supergraph
Meta-orchestrator — dispatches to the right skill for the task. Use before any non-trivial work.
Install
npx skills add https://github.com/datit309/supergraph/tree/master/plugins/supergraph
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install datit309-supergraph@llmmart
git clone https://github.com/datit309/supergraph.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole datit309/supergraph collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
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
- User CLAUDE.md / AGENTS.md (highest)
- This skill set
- Default system behavior
Dispatch Table
| User intent | Skill 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:tdddirectly - ≤5 files, clear requirement, no cross-boundary →
/supergraph:planwith lightweight tasks - >5 files, ambiguous, hub/bridge, cross-boundary →
/supergraph:analyzefirst, 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)
Files (supergraph)
-
.claude-plugin
-
marketplace.json 12.4 KB
Loading… -
plugin.json 1.3 KB
Loading…
-
-
.codex-plugin
-
.mcp.json 245 B
Loading… -
plugin.json 1.2 KB
Loading…
-
-
.dsh-plugin
-
cordis.patch.yml 12.7 KB
Loading… -
plugin.json 338 B
Loading… -
README.md 1.4 KB
Loading…
-
-
.githooks
-
pre-commit 1.7 KB · in bundle
-
-
.github
-
ISSUE_TEMPLATE
-
1.bug_report.yml 1.5 KB
Loading… -
2.feature_request.yml 926 B
Loading… -
3.skill_submission.yml 1.3 KB
Loading… -
config.yml 212 B
Loading…
-
-
workflows
-
graph-review.yml 4.7 KB
Loading… -
release.yml 700 B
Loading…
-
-
dependabot.yml 118 B
Loading… -
pull_request_template.md 418 B
Loading…
-
-
.opencode-plugin
-
LICENSE 1 KB · in bundle
-
opencode.json 3.2 KB
Loading… -
plugin.ts 14 KB
Loading… -
SECURITY.md 1.1 KB
Loading…
-
-
agents
-
code-reviewer.md 4.9 KB
Loading… -
diagnostician.md 3.3 KB
Loading… -
executor.md 7.4 KB
Loading… -
plan-reviewer.md 3.1 KB
Loading… -
plan-writer.md 2.8 KB
Loading… -
qa-tester.md 3.9 KB
Loading… -
security-auditor.md 4.1 KB
Loading…
-
-
bin
-
detect-project.sh 3.7 KB
Loading… -
sg-browser-mcp.js 1.7 KB
Loading… -
sg-team-mcp.js 143 B
Loading… -
sg-team-status.js 2.4 KB
Loading… -
sg-team-ui.js 6.1 KB
Loading…
-
-
docs
-
GITHUB-LABELS.md 5.3 KB
Loading… -
TEAM-SETUP.md 6.9 KB
Loading…
-
-
extensions
-
chrome-relay
-
bin
-
supergraph-relay 295 B · in bundle
-
-
scripts
-
install-extension.sh 4.1 KB
Loading…
-
-
background.js 6.7 KB
Loading… -
manifest.json 518 B
Loading… -
popup.html 1.6 KB · in bundle
-
popup.js 709 B
Loading… -
README.md 1.5 KB
Loading… -
relay-server.js 9.2 KB
Loading…
-
-
-
hooks
-
bash-guard 1.4 KB · in bundle
-
hooks.json 1.9 KB
Loading… -
post-tool-use 196 B · in bundle
-
post-tool-use-bash 1.4 KB · in bundle
-
pre-compact 1 KB · in bundle
-
pre-invocation 8.3 KB · in bundle
-
pre-tool-use 4.1 KB · in bundle
-
run-hook.cmd 1.4 KB · in bundle
-
session-start 9 KB · in bundle
-
stop 1.8 KB · in bundle
-
user-prompt-submit 5.8 KB · in bundle
-
-
references
-
codebase-memory-contract.md 3.3 KB
Loading…
-
-
scripts
-
normalize-codebase-memory-json.py 4 KB
Loading…
-
-
skills
-
analyze
-
SKILL.md 4.8 KB
Loading…
-
-
architecture
-
SKILL.md 3 KB
Loading…
-
-
browser-agent
-
scripts
-
init-qa.sh 4.1 KB
Loading…
-
-
templates
-
bug-report-template.md 1.9 KB
Loading… -
test-matrix-api-template.md 3.1 KB
Loading… -
test-matrix-fullstack-template.md 2.8 KB
Loading… -
test-matrix-template.md 2.7 KB
Loading…
-
-
SKILL.md 6.7 KB
Loading…
-
-
caveman
-
SKILL.md 1.4 KB
Loading…
-
-
database-migrations
-
REFERENCE.md 7.4 KB
Loading… -
SKILL.md 5 KB
Loading…
-
-
design-taste-frontend
-
SKILL.md 85.2 KB
Loading…
-
-
diagnose
-
SKILL.md 4 KB
Loading…
-
-
execute
-
scripts
-
review-package 1.9 KB · in bundle
-
sdd-workspace 927 B · in bundle
