GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills，按职业与使用场景整理，复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196921
cost-tracking
Track and report Claude Code token usage, spending, and budgets from a local cost-tracking database. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by project, tool, session, or date.
bmad-create-prd
Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD"
cost-aware-llm-pipeline
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
bmad-create-epics-and-stories
Break requirements into epics and user stories. Use when the user says "create the epics and stories list"
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
bmad-create-architecture
Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design"
bmad-correct-course
Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change"
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
bmad-code-review
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"
consensus-tooluniverse-research
Use when downloading or systematically harvesting research from Consensus.app — extract each shared search browser-free from the page __NEXT_DATA__ payload, resolve every cited paper to a DOI and open-access PDF with ToolUniverse (Crossref, OpenAlex, Unpaywall, EuropePMC), organize by topic with a DOI-linked bibliography, capture the Consensus Meter graphs, and verify headline claims against primary sources. Bundles paste-ready AI-scope and user-scope instructions for mechanistic neuropharmacology and harm-reduction research.
bmad-cis-storytelling
Craft compelling narratives using story frameworks. Use when the user says "help me with storytelling" or "I want to create a narrative through storytelling"
bmad-cis-problem-solving
Apply systematic problem-solving methodologies to complex challenges. Use when the user says "guide me through structured problem solving" or "I want to crack this challenge with guided problem solving techniques"
competitive-programming-solver
Solves algorithmic and competitive programming problems by producing fast, correct solutions in C, C++, and Python. Use this skill whenever the user mentions a problem from Codeforces, AtCoder, LeetCode, Infoarena, pbinfo, Kattis, SPOJ, USACO, ICPC, IOI, or any online judge / olympiad / contest. Also use for any problem statement with input/output specs, time/memory limits, or wording like "given N elements... output the answer", "TLE", "AC", "passes the time limit", "1-indexed array", or "competitive programming". Trigger even if the user only shares an input file, a buggy submission, or asks "why is my solution slow / wrong / failing test X". Default to producing all three languages unless the user specifies one.
bmad-cis-innovation-strategy
Identify disruption opportunities and architect business model innovation. Use when the user says "lets create an innovation strategy" or "I want to find disruption opportunities"
compchem-validators
Use when a docking / MD / free-energy campaign needs an OUTPUT quality gate - post-dock pose validity (PoseBusters), a cheap-tier prefilter before the token-gated tiers (Uni-Dock GPU-Vina before Glide, Boltz-2 affinity before FEP+/QDX credits), or a "docking done / ΔG=… / MD converged" claim that should be backed by a validity artifact before it is treated as done. compchem-preflight guards INPUT; this skill guards OUTPUT (a pose can score well yet be physically impossible). Also the map for the open-weights compute arm - MACE-OFF near-DFT MD, OpenFE token-free FEP twin, REINVENT 4 generative loop, PLINDER leakage-free splits, and the TxAgent/ToolUniverse grounded-reasoning pattern (Opus reasoner, not the fine-tuned model). All ride the existing schrodinger / qdx-rush / cloud-hub MCPs - scientific compute is NOT agent runtime. Do NOT use for the receptor-prep-to-dock pipeline itself (use structure-based-screening) or license-free cheminformatics (use cheminformatics-rdkit).
bmad-cis-design-thinking
Guide human-centered design processes using empathy-driven methodologies. Use when the user says "lets run design thinking" or "I want to apply design thinking"
comp-pharm-cascade
Use when ranking/prioritizing a congeneric small-molecule series against a protein target (binding-affinity SAR, hit triage, mechanism-of-action), or when scoping such a campaign. Routes the work through a cost-escalating cascade — experimental-anchor data → license-free ML (Boltz-2) breadth + pose → licensed Schrödinger physics (FEP/MM-GBSA/BPMD) for the headline ΔΔG → QM (EXESS) mechanism → figures — with consensus checks at the two gates that are catastrophic when silently wrong (pose, and the published number). NOT for a single one-off docking (use schrodinger-maestro-driver / structure-based-screening) or pure knowledge lookup (use tooluniverse).
bmad-cis-agent-storyteller
Master storyteller for compelling narratives using proven frameworks. Use when the user asks to talk to Sophia or requests the Master Storyteller.