跳到正文
cccskills
免费在 GitHub 公开

supergraph

Meta-orchestrator — dispatches to the right skill for the task. Use before any non-trivial work.

中文简介正在准备中。当前显示原文说明。

datit309/supergraph
查看安装方法

包含的文件（153）

  • SKILL.md2.5 KB
  • .claude-plugin/marketplace.json12.4 KB
  • .claude-plugin/plugin.json1.3 KB
  • .codex-plugin/.mcp.json245 B
  • .codex-plugin/plugin.json1.2 KB
  • .dsh-plugin/cordis.patch.yml12.7 KB
  • .dsh-plugin/plugin.json338 B
  • .dsh-plugin/README.md1.4 KB
  • .githooks/pre-commit1.7 KB
  • .github/dependabot.yml118 B
  • .github/ISSUE_TEMPLATE/1.bug_report.yml1.5 KB
  • .github/ISSUE_TEMPLATE/2.feature_request.yml926 B
  • .github/ISSUE_TEMPLATE/3.skill_submission.yml1.3 KB
  • .github/ISSUE_TEMPLATE/config.yml212 B
  • .github/pull_request_template.md418 B
  • .github/workflows/graph-review.yml4.7 KB
  • .github/workflows/release.yml700 B
  • .gitignore.supergraph41 B
  • .mcp.json344 B
  • .opencode-plugin/LICENSE1.0 KB
  • .opencode-plugin/opencode.json3.2 KB
  • .opencode-plugin/plugin.ts14.0 KB
  • .opencode-plugin/SECURITY.md1.1 KB
  • AGENTS.md12.4 KB
  • agents/code-reviewer.md4.9 KB
  • agents/diagnostician.md3.3 KB
  • agents/executor.md7.4 KB
  • agents/plan-reviewer.md3.1 KB
  • agents/plan-writer.md2.8 KB
  • agents/qa-tester.md3.9 KB
  • agents/security-auditor.md4.1 KB
  • bin/detect-project.sh3.7 KB
  • bin/sg-browser-mcp.js1.7 KB
  • bin/sg-team-mcp.js143 B
  • bin/sg-team-status.js2.4 KB
  • bin/sg-team-ui.js6.1 KB
  • CHANGELOG.md21.0 KB
  • CLAUDE.md12.4 KB
  • client.js7.7 KB
  • cordis.patch.yml12.7 KB
  • docs/GITHUB-LABELS.md5.3 KB
  • docs/TEAM-SETUP.md6.9 KB
  • extensions/chrome-relay/background.js6.7 KB
  • extensions/chrome-relay/bin/supergraph-relay295 B
  • extensions/chrome-relay/manifest.json518 B
  • extensions/chrome-relay/popup.html1.6 KB
  • extensions/chrome-relay/popup.js709 B
  • extensions/chrome-relay/README.md1.5 KB
  • extensions/chrome-relay/relay-server.js9.2 KB
  • extensions/chrome-relay/scripts/install-extension.sh4.1 KB
  • hooks.json1.2 KB
  • hooks/bash-guard1.4 KB
  • hooks/hooks.json1.9 KB
  • hooks/post-tool-use196 B
  • hooks/post-tool-use-bash1.4 KB
  • hooks/pre-compact1.0 KB
  • hooks/pre-invocation8.3 KB
  • hooks/pre-tool-use4.1 KB
  • hooks/run-hook.cmd1.4 KB
  • hooks/session-start9.0 KB
  • hooks/stop1.8 KB
  • hooks/user-prompt-submit5.8 KB
  • index.js6.2 KB
  • install.sh10.8 KB
  • LICENSE1.0 KB
  • mcp_config.json339 B
  • OPENCODE.md2.5 KB
  • package.json1.5 KB
  • plugin.json1.2 KB
  • references/codebase-memory-contract.md3.3 KB
  • scripts/normalize-codebase-memory-json.py4.0 KB
  • SECURITY.md1.4 KB
  • settings.json3.6 KB
  • skills/analyze/SKILL.md4.8 KB
  • skills/architecture/SKILL.md3.0 KB
  • skills/browser-agent/scripts/init-qa.sh4.1 KB
  • skills/browser-agent/SKILL.md6.7 KB
  • skills/browser-agent/templates/bug-report-template.md1.9 KB
  • skills/browser-agent/templates/test-matrix-api-template.md3.1 KB
  • skills/browser-agent/templates/test-matrix-fullstack-template.md2.8 KB
