uinaf/docs
Update repo documentation and agent-facing guidance such as AGENTS.md, README.md, docs/, specs, plans, and runbooks. Use when code, skill, or infrastructure changes risk doc drift or when documentation needs cleanup or restructuring. Do not use for code review, runtime verification, or boot/readiness infrastructure setup.
99
100%
Does it follow best practices?
Impact
99%
1.08xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 that clearly specifies what it does (updates documentation artifacts), when to use it (doc drift risk, cleanup needs), and when not to use it (code review, runtime verification). It uses third person voice, lists concrete artifact types, and includes natural trigger terms that users would employ when requesting documentation work.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifacts: 'Update repo documentation and durable agent-facing artifacts such as AGENTS.md, README.md, docs/, specs, plans, decisions, and runbooks.' This enumerates specific file types and document categories. | 3 / 3 |
Completeness | Clearly answers both 'what' (update repo documentation and durable agent-facing artifacts) and 'when' (when code/skill/infrastructure changes risk doc drift, or when documentation needs cleanup/restructuring). Also includes explicit 'do not use' guidance, which further clarifies scope. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'documentation', 'AGENTS.md', 'README.md', 'docs/', 'specs', 'plans', 'decisions', 'runbooks', 'doc drift', 'cleanup', 'restructuring'. These cover a good range of terms a user would naturally use when needing documentation updates. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carves out a distinct niche around documentation maintenance with explicit negative boundaries ('Do not use for code review, runtime verification, or boot/readiness infrastructure setup'), making it unlikely to conflict with code review or infrastructure skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that efficiently covers documentation maintenance with clear workflows, concrete validation commands, and well-structured progressive disclosure. It respects Claude's intelligence by avoiding explanations of basic concepts while providing specific, actionable guidance for each step. The handoffs section clearly scopes what is and isn't docs work, and the output format ensures consistent reporting.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It avoids explaining what documentation is or why it matters beyond a few tight principles. Every section carries actionable weight without padding or restating things Claude already knows. | 3 / 3 |
Actionability | Provides concrete commands (rg, test -e, test -L, readlink), specific file targets, a diff example for fixing stale paths, and explicit checklists. The validation section includes copy-paste-ready shell commands for verifying doc accuracy. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced (audit → routing docs → deep docs → cleanup → validate) with explicit validation in step 5 including concrete verification commands. The feedback loop of checking reality against prose before finalizing is well-defined, and the output format provides a structured checkpoint. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled one-level-deep references to three supporting files (documentation.md, specifications.md, structuring.md). Content is appropriately split between the main skill and reference materials, with specific callouts to which reference to consult for which purpose. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents