Agent Skills
› dartsim/dart
› dart-analyze
dart-analyze
GitHub执行只读仓库分析工作流，通过检查代码、测试和文档来回答问题，严格禁止文件编辑或外部变更，确保输出基于确凿证据并区分事实与推断。
Trigger Scenarios
需要分析仓库状态但不修改代码
请求对现有代码库进行只读审查或证据收集
Install
npx skills add dartsim/dart --skill dart-analyze -g -y
SKILL.md
Frontmatter
{
"name": "dart-analyze",
"description": "DART Analyze: analyze repository evidence without editing"
}
dart-analyze
Use this skill to run the DART dart-analyze workflow. The editable workflow
source lives in .claude/commands/; this generated skill is its entrypoint for
Codex and Muse.
Invocation
- Claude Code:
/dart-analyze <arguments> - Codex:
$dart-analyze <arguments> - Muse:
/dart-analyze <arguments>
Treat the text after the skill name, or the user's request when the skill is
loaded on demand, as $ARGUMENTS. When the workflow references $1, $2,
etc., map those to the positional values supplied by the user.
Command Body
Analyze repository evidence without editing: $ARGUMENTS
Required Reading
@AGENTS.md @docs/ai/principles.md @docs/ai/workflows.md @docs/ai/verification.md @docs/onboarding/ai-tools.md
Workflow
- Restate the question and the read-only boundary. Do not edit files, stage changes, or perform GitHub, CI, branch, or review-thread mutations.
- Inspect local state enough to avoid misreading user work:
git status --short --branch git diff --stat - Build an evidence set from repository files, tests, docs, generated
artifacts, and command output. Load task-specific docs from
AGENTS.mdwhen the question names a subsystem. - Separate direct evidence from inference and unknowns. Do not present an inference as a fact, and do not turn a read-only answer into an implementation plan.
- Rank explanations, risks, or options by confidence when multiple readings are plausible. Use concrete file and line references for material claims.
- If current external documentation or standards are needed for correctness, gather source-backed evidence and label date/version context explicitly.
- Stop when the synthesis answers the question with enough evidence, or report the exact proof source that is unavailable.
Output
Report:
- the question answered and the scope inspected;
- ranked synthesis with confidence;
- evidence, inference, and unknowns as separate sections;
- any discriminating read-only probe that would reduce remaining uncertainty;
- confirmation that no local edits or external mutations were performed.
Version History
-
f630c91
Current 2026-10-18 20:24
移除对 OpenCode 和 Gemini 客户端的支持，新增 Muse 客户端支持，并优化指令加载逻辑。
-
deb9869
2026-09-08 21:44
将支持的 AI 环境限制为 Claude Code 和 Codex，移除了对 OpenCode 的支持。
- b9fbefc 2026-07-19 11:29