-
task-brief 1.9 KB · in bundle
-
-
SKILL.md 7.6 KB
Loading…
-
-
explore
-
SKILL.md 2.8 KB
Loading…
-
-
fix
-
SKILL.md 3.5 KB
Loading…
-
-
flutter-dart-code-review
-
CHECKLIST.md 11.1 KB
Loading… -
SKILL.md 2.1 KB
Loading…
-
-
flutter-screenshots
-
scripts
-
capture-store-shots.sh 4.9 KB
Loading…
-
-
SKILL.md 8.1 KB
Loading…
-
-
flutter-ui
-
SKILL.md 6.1 KB
Loading…
-
-
frontend-design
-
SKILL.md 3.1 KB
Loading…
-
-
gpt-taste
-
SKILL.md 7.7 KB
Loading…
-
-
handoff
-
SKILL.md 2.4 KB
Loading…
-
-
image-to-code
-
SKILL.md 35.6 KB
Loading…
-
-
integration
-
SKILL.md 3.6 KB
Loading…
-
-
plan
-
SKILL.md 5.8 KB
Loading…
-
-
prd
-
SKILL.md 2.9 KB
Loading…
-
-
prototype
-
SKILL.md 3.8 KB
Loading…
-
-
redesign-existing-projects
-
SKILL.md 14.7 KB
Loading…
-
-
review
-
SKILL.md 6.5 KB
Loading…
-
-
scan
-
SKILL.md 4.4 KB
Loading…
-
-
sdd
-
SKILL.md 5.5 KB
Loading…
-
-
serena
-
SKILL.md 6.2 KB
Loading…
-
-
tdd
-
SKILL.md 4.8 KB
Loading… -
writing-good-tests.md 1.4 KB
Loading…
-
-
threejs-animation
-
SKILL.md 12.3 KB
Loading…
-
-
threejs-fundamentals
-
SKILL.md 11.3 KB
Loading…
-
-
threejs-geometry
-
SKILL.md 13.5 KB
Loading…
-
-
threejs-interaction
-
SKILL.md 15.9 KB
Loading…
-
-
threejs-lighting
-
SKILL.md 11.7 KB
Loading…
-
-
threejs-loaders
-
SKILL.md 13.7 KB
Loading…
-
-
threejs-materials
-
SKILL.md 13.1 KB
Loading…
-
-
threejs-postprocessing
-
SKILL.md 14.1 KB
Loading…
-
-
threejs-shaders
-
SKILL.md 13.7 KB
Loading…
-
-
threejs-textures
-
SKILL.md 13.3 KB
Loading…
-
-
triage
-
SKILL.md 3.4 KB
Loading…
-
-
verify
-
SKILL.md 4.3 KB
Loading…
-
-
vibesec
-
SKILL.md 24.9 KB
Loading…
-
-
zoom-out
-
SKILL.md 1.8 KB
Loading…
-
-
-
team
-
engine.js 5.9 KB
Loading… -
mcp-server.js 18.3 KB
Loading… -
ui-html.js 42.3 KB
Loading… -
worktree.js 12 KB
Loading…
-
-
tests
-
fixtures
-
codebase-memory
-
app.sh 255 B
Loading… -
app_test.sh 263 B
Loading…
-
-
-
test-bootstrap-installer-powershell.sh 4.7 KB
Loading… -
test-bootstrap-installer.sh 3.7 KB
Loading… -
test-codebase-memory-migration.sh 17.9 KB
Loading… -
test-documentation-consistency.sh 2.6 KB
Loading… -
test-dsh-installer.sh 2.3 KB
Loading… -
test-dsh-plugin.mjs 2.6 KB · in bundle
-
test-hook-contracts.sh 11.2 KB
Loading… -
test-run-hook-cmd.sh 1.5 KB
Loading… -
test-sg-browser-mcp.mjs 1.5 KB · in bundle
-
test-taste-skill-integration.sh 2.3 KB
Loading… -
test-team-e2e-simulation.mjs 8 KB · in bundle
-
test-team-engine.mjs 11.6 KB · in bundle
-
test-team-mcp.mjs 6.9 KB · in bundle
-
test-team-session-isolation.mjs 2.3 KB · in bundle
-
test-threejs-skills-integration.sh 3.9 KB
Loading… -
test-ui-html-theme.mjs 1.5 KB · in bundle
-
test-upstream-content-contracts.sh 1.4 KB
Loading… -
test-upstream-superpowers.sh 6.1 KB
Loading… -
test-user-prompt-submit-hook.sh 821 B
Loading…
-
-
themes
-
theme.json 137 B
Loading…
-
-
.gitignore.supergraph 41 B · in bundle
-
.mcp.json 344 B
Loading… -
AGENTS.md 12.4 KB
Loading… -
CHANGELOG.md 21 KB
Loading… -
CLAUDE.md 12.4 KB
Loading… -
client.js 7.7 KB
Loading… -
cordis.patch.yml 12.7 KB
Loading… -
hooks.json 1.2 KB
Loading… -
index.js 6.2 KB
Loading… -
install.sh 10.8 KB
Loading… -
LICENSE 1 KB · in bundle
-
mcp_config.json 339 B
Loading… -
OPENCODE.md 2.5 KB
Loading… -
package.json 1.5 KB
Loading… -
plugin.json 1.2 KB
Loading… -
SECURITY.md 1.4 KB
Loading… -
settings.json 3.6 KB
Loading… -
SKILL.md 2.5 KB
--- name: supergraph description: Meta-orchestrator — dispatches to the right skill for the task. Use before any non-trivial work. mcp: codebase-memory-mcp --- # 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 intent | Skill 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) -
SOUL.md 3.4 KB
Loading…
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.