graphify
Skill29 starsChanged 7 months agoMITView on GitHub
Query the local Graphify-Labs AST knowledge graph for ThumbGate architecture questions (what connects X to Y, explain a symbol, PreToolUse/gates/adapters). Slash: /graphify.
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 111 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
When the graph exists, prefer these over raw grep for architecture:
- Very specific: line 40
Treat graph.html as retrieval
“Common” is measured: kept by at least 6 in 10 of the 111 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Graphify — ThumbGate rail (Graphify-Labs)
Upstream package: graphifyy (Graphify-Labs/graphify).
This repo wires it locally. We do not clone Graphify into a ThumbGate SKU.
Setup / readiness
npm run graphify:setup
npm run graphify:ready -- --require-graph
npm run graphify:staleBinary: .graphify-venv/bin/graphify
Graph: graphify-out/graph.json (gitignored runtime)
Query first
When the graph exists, prefer these over raw grep for architecture:
.graphify-venv/bin/graphify query "<question>"
.graphify-venv/bin/graphify path "<A>" "<B>"
.graphify-venv/bin/graphify explain "<concept>"
.graphify-venv/bin/graphify god-nodes --top 10Refresh after large pulls: .graphify-venv/bin/graphify update . --no-cluster
Never
- Treat
graph.htmlas retrieval - Claim a vector store
- Dual-edit DIRTY lesson-store graph PR #3650
- Ship Graphify as a paid ThumbGate feature without counsel clearance
Detail
docs/agents/code-search.md- Upstream skill references (if present):
.agents/skills/graphify/references/
Other versions113 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 113
- safishamsi/graphify★ 140ksame name
- Graphify-Labs/graphify★ 140ksame name
- neozhu/CleanArchitectureWithBlazorServer★ 1.2ksame name
- ZaxbyHub/opencode-swarm★ 517same name
- zaxbysauce/opencode-swarm★ 503same name
- nandyalu/trailarr★ 469same name
- DonnieDice/protondrive-linux★ 355same name
- bdfinst/agentic-dev-team★ 295same name
- cin12211/orca-q★ 224same name
- Cap-go/capgo★ 211same name
103 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use remotion-maps, threejs-materials and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillremotion-maps
Remotion Map animation knowledge
Also in 3 projects that use this
sirakinbSkillthreejs-materials
Three.js materials - PBR, basic, phong, shader materials, material properties. Use when styling meshes, working with textures, creating custom shaders, or optimizing material performance.
Also in 3 projects that use this
callmeradicalSkillgauntlet-loop
Two-agent build/review loop. A Builder subagent implements a task via TDD; a Critic subagent, spawned fresh with no shared history, evaluates the Builder's output against a stated, concrete quality bar and returns PASS or HOLD with specific, actionable feedback. On HOLD, the feedback becomes the Builder's next task and the loop repeats. On PASS, or when a max-iteration ceiling is hit, the loop stops and reports. Use when the user says "gauntlet loop", "builder and critic", "build then review in a loop", or wants an adversarial-review pattern where the reviewer can't rationalize the builder's own choices because it never saw them being made.
Also in 3 projects that use this
gcpdevSkillllm-council
Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries external LLM APIs, synthesizes their perspectives, and presents an adapted implementation plan.
Also in 6 projects that use this
OpenAISkillremotion-saas
Build an app with Remotion
Also in 3 projects that use this
sanmidableSkillwrite-swift
Also in 3 projects that use this
In this repository98 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .well-known/llms.txtllms.txt
- activesaddler-curriculum-honestySkill
- article-syndication-pipelineSkill
- autonomous-execution-mandateSkill
- aws-strands-harness-not-cloneSkill
- bolt-forge-opt-in-not-cloneSkill
- ci-gha-buildkite-patterns-not-cloneSkill
- cobble-hot-store-compare-not-cloneSkill
- colab-compute-honesty-not-cloneSkill
- comet-session-loggerSkill
- craft-playbook-gateSkill
- cyberstrike-compare-not-cloneSkill
- datadog-llm-obs-compare-not-cloneSkill
- decisive-step-evaluatorSkill
- deeppattern-discipline-honesty-not-cloneSkill
- earnie-third-author-governanceSkill
- embeddinggemma-multimodal-firewallSkill
- fiddler-control-plane-honestySkill
- gitlab-sandbox-allowlist-not-trustSkill
- halo-trace-optimize-not-cloneSkill
- harness-evolution-ceilingSkill
- ideabrowser-connectorSkill
- infoq-architect-honesty-not-cloneSkill
- jit-harness-compare-not-cloneSkill
- meko-datapack-honesty-not-cloneSkill
- mintlify-knowledge-honesty-not-cloneSkill
- model-distress-governanceSkill
- multi-harness-rl-invariantsSkill
- nvidia-specdecode-al-doctorSkill
- omp-coordination-honesty-not-cloneSkill
- openui-catalog-compose-honestySkill
- package-manager-honesty-doctorSkill
- qwenwork-policy-group-honesty-not-cloneSkill
- saas-moat-honesty-not-cloneSkill
- salt-code-policy-honesty-not-cloneSkill
- show-meSkill
- siren-mcp-governanceSkill
- skool-headless-readerSkill
- snapchat-abm-playbook-stealSkill
- strands-harness-sentinelSkill
- tailscale-p2p-governance-not-cloneSkill
- thumbgate-board-loopSkill
- thumbgate-daily-discoveriesSkill
- thumbgateSkill
- token-shunt-honesty-not-cloneSkill
- typesafe-typed-questions-not-cloneSkill
- vs-coverage-gap-not-cloneSkill
- vulnerability-pre-action-diodeSkill
- windbg-evidence-diagnosticsSkill
- wisdom-context-artifact-not-cloneSkill
- zero-outbound-spend-they-pay-usSkill
- zvec-grep-compare-not-cloneSkill
- ci-failure-triageSkill
- evidence-first-answerSkill
- fleet-coordinationSkill
- paranoid-mode-honesty-not-cloneSkill
- revenue-truthSkill
- scope-disciplineSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