  • skills/browser-agent/templates/test-matrix-template.md2.7 KB
  • skills/caveman/SKILL.md1.4 KB
  • skills/database-migrations/REFERENCE.md7.4 KB
  • skills/database-migrations/SKILL.md5.0 KB
  • skills/design-taste-frontend/SKILL.md85.2 KB
  • skills/diagnose/SKILL.md4.0 KB
  • skills/execute/scripts/review-package1.9 KB
  • skills/execute/scripts/sdd-workspace927 B
  • skills/execute/scripts/task-brief1.9 KB
  • skills/execute/SKILL.md7.6 KB
  • skills/explore/SKILL.md2.8 KB
  • skills/fix/SKILL.md3.5 KB
  • skills/flutter-dart-code-review/CHECKLIST.md11.1 KB
  • skills/flutter-dart-code-review/SKILL.md2.1 KB
  • skills/flutter-screenshots/scripts/capture-store-shots.sh4.9 KB
  • skills/flutter-screenshots/SKILL.md8.1 KB
  • skills/flutter-ui/SKILL.md6.1 KB
  • skills/frontend-design/SKILL.md3.1 KB
  • skills/gpt-taste/SKILL.md7.7 KB
  • skills/handoff/SKILL.md2.4 KB
  • skills/image-to-code/SKILL.md35.6 KB
  • skills/integration/SKILL.md3.6 KB
  • skills/plan/SKILL.md5.8 KB
  • skills/prd/SKILL.md2.9 KB
  • skills/prototype/SKILL.md3.8 KB
  • skills/redesign-existing-projects/SKILL.md14.7 KB
  • skills/review/SKILL.md6.5 KB
  • skills/scan/SKILL.md4.4 KB
  • skills/sdd/SKILL.md5.5 KB
  • skills/serena/SKILL.md6.2 KB
  • skills/tdd/SKILL.md4.8 KB
  • skills/tdd/writing-good-tests.md1.4 KB
  • skills/threejs-animation/SKILL.md12.3 KB
  • skills/threejs-fundamentals/SKILL.md11.3 KB
  • skills/threejs-geometry/SKILL.md13.5 KB
  • skills/threejs-interaction/SKILL.md15.9 KB
  • skills/threejs-lighting/SKILL.md11.7 KB
  • skills/threejs-loaders/SKILL.md13.7 KB
  • skills/threejs-materials/SKILL.md13.1 KB
  • skills/threejs-postprocessing/SKILL.md14.1 KB
  • skills/threejs-shaders/SKILL.md13.7 KB
  • skills/threejs-textures/SKILL.md13.3 KB
  • skills/triage/SKILL.md3.4 KB
  • skills/verify/SKILL.md4.3 KB
  • skills/vibesec/SKILL.md24.9 KB
  • skills/zoom-out/SKILL.md1.8 KB
  • SOUL.md3.4 KB
  • team/engine.js5.9 KB
  • team/mcp-server.js18.3 KB
  • team/ui-html.js42.3 KB
  • team/worktree.js12.0 KB
  • tests/fixtures/codebase-memory/app_test.sh263 B
  • tests/fixtures/codebase-memory/app.sh255 B
  • tests/test-bootstrap-installer-powershell.sh4.7 KB
  • tests/test-bootstrap-installer.sh3.7 KB
  • tests/test-codebase-memory-migration.sh17.9 KB
  • tests/test-documentation-consistency.sh2.6 KB
  • tests/test-dsh-installer.sh2.3 KB
  • tests/test-dsh-plugin.mjs2.6 KB
  • tests/test-hook-contracts.sh11.2 KB
  • tests/test-run-hook-cmd.sh1.5 KB
  • tests/test-sg-browser-mcp.mjs1.5 KB
  • tests/test-taste-skill-integration.sh2.3 KB
  • tests/test-team-e2e-simulation.mjs8.0 KB
  • tests/test-team-engine.mjs11.6 KB
  • tests/test-team-mcp.mjs6.9 KB
  • tests/test-team-session-isolation.mjs2.3 KB
  • tests/test-threejs-skills-integration.sh3.9 KB
  • tests/test-ui-html-theme.mjs1.5 KB
  • tests/test-upstream-content-contracts.sh1.4 KB
  • tests/test-upstream-superpowers.sh6.1 KB
  • tests/test-user-prompt-submit-hook.sh821 B
  • themes/theme.json137 B

