Skip to content
SkillCheatSheet Sign in

codegraph

An AI agent skill from QwenLM/qwen-code, scored 57 out of 100 by code.

57/ 100C

Code score by group

  • Spec18/20
  • Description13/20
  • Procedure12/15
  • Done criteria0/15
  • Resources6/10
  • Scripts2/8
  • Safety3/7
  • Upkeep3/5

It loses the most points in Done criteria (15), the group that checks whether there is a checklist and a step that verifies the work.

What the author says it does

Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection, auto-merge candidates, labeling). Also covers creating, inspecting, and repairing a CodeScope index. Use for: code structure, who calls what, why something changed, similar functions, module boundaries, bug tracing, class relationships, PR risk/conflicts, or any question benefiting from…

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
QwenLM/qwen-code
Folder
.qwen/skills/codegraph
License
Apache-2.0
GitHub stars
29,507
SKILL.md lines
658
Other files
5

Add codegraph to your agent

npx skills add QwenLM/qwen-code --skill codegraph

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

More skills from QwenLM/qwen-code

  1. desktop-brand-builder

    Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop cli…

    Verified87A
  2. agent-reproduce-feature

    Use when reproducing an existing Codex or Claude Code feature in Qwen Code or another agent CLI by choosing a reference agent, capturing HTTP request bodies, prompts, tool/functio…

    79B
  3. goal-draft

    Turn a fuzzy intention into a /goal objective the Goal verifier can actually judge - one outcome, numbered binary "Done when" checks that leave evidence in the transcript, guardra…

    79B
  4. agent-reproduce-align

    Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal tra…

    75B
  5. bugfix

    Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a G…

    74B
  6. docs-update-from-diff

    Review local code changes with git diff and update the official docs under docs/ to match. Use when the user asks to document current uncommitted work, sync docs with local change…

    74B
  7. memory-leak-debug

    Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retent…

    72B
  8. tmux-real-user-testing

    This skill should be used when the user asks to "用 tmux 做真实测试", "保存 tmux 日志", "像真实用户一样测试 Qwen", "生成可复查的 TUI 测试报告", "测试 slash command 交互", or requests a tmux-based real user E2E ru…

    72B

All skills in QwenLM/qwen-code

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.