graph-engineering
Skill1 starsChanged 5 months agoMITView on GitHub
Use when work spans multiple components, an unfamiliar codebase needs dependency mapping, impact analysis depends on architecture or constraints, or durable evidence-backed project context must be created or refreshed.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- anuragsarkar97/skillstheir own version, first seen Nov 8, 2026
- Mark393295827/graph-engineering-architecturestheir own version, first seen Nov 8, 2026
- Jamie-BitFlight/claude_skillstheir own version, first seen Sep 23, 2026
- calebnewtonusc/Chewbaccatheir own version, first seen Aug 11, 2026
- HM-Li/graph-engineeringtheir own version, first seen Aug 8, 2026
- vupercentmove/claude-skillstheir own version, first seen Aug 2, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- codejunkie99/graph-engineering★ 471same name
- Jamie-BitFlight/claude_skills★ 67same name
- calebnewtonusc/Chewbacca★ 8same name
- HM-Li/graph-engineering★ 4same name
- Mark393295827/graph-engineering-architectures★ 4same name
- anuragsarkar97/skills★ 0same name
- vupercentmove/claude-skills★ 0same name
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.
In this repository14 other files it gives its agents.
- design-md-to-shadcnSkill
- figma-icons-iconifySkill
- figma-logos-svglSkill
- intro-videoSkill
- ko-naturalSkill
- langfuse-laravel-aiSkill
- loop-engineeringSkill
- onboarding-designSkill
- public-sector-rfp-authoringSkill
- release-showcaseSkill
- token-auditSkill
- ux-writing-koreanSkill
- writing-project-readmeSkill
- template-skillSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Do not require a graph database, MCP server, external API, or special runtime.
- Distinctive: line 45
Default to read-only analysis.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Graph Engineering
Overview
Model a project as evidence-backed knowledge, not a pile of files. Build only the graph needed for the current decision, keep facts separate from inference, and persist only durable knowledge.
Core Contract
- Define the question and the smallest useful scope.
- Inspect existing documentation before source code, tests, configuration, and history.
- Attach a repository path, symbol, sanitized command result, or commit to every important claim.
- Classify each claim as
observed,inferred,proposed, orunknown. - Represent relevant entities and connections with the vocabulary in knowledge-schema.md.
- Apply update-policy.md before changing durable documentation.
- Report impact, risk, unresolved questions, and the evidence that supports each conclusion.
Do not require a graph database, MCP server, external API, or special runtime. A compact Markdown table or diagram is enough when it preserves the required semantics.
Output Contract
Return these sections in order:
- Scope — question, boundaries, and audited revision when available.
- Evidence — strongest sources and any contradictions.
- Knowledge map — relevant nodes and directed relations.
- Impact — affected components, interfaces, constraints, and decisions.
- Risks and unknowns — consequences, missing evidence, and validation needed.
- Persistence decision — no change, update an existing document, or propose a new durable location.
Example map:
| Source | Relation | Target | Status | Evidence |
AccountDeletionRoute | implemented_by | DeleteAccountService | observed | api/routes/account.ts#deleteAccount |
DeleteAccountService | depends_on | DeletionJob | proposed | approved ADR-0042 |
DeletionJob | constrained_by | Idempotent cleanup | inferred | retry configuration + integration test |
Durable Knowledge Guardrail
Default to read-only analysis. Edit project knowledge only when the user explicitly requests documentation changes or the authorized task clearly includes them.
Never persist:
- chain-of-thought, hidden reasoning, scratch notes, or loop transcripts;
- raw command output or logs; persist a sanitized conclusion and command reference instead;
- unverified guesses presented as facts;
- secrets, credentials, personal data, or environment-specific identifiers;
- temporary status that will be obsolete when the current task ends.
Common Mistakes
| Mistake | Correction |
| Mapping every file | Keep only entities that affect the current decision. |
| Treating a diagram as evidence | Attach evidence to each important node or relation. |
| Replacing conflicting history | Mark the conflict and supersede only with stronger evidence. |
| Creating a new context folder immediately | Prefer the closest existing durable document. |
| Writing assumptions as architecture | Label them inferred, proposed, or unknown. |
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.

