RADAR DES SKILLS · GITHUB
Des Agent Skills utiles, classés selon leur usage réel.
Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.
- PÉRIMÈTRE
- VÉRIFIÉ
- Skills
- 5 771
- dépôts
- 824
- dernière synchronisation
- 8 sept. 2026
xiehuan123dsh-deepread
Evidence-first deep reading for books, articles, PDFs, and document sets. Extract core claims, argument structure, supporting evidence, source locations, confidence levels, knowledge maps, and recall questions. Use when the user asks to deep-read, analyze an article, extract claims, trace evidence, map knowledge, compare documents, or learn with the Feynman technique; also matches Chinese requests such as 精读、分析文章、核心观点、论证逻辑、知识地图、费曼读书法. Five modes are quick, deep, map, feynman, and book.
- installations
- 1
- GitHub Stars
- 48
- Mis à jour
- 3 sept.
anycap-aianycap-ai-tool-seo
Guide for planning and auditing SEO for AI tool, SaaS, and product-led websites. Powered by AnyCap -- the capability runtime that equips AI agents with web search and web crawl through a single CLI. Use when Codex needs to define SEO ICPs, map search intent to page types, inspect live SERPs, write page briefs for tool/comparison/alternatives/pricing/tutorial pages, prioritize technical SEO foundations, plan citations or backlinks, or decide whether programmatic SEO is safe and worthwhile. Trigger on mentions of AI tool SEO, SaaS SEO, product-led SEO, search intent, page type mapping, vs pages, alternatives pages, pricing pages, directory submissions, backlink plans, citations, or pSEO.
- installations
- 1
- GitHub Stars
- 43
- Mis à jour
- 25 août
anycap-aianycap-worldcup-predict
World Cup match prediction and pre-match intel for football (soccer) fans: predict who will win and a likely scoreline, backed by structured, verifiable evidence -- player profiles, squad dossiers, current form, head-to-head records, and past-tournament history -- using AnyCap web search and crawl. Weighs FIFA ranking, recent form, head-to-head, and key players, plus any user-defined dimensions (home advantage, injuries, rest, weather, vibes), then makes a clearly-labeled for-fun call with a confidence level and a mandatory disclaimer. Built on the 'search less, not faster' strategy: narrow the search space first, retrieve only what matters, then verify against authoritative sources. Use when a fan wants a World Cup match prediction, predicted score, or who-will-win call; wants a player's profile, bio, form, or stats; wants a full World Cup squad or national-team lineup table; wants to size up two teams before a match; or wants head-to-head and past World Cup context. Trigger on: World Cup prediction, predict the score, who will win, match prediction, predicted scoreline, World Cup, World Cup squad, national team lineup, pre-match analysis, matchup, player form, footballer stats, player profile, head-to-head, or scout a team.
- installations
- 1
- GitHub Stars
- 43
- Mis à jour
- 25 août
temporaliotemporal-cloud
Fix Temporal Cloud connection, auth, and config problems. Use when users hit login failures, can't connect to Cloud, get x509/TLS errors, have namespace or endpoint mismatches, paste broken SDK connection snippets, are confused about which endpoint to use, see "no pollers" or RESOURCEEXHAUSTED, struggle with PrivateLink/PSC, or need help setting up a new namespace. Also use for HA namespace failover and DNS issues. Not for worker performance tuning or scaling.
- installations
- 1
- GitHub Stars
- 5
- Mis à jour
- 27 mars
arpitbbhayaniape-commit
Defines how to write and format git commit messages. Use this skill whenever the user asks you to write, draft, suggest, or format a git commit message, summarize changes into a commit, or help stage and describe code changes. Trigger even for casual requests like "write me a commit for this" or "what should my commit say".
- installations
- 1
- GitHub Stars
- 36
- Mis à jour
- 7 sept.
arpitbbhayaniape-cut-fluff
A surgical editor that strips fluff -- hedging, throat-clearing, redundancy, padding, filler -- and drives writing down to the bare minimum word count needed to convey the concept. Use whenever the user says "cut the fluff", "trim/tighten this", "make this crisp", "remove filler/redundancy", "edit this down", or shares text, a file, a blog post, or a URL and asks to cut the fluff. Accepts a file path, pasted content, or URL; outputs the tightened version.
- installations
- 1
- GitHub Stars
- 36
- Mis à jour
- 7 sept.
arpitbbhayaniape-help-me-understand
Digests dense content -- a post, paper, doc, or thread -- into a TLDR that keeps the numbers and caveats, a so-what naming why it matters, the key points, and an analogy with its breaking point. Trigger on "ape understand", "tldr this", "help me understand this", "give me an analogy", or when the user shares a post, paper, doc, or thread and asks to digest or summarize it. Do not trigger for plain questions that want a direct answer, not a digest.
- installations
- 1
- GitHub Stars
- 36
- Mis à jour
- 7 sept.
arpitbbhayaniape-plan-project
Splits a product + engineering spec into phases, each a working vertical slice with its own agent-ready design doc. Use for "ape plan project", "plan this project", "phase this spec", or "split this into milestones for an agent to build".
