agentleFS
TIKAZITIKAZI/TIKAZ-Codex-Engineering/code-intelligence/SKILL.md

code-intelligence

Skill0 starsChanged 3 months agoMITView on GitHub

Understand repositories as systems: map code structure and semantic relationships, analyze change impact, review pull requests, and plan safe refactors. Use when a task involves unfamiliar codebases, dependency tracing, architecture mapping, PR review, or cross-file refactoring.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. WingedGuardian/GENesis-AGI★ 100same name
    2. dachent/skills★ 27same name
    3. darinh/copilot-tools★ 1same name
    4. naranor/code-intelligence-skill★ 1same 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 repository5 other files it gives its agents.

The file

Files
SKILL.md

Code Intelligence

This public entry combines the local 代码-CodeGraph and 代码-GitNexus roles into one non-competing, clean-room workflow. This TIKAZ Edition is designed, integrated, refactored, and continuously maintained by TIKAZ.

Workflow

  1. Identify the repository, framework, entry points, tests, build commands, and local instructions.
  2. Build a compact map of modules, symbols, imports, data flow, and public boundaries.
  3. For a change, trace direct and indirect consumers before proposing edits.
  4. For a PR, review correctness, regressions, security, tests, and maintainability; cite files and lines.
  5. For a refactor, define invariants, migration steps, compatibility risks, and a rollback path.
  6. Validate with repository-native tests, type checks, lint, build, and focused impact checks.

Inputs and output contract

Accept a repository path or PR, the question or proposed change, and any known constraints. Return an evidence-backed architecture map, direct and indirect consumers, prioritized findings, an implementation or refactor plan, and verification results. Cite files and lines where possible; separate observed facts, inferences, and recommendations.

Validation and fallback

Cross-check the map against repository search, build metadata, tests, and call sites. If graph tooling is unavailable, fall back to repository-native search and explicit uncertainty rather than inventing relationships. Do not edit code unless the user also requests implementation.

Example

Use code-intelligence to map the authentication flow, find consumers of this API, and identify refactor risks before any edits.

Limits

Static analysis can miss runtime reflection, generated code, environment-specific wiring, and external consumers. Mark these gaps.

Source note

This role was written independently after studying the problem space. CodeGraph and GitNexus are research references only; no GitNexus code or documentation is distributed here.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.