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
- 15 606
- dépôts
- 2526
- dernière synchronisation
- 12 oct. 2026
suzhengk2f-academic-paper
Turn research questions, data, and literature into submission-ready academic manuscripts with venue-aligned structure, claim–evidence flow, and reader-scannable hierarchy. Use when the user asks for an academic paper, journal article, conference paper, thesis chapter, IMRaD manuscript, abstract, or manuscript outline from notes or a draft. Create academic papers with AI-native design and the highest aesthetic standards, powered by the K2F format and engine. Purpose-built for AI agents, K2F lets
- installations
- 9
- GitHub Stars
- 2
- Mis à jour
- 1 oct.
rohitg00commit-context
Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00commit-history
List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00forget
Delete specific observations from agentmemory after showing them and getting explicit confirmation. Use when the user says "forget this", "delete memory", "remove that note", or wants to scrub specific data for privacy.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00lesson
Save a correction or hard-won rule as a confidence-weighted lesson that resurfaces before similar work. Use when the user corrects your approach, says "learn this", "always" or "never do X", or you notice yourself repeating a past mistake.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00memory-discipline
The session loop that makes agentmemory pay off, recall before starting work, save at decision points, learn from corrections. Use when starting a nontrivial task, after settling a decision or debugging a gotcha, or whenever deciding if something belongs in memory.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00recall
Search agentmemory for past observations, sessions, and learnings about a topic using hybrid BM25 plus vector plus graph search. Use when the user says "recall", "what did we do about", "did we ever", "have we seen", or needs context from past sessions.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00recap
Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00remember
Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags. Use when the user says "remember this", "save this", "note that", "don't forget", or wants to preserve knowledge for future sessions.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
rohitg00session-history
Show what happened in recent past sessions on this project as a clean timeline. Use when the user asks "what did we do last time", "session history", "past sessions", or wants an overview of previous work.
- installations
- 9
- GitHub Stars
- 29,2 k
- Mis à jour
- 5 oct.
samberbusiness-event-formats
Choose which company-run event shape to run - invite-only dinner, executive summit, single-city user conference, multi-city roadshow, or a floor-primary trade-show event - plus how its program is sourced and what shape its floor takes. Use whenever a company weighs a user conference against a roadshow or a summit, asks what kind of event to put on for developers, customers or partners, or asks whether to run its own floor or exhibit on someone else's, even if they only say "we want to do an even
- installations
- 9
- GitHub Stars
- 2
- Mis à jour
- 28 sept.
samberevent-positioning
Define a technical event's positioning - what it stands for, against which alternatives, for which audience identity. Covers the governance axis (community-run, foundation, media-run, vendor-owned), competitive-alternative mapping, best-fit attendee and sponsor segments, market-category strategy (head-to-head, subcategory, new category and its education tax), the positioning statement, contrast-not-attack anti-positioning, and the rebrand gate. Use whenever asked to position a conference, meetup
- installations
- 9
- GitHub Stars
- 2
- Mis à jour
- 28 sept.
samberevent-risk-management
Build and maintain the standing risk register for a technical event - risks named by category, scored on a likelihood x impact matrix adapted to a dated one-shot deliverable, split into prevention, contingency or insurance, the insurance stack including the communicable-disease buy-back, internal go/no-go decision dates set against the venue's escalating cancellation-fee curve, and the on-site emergency plan. Use whenever the user mentions event insurance, cancelling or postponing an event, a go
- installations
- 9
- GitHub Stars
- 2
- Mis à jour
- 28 sept.
verceltechnical-writing
Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current source, tests, CLI help, public releases, and repository conventions.
- installations
- 9
- GitHub Stars
- 5,4 k
- Mis à jour
- 2 oct.
tencentweread-skills
微信读书助手 — 搜索书籍、管理书架、查看笔记划线、浏览书评、阅读统计、发现推荐好书
- installations
- 9
- GitHub Stars
- 248
- Mis à jour
- 1 juil.
rstackjsrslib-best-practices
Configure, review, or troubleshoot Rslib library builds, output formats, declarations, dependency handling, and integrations.
- installations
- 9
- GitHub Stars
- 93
- Mis à jour
- 15 sept.
agents365-aidrawio-skill
Create, edit, synchronize, inspect, test, and publish editable draw.io diagrams. Use when the user explicitly requests draw.io/diagrams.net, needs a polished architecture, ERD, UML, sequence, C4, SysML, BPMN, network, swimlane, ML, or infrastructure diagram, wants code/IaC/SQL/OpenAPI/AsyncAPI/Protobuf converted into a diagram, or wants an existing diagram queried, reviewed, diffed, restyled, kept in sync, or made interactive. Prefer Mermaid/PlantUML elsewhere when the requested artifact is diag
- installations
- 9
- GitHub Stars
- 48
- Mis à jour
- 11 sept.
stripelink-cli
Install and authenticate Link CLI for agent payments, financial insights, or both. Use when a user is setting up Link CLI for the first time, asks to connect or log in to Link, or needs to configure Link access before using payment or financial-data features.
- installations
- 9
- GitHub Stars
- 779
- Mis à jour
- 13 sept.
paidaxingyo666manta-cli
- Use the public manta CLI to operate Manta-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and the browser embedded inside the Manta app. Use when the user says "$manta-cli", "use manta cli", "Manta worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Manta terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Manta browser", "manta artif
- installations
- 9
- GitHub Stars
- 8
- Mis à jour
- 8 sept.
railwayappuse-railway
Operate Railway infrastructure: sign up for or sign in to a Railway account, create projects, provision services, databases, and buckets, deploy code, configure infrastructure as code, environments and variables, manage domains, trace requests with OpenTelemetry, troubleshoot failures, check status and metrics, manage feature flags, database recovery and HA, cloud agents, usage limits, and Railway agent tooling. Use this skill whenever the user mentions Railway, feature flags, flag rollout, targ
- installations
- 8
- GitHub Stars
- 326
- Mis à jour
- 9 oct.
nick-velsautopilot
Builds an app, site, bot, or feature end-to-end from a dictated idea — requirements, briefing, spec, tickets, subagents, review, acceptance — with a live dashboard, for users who expect a finished result without reviewing specs or code. Starts only on /autopilot; a bare /autopilot resumes an interrupted run.
- installations
- 8
- GitHub Stars
- 451
- Mis à jour
- 10 oct.
wshobsonstride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
- installations
- 8
- GitHub Stars
- 40,4 k
- Mis à jour
- 5 oct.
bmad-code-orgbmad-build-auto
One iteration of an unattended development loop. Use when invoked by name
- installations
- 8
- GitHub Stars
- 54 k
- Mis à jour
- 12 oct.
bmad-code-orgbmad
Answers BMad questions and recommends the next skill from what is installed. Use when the user asks bmad for help, what to do next or where to start; to set up, update, repair, doctor, migrate or check the status of the installation, or add modules; or to see or change the active initiative.
- installations
- 8
- GitHub Stars
- 54 k
- Mis à jour
- 12 oct.