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

supergraph

Graph evidence uses codebase-memory-mcp scoped by CBM_PROJECT. Orientation loads get_architecture aspects overview, layers, boundaries, clusters, and hotspots, plus validated hubs, bridges, and test-gaps recipes. If optional graph evidence is unavailable, label it unavailable and use Serena or filesystem evidence.

Dispatch to the right skill. 1% rule: if it might apply, invoke it.

Priority

  1. User CLAUDE.md / AGENTS.md (highest)
  2. This skill set
  3. Default system behavior

Dispatch Table

User intentSkill to invoke
"start", "begin", unclear scope/supergraph:analyze
"plan", "lên kế hoạch", explicit plan request/supergraph:plan
"implement", "build", "execute" (plan saved)/supergraph:execute
"fix bug", "debug", "why failing"/supergraph:fix
"test", "TDD", "add tests"/supergraph:tdd
"refactor", "clean up", "reorganize"/supergraph:plan (then execute)
integration/e2e tests, after unit green/supergraph:integration
"done?", "verify", before commit/PR/supergraph:verify
"review", "merge", "PR", before merge/supergraph:review
Need project context/supergraph:scan

Adaptive Gate

  • < 20 lines, ≤2 files, no hub/bridge, complexity <10 → use /supergraph:tdd directly
  • ≤5 files, clear requirement, no cross-boundary → /supergraph:plan with lightweight tasks
  • >5 files, ambiguous, hub/bridge, cross-boundary → /supergraph:analyze first, then plan

User Instructions

"Add X" or "Fix Y" is the WHAT. Skills determine HOW. Never skip a skill because the task "feels simple."

Red Flags (STOP if you catch yourself):

  • "I'll just do it quickly" → pick a skill, follow it
  • "I already know what to do" → skills evolve, load current one
  • "This is too simple for a skill" → simple becomes complex fast

Integration

All skills depend on /supergraph:scan being loaded first in the session.

Subagent Guard

When dispatching subagents (executor, code-reviewer, plan-writer, plan-reviewer, qa-tester, security-auditor, diagnostician):

  • Subagents get self-contained prompts — never session history
  • Subagents do NOT trigger skills independently — this is the orchestrator's job
  • Subagents report results back; orchestrator decides next step (fix, verify, review)

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护，适用 Google 的隐私权政策和服务条款。

同一仓库的技能

analyze

免费

Risk analysis and approach selection before planning. Use when requirements are ambiguous, approaches vary, or work touches hub/bridge nodes. Skip for typo fixes.

中文简介正在准备中。当前显示原文说明。

datit309/supergraph212026年10月18日 更新

architecture

免费

Proactive architecture review — explore codebase structure, generate a self-contained HTML report with Mermaid diagrams and candidate improvements, then grill the findings. Use when planning a large refactor, onboarding to an unfamiliar codebase, or before a major architectural change.

中文简介正在准备中。当前显示原文说明。

datit309/supergraph212026年10月18日 更新

browser-agent

免费

Autonomous human-like browser control and professional QA/QC testing. Powered by agent-browser (Rust native CDP, zero Playwright) with ISTQB test matrix generation, automated testcase execution, console/network error tracing, and defect reporting.

中文简介正在准备中。当前显示原文说明。

datit309/supergraph212026年10月18日 更新

caveman

免费

Persistent token-compression mode (~75% reduction) — now always-on by default. Strips filler while keeping code exact.

中文简介正在准备中。当前显示原文说明。

datit309/supergraph212026年10月18日 更新

database-migrations

免费

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).

中文简介正在准备中。当前显示原文说明。

datit309/supergraph212026年10月18日 更新

design-taste-frontend

免费

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

中文简介正在准备中。当前显示原文说明。

datit309/supergraph212026年10月18日 更新

查看 datit309 的全部技能

报告此技能的问题