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
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
dependency-management
Cross-language dependency management — lockfiles, version pinning, automated updates, security, and licenses. Use when setting up or reviewing lockfile strategy, configuring automated dependency updates, auditing dependencies for security or license issues, handling monorepo dependencies, or deciding whether to vendor.
dependency-audit
Audit project dependencies for vulnerabilities and outdated packages. Use when checking the security posture of dependencies, planning updates, or running a pre-release dependency review.
decision-record
Record decisions with rationale, alternatives, and consequences — the ADR pattern as a primitive. Use when a consequential choice is made — architecture, tooling, process, scope, trade-off. Capture WHY, not just WHAT.
debugging
Systematic debugging — reproduce, read the error, isolate, hypothesize, fix, verify, document. Use when tracking down a bug, unexpected behavior, or test failure — including phrases like "this doesn't work", "why is this failing", or "help me debug".
database-modeling
Data modeling — ER diagrams, normalization, denormalization trade-offs, relationship patterns, and schema evolution. Use when designing a new schema, critiquing an existing data model, choosing between normalized and denormalized designs, or modeling complex relationships like polymorphism, hierarchy, or temporal data.
database-migration
Schema migration workflows — zero-downtime expand/contract, batched backfills, and rollback strategies. Use when planning a schema migration, reviewing migration scripts, troubleshooting a slow or failed migration, or rolling back a deployed change.
data-visualization
Chart selection, color accessibility, annotation, and dashboard design. Use when creating charts, designing dashboards, choosing visualization types, improving chart readability, or reviewing data presentations for clarity.
data-storytelling
Translates data analysis into clear narratives and recommendations that non-technical audiences can act on. Use when presenting analysis results, writing data-driven reports, creating executive summaries from dashboards, or when data needs to be communicated as a decision rather than as numbers.
data-science
Data analysis workflow from import through modeling and communication. Use when analyzing a dataset, exploring data, building a statistical model, selecting features, or communicating findings to stakeholders.
data-quality
Data quality framework — completeness, accuracy, consistency, validation, and contracts. Use when implementing data validation, setting up quality checks for a pipeline, defining data contracts between teams, or investigating data anomalies.
data-pipeline
Data pipeline patterns — ETL/ELT, batch vs streaming, idempotency, orchestration. Use when designing a data pipeline, choosing between batch and streaming, implementing ingestion or transformation, setting up orchestration, or debugging pipeline failures.
cross-reference-management
Conventions and helpers for lightweight relationships between entities expressed as frontmatter references (not first-class Binding entities). Use when linking two entities with a simple, unscoped, untemporal relationship — 'this work item blocks that one', 'this decision relates to that work item'. For scoped/temporal relationships, use binding-management instead.
context-grooming
Periodically review and prune the project context — archive completed work, summarize stale entries, propose disabling unused skills. Keeps the context lean so agents load less per session. Run on a regular cadence (weekly or monthly) — or when the user notices session context bloat. Always proposes changes for human approval; never moves or deletes files silently.
container-orchestration
Docker Compose patterns for multi-service apps — health checks, networking, volumes, dependencies. Use when writing or editing docker-compose files, designing multi-service architectures, debugging container networking, or managing volumes and service dependencies.
constraint-management
Manage Constraint entities — rules and limits the project must respect (budget, latency SLO, team size, compliance). Use when recording a rule, limit, or boundary that affects decisions — budget ceiling, latency SLO, regulatory requirement, team bandwidth.
concurrency-patterns
Concurrency and parallelism patterns — async/await, threads, actors, channels, deadlock prevention. Use when choosing a concurrency model, designing concurrent or parallel pipelines, debugging deadlocks or race conditions, or reasoning about shared state and backpressure.
code-review
Structured code review with a checklist covering correctness, clarity, tests, security, performance, and style. Use when reviewing a PR, diff, or set of code changes before merging — including phrases like "review this", "check my changes", or "is this ready to merge".
code-generation
Code generation patterns — template engines, AST manipulation, scaffolding, build-step generation. Use when building or extending a code generator, choosing a template engine, deciding whether to generate code or write an abstraction, adding codegen as a build step, or implementing macro/AST transformations.