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 192262
findings-crosscheck
Adversarially verify REPORTED findings against the real code before any of them becomes a task. Use when an audit, a security scan, another agent's relay, a "N fields are missing / X is broken" list, a bug report, or even your own claim from a past session asserts something is true about the system — triage the falsifiable claims, fan out one verifier per claim (file:line CONFIRMED/REFUTED/RECLASSIFIED), adversarially verify the consequential ones in BOTH directions, reproduce alarming numbers, and only let survivors become work.
etl-guidelines
DEPRECADA — ETL legado (apps.dat_ingest) REMOVIDO. Import atual = import_export_contract + endpoints DRF. Não codar contra apps.dat_ingest.
domain-modeling
Construir e afiar o modelo de domínio do Aprender Sistema — glossário de termos e ADRs — durante uma conversa de design. Use ao discutir terminologia do negócio, editar o glossário, ou registrar/editar um ADR. Para só consultar regras RF/RD/PA/CP, use `aprender-domain`.
django-security
Review and harden security in the AS v2 Django/DRF backend. Use when auditing RBAC access control, reviewing auth/OAuth/import code for vulnerabilities, or hardening an endpoint before deploy. Covers OWASP Top 10, IDOR, CSV injection, row-level scoping, and secrets — mapped to AS v2's session auth, capability RBAC, and Google OAuth.
django-patterns
Django 5.2 + DRF implementation patterns specific to Aprender Sistema v2 (modular apps/core layout, HasPerm RBAC, read/write serializers, service layer, owner-scoped querysets). Use when writing a model, serializer, view/viewset, service, permission, or test in the v2 backend.
deprecation-and-migration
Deprecate and remove old APIs, models, fields, or dependencies in AS v2 without breaking consumers. Use when replacing a lib/service/model with a new one, consolidating duplicates, or deleting dead code — follow the ordered procedure and its completion gates before removing anything.
debugging-and-error-recovery
Debug AS v2 (Django + React + Celery + Docker) by root cause, then guard against recurrence. Use when a test fails, a build breaks, a runtime error fires, or behavior doesn't match expectations.
create-plan
Create detailed implementation plans through interactive research. Use when the user asks to plan a feature/epic/refactor before implementing, or invokes /create-plan with a ticket/spec.
create-handoff
Write a handoff document that compacts the current session's context for another agent. Use when ending a session with unfinished work, before /clear, or when context is full.
continuity-ledger
Preserve session state across /clear in long-running sessions. Use before running /clear, when context usage passes ~70%, or for multi-day implementations and large refactors you pick up and put down. Unlike handoffs (cross-session), a ledger preserves state within one session.
ci-github-actions
CI/CD do AS v2 (GitHub Actions). Use ao editar workflows, destravar checks [required], preparar PR para o staging gate, debugar CI vermelha, ou mexer no deploy. Cobre os gates obrigatorios, os 3 marcadores do staging-gate, pytest --no-migrations e os flakes recorrentes.
brainstorming
Explore the solution space before committing to an approach. Use when the user has a rough idea, when multiple valid approaches exist, or in early-stage feature design before coding.
aprender-domain
Business-rules reference for Aprender Sistema v2 — RF (functional requirements), RD (availability rules), PA (approval policy), CP (immutable clauses), and core domain models. Use when implementing a feature, validating a requirement, or writing a compliance test against any RF/RD/PA/CP rule.
writing-standards
Apply AS v2 technical-writing standards (clarity, brevity, active voice, Python/Django conventions). Use when writing a README, a docstring (PEP 257), a commit message, a PR description, an error message, or any technical doc.
verification-gate
Verify before claiming success. Use when about to say something works/is done, after implementing a feature, after a bugfix, or before pushing — run the proof command and confirm output first.
test-driven-development
Write the failing test before the implementation in AS v2 (pytest + Django/DRF). Use when implementing a feature or fixing a bug, before any production code is written.
subagent-development
Orquestra subagents no AS v2 — decompõe a tarefa em domínios independentes, paraleliza e revisa em 2 estágios. Use ao delegar exploração, implementação ou validação cross-arquivo para acelerar o trabalho e poupar o contexto principal.
security-scan
Automated security scanning for AS v2. Use before commits or when reviewing changes for vulnerabilities. Runs dependency audit (pip-audit, npm audit), secret detection (grep patterns), and code pattern scanning (SQL injection, XSS, eval, pickle, hardcoded secrets). Integrates with project hooks system.