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 `agent-readiness` setup.
97
97%
Does it follow best practices?
Impact
100%
1.06xAverage 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 an excellent skill description that clearly defines its scope, provides concrete file targets and actions, includes both positive and negative trigger conditions, and uses proper third-person voice throughout. The inclusion of 'Do not use' clauses is a notable strength that helps disambiguate this skill from related ones. The natural trigger terms cover the domain well.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Update repo documentation and agent-facing guidance' with explicit file targets (AGENTS.md, README.md, docs/, specs, plans, runbooks). Also specifies cleanup and restructuring as actions. | 3 / 3 |
Completeness | Clearly answers both 'what' (update repo documentation and agent-facing guidance for specific file types) and 'when' (when code/skill/infrastructure changes risk doc drift, or when docs need cleanup/restructuring). Also includes explicit 'Do not use' negative triggers, which further strengthens completeness. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'documentation', 'AGENTS.md', 'README.md', 'docs/', 'specs', 'plans', 'runbooks', 'doc drift', 'cleanup', 'restructuring'. These cover a good range of terms a user or agent would naturally use when needing documentation updates. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to documentation maintenance with explicit negative boundaries ('Do not use for code review, runtime verification, or agent-readiness setup'), making it highly distinguishable from code review skills, testing skills, or setup skills. The specific file targets (AGENTS.md, README.md, etc.) further reduce conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%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 provides clear, actionable guidance for documentation maintenance. The workflow is well-sequenced with concrete validation steps, the content is concise and respects Claude's intelligence, and the handoff boundaries are explicit. The only minor weakness is that progressive disclosure relies on reference files that aren't provided in the bundle, making it impossible to verify the full content structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and well-structured. It assumes Claude's competence throughout — no unnecessary explanations of what documentation is or why it matters. Every section earns its place with actionable guidance, and the principles section is terse yet informative. | 3 / 3 |
Actionability | Provides concrete commands (rg, test -e, test -L with readlink), specific file lists to check, a diff example for fixing stale paths, and explicit validation checks. The output format is clearly specified with labeled lines. Guidance is specific and executable rather than abstract. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced (audit → update routing → update deep docs → clean drift → validate reality) with explicit validation in step 5 including concrete shell commands. The handoffs section clearly routes to other skills for out-of-scope work, preventing misuse. | 3 / 3 |
Progressive Disclosure | References to three supporting files (references/documentation.md, references/specifications.md, references/structuring.md) are clearly signaled and one-level deep, which is good. However, no bundle files were provided, so we cannot verify these references exist. The main content is well-organized but some sections (like step 2 'Update routing docs') are fairly detailed inline rather than being pushed to reference files. | 2 / 3 |
Total | 11 / 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