCF if needed, then pushes. Decoupled from /generate-pcf-companion so the engineer can scaffold and customize locally, then deploy when ready. Updates `.extension-state.md` with deployment history (timestamp, env URL, version, prefix used).DevOpsNo warnings★ 1.1K↓ —
- oma-qafirst-fluke/oh-my-agentReview changes for correctness, security, accessibility, and performance. Use for scoped quality reviews or verification plans; bug fixes use oma-debug.TestingNo warnings★ 1.4K↓ —
- oma-skill-creationfirst-fluke/oh-my-agentCreate or revise OMA skills and their references. Use for skill routing, execution contracts, conditional loading, and authoring validation.OtherNo warnings★ 1.4K↓ —
- my-energy-mapmohitagw15856/pm-claude-skillsMap your real energy through the day and week, then match your tasks to it — hard things when you're sharp, easy things when you're not. Use when asked when should I do my hard work, map my energy, why am I so unproductive at certain times, or schedule around my focus. Produces a picture of your energy peaks, troughs, and patterns from your own observations, a task-to-energy matching plan (deep work at peaks, admin at troughs), the traps you're currently falling into, and a realistic daily shape — because fighting your natural rhythm wastes your best hours on your worst tasks.PlanningNo warnings★ 1.5K↓ —
- improve-search-visibility-store-listing-auditgooseworks-ai/goose-skillsAudits an app's App Store and Google Play listing against three competitors (title, subtitle, description opening, first screenshots and captions, rating, review themes) and writes a field-by-field rewrite with character counts, or a launch-day listing before release. Use alone when you already have the app's store links and signed-off product facts; otherwise run improve-search-visibility.WritingNo warnings★ 1.3K↓ —
- sno-mem-claudesno-ai/sno-stationUse Sno memory from Claude through four explicit commands.ProductivityNo warnings★ 1.1K↓ —
architect
hashgraph-online/awesome-codex-plugins
NewPlanningUpdated 16 hours ago
From the author
Settle structure before writing logic. Ground in the current code, get competing design sketches (types, signatures, modules, trust boundaries) through arena, implement against the merged sketch, scrap it on a friction pattern. Use for "architect this", "design X first".
Install
npx skills add hashgraph-online/awesome-codex-plugins --skill architect -a claude-code
Installs to .claude/skills/architect/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance78
Maintenance100
Licence100
Adoption51
Files (4)
- SKILL.md
- references/rationale-template.md
- references/red-flags.md
- references/runner-brief.md