This skill should be used when the user says "document project", "generate docs", "create documentation", "write docs", "arness code document", "arn-code-document-project", "document this feature", "document this fix", or wants to generate developer documentation for a completed feature or bug fix. Reads plan artifacts, spec files, execution reports, and git diff to produce accurate documentation. Do NOT use this for general-purpose documentation — this is specifically for Arness pipeline projects.
86
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description with excellent trigger term coverage and clear scoping to a specific pipeline context. The explicit negative boundary ('Do NOT use this for general-purpose documentation') and numerous trigger phrases make it highly distinguishable. The main weakness is that the specific output actions could be more concrete — what exactly does the produced documentation look like?
Suggestions
Specify the concrete documentation outputs more precisely (e.g., 'generates markdown documentation including feature summaries, implementation details, API changes, and usage examples') rather than the generic 'produce accurate documentation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (developer documentation for Arness pipeline projects) and mentions some actions like reading plan artifacts, spec files, execution reports, and git diffs, but the concrete output actions are somewhat vague — 'produce accurate documentation' doesn't specify what kind of documentation artifacts are created (e.g., README updates, API docs, changelogs). | 2 / 3 |
Completeness | Clearly answers both 'what' (reads plan artifacts, spec files, execution reports, and git diff to produce developer documentation) and 'when' (explicit trigger phrases and use-case guidance, plus a clear negative boundary about not using for general-purpose documentation). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'document project', 'generate docs', 'create documentation', 'write docs', 'document this feature', 'document this fix', plus the specific pipeline identifiers 'arness code document' and 'arn-code-document-project'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the explicit scoping to 'Arness pipeline projects' and the negative boundary ('Do NOT use this for general-purpose documentation'), plus unique trigger terms like 'arn-code-document-project'. Very unlikely to conflict with other documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill with a clear multi-step workflow, concrete commands, and good error handling. Its main strengths are the explicit validation step, comprehensive error recovery guidance, and specific decision criteria throughout. Minor weaknesses include slight verbosity in artifact descriptions and the inability to verify referenced bundle files exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but there's some verbosity in the step descriptions that could be tightened. For example, the parenthetical explanations after artifact names (e.g., '-- project overview, goals, key decisions') add moderate value but could be trimmed. The pipeline position diagram and overall structure are lean. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (git diff commands with exact flags, specific file paths, mkdir -p), specific file names to read, clear decision criteria (e.g., 'fewer than 15 changed files AND 3 or fewer phases'), and references to a concrete template. The AskUserQuestion interaction is fully specified with exact options. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation in Step 7 (verify file paths exist, verify class/function names are accurate). Error handling is comprehensive with specific recovery actions for each failure mode. The missing-reports scenario includes a user decision checkpoint with clear branching options. | 3 / 3 |
Progressive Disclosure | The skill references external files (doc-template.md, template-versioning.md) which is good progressive disclosure, but no bundle files were provided to verify these exist. The skill itself is moderately long and some content (like the full error handling section) could potentially be in a reference file, though it's not egregiously long. The references are one-level deep and clearly signaled. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
1fe948f
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.