- installations
- 1
- GitHub Stars
- 36
- Mis à jour
- 7 sept.
arpitbbhayaniape-poke-holes
Adversarial review of design docs, specs, plans, blog posts, and technical writeups. Finds failure modes, unstated assumptions, scale cliffs, and gaps in understanding -- the questions a reader is left holding, the steps that were hand-waved, the claims that were never earned. No praise, no solutions, only holes. Trigger on "ape poke holes", "poke holes in this", "what could go wrong", "what is missing here", "red-team this", or any request for adversarial review of a design or an explanation.
- installations
- 1
- GitHub Stars
- 36
- Mis à jour
- 7 sept.
arpitbbhayaniape-style-markdown
Apply consistent, professional Markdown formatting rules whenever producing or reformatting Markdown output. Use this skill when generating any Markdown document, when the user asks to reformat or clean up existing Markdown, when producing README files, technical docs, notes, or any other content that will be rendered as Markdown. Trigger even when the request seems simple -- any Markdown output should follow these rules. Do not use this skill for non-Markdown outputs such as plain text, HTML, or code-only responses.
- installations
- 1
- GitHub Stars
- 36
- Mis à jour
- 7 sept.
arpitbbhayaniape-teach
Masterclass teacher that takes any concept, note, URL, paper, or write-up, expands on it if needed, and teaches it through and through, step by step. Uses real-world and engineering mental models, selective and intuitive analogies with breaking points only where needed, visual ASCII diagrams, minimal code snippets, in-between check questions, web research when required, and prompts to up the ante and go deeper until the user explicitly signals they are done. Trigger on "ape teach", "teach me", "masterclass on this", "explain this step by step", or when the user provides a concept, note, paper, or link and asks to learn or be taught it thoroughly.
- installations
- 1
- GitHub Stars
- 36
- Mis à jour
- 7 sept.
a-dithya-bagent-native-cli
Design and improve CLI, scripts, Make targets, and tool interfaces for AI coding agents. Use when a repository exposes repetitive shell workflows, noisy command output, fragile multi-step operations, or tooling that could be made more deterministic, discoverable, structured, and token-efficient.
- installations
- 1
- GitHub Stars
- 21
- Mis à jour
- 4 sept.
andrew1326blender-3d-modeling
- Create 3D models procedurally with Blender Python. Use when the user wants to generate meshes from code, build geometry with bmesh, apply modifiers, create parametric shapes, procedural landscapes, grids, curves, or any programmatic 3D modeling in Blender.
- installations
- 1
- GitHub Stars
- 20
- Mis à jour
- 30 mai
texasinstrumentsc2000-idea
Step-by-step workflows for C2000 code migration tasks. Supports F28x to F28x and F28x to F29x device migration (F29x not yet implemented), bitfield-to-driverlib conversion, and SysConfig ePWM-to-MCPWM peripheral migration — migrate, port, or consolidate an EPWM-based .syscfg project onto a device's MCPWM peripheral, including checking whether several EPWM instances can share one MCPWM instance and reconciling the sync chain / time-base before migrating. Uses the IDEA MCP server as the primary tool, with CCS Project MCP, CCS SysConfig MCP, and TI ASM MCP as supporting dependencies.
- installations
- 1
- GitHub Stars
- 20
- Mis à jour
- 5 sept.
huytdcreate-wiki
Deep-investigate a codebase and generate a single-page project wiki at .docs/index.html. Use this skill whenever the user asks to "create a wiki", "generate docs", "document this project", "explain this codebase", "make a project wiki", or wants a comprehensive HTML overview of a repository. Also trigger when the user says /create-wiki. Even if the user just says "wiki" in the context of documentation, use this skill.
- installations
- 1
- GitHub Stars
- 19
- Mis à jour
- 2 avr.
huytdwalkthrough
Walk through git changes step by step in a multi-turn conversational way. Use this skill whenever the user says /walkthrough, or asks to "walk me through the changes", "explain this diff", "walk through this PR", "explain what changed in this branch", or wants to understand code changes one file at a time. Also trigger when a user shows a git diff and wants a guided explanation.
- installations
- 1
- GitHub Stars
- 19
- Mis à jour
- 2 avr.
memorysaveraep-dispatch
- Picks one ready story and hands it to /aep-design or /aep-launch. Use for "what's next" or "dispatch"; running continuously is /aep-autopilot.
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.
memorysaveraep-envision
- Validates and frames a product opportunity into the Context Document downstream agents read. Use to start or revisit an idea, or for "what should we build".
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.
memorysaveraep-executor
- Spawns and steers workspace agents across Claude Code and Codex backends. Use for backend choice, launch mode, or host detection; other skills call it.
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.
memorysaveraep-launch
- Creates a designed feature's worktree and spawns its implementation agent, plus an optional evaluator. Use after /aep-design or for "launch workspace".
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.
memorysaveraep-map
- Decomposes a product into a system map, layered story graph, and agent topology. Use after /aep-envision, or for "break this down" and "plan the stories".
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.
memorysaveraep-model
- Builds a human-reviewed OOUX object map and noun-first UI blueprint. Use after /aep-map, before UI stories, or for "object model" and "OOUX".
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.
memorysaveraep-onboard
- Installs, verifies, and explains AEP itself: environment, tools, plugin config. Use for first contact with AEP; creating a project is /aep-scaffold.
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.
memorysaveraep-scaffold
- Creates a new AEP project or repairs an existing project's agentic infrastructure and skills layout. Installing AEP itself is /aep-onboard.
- installations
- 1
- GitHub Stars
- 18
- Mis à jour
- 5 sept.