CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

docs-lifecycle-scan

Use when closing out a feature, tidying developing/ documentation, or asked to check docs health — runs the lifecycle linter and applies the README deletion rules.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplarily lean thin-router body with exact, executable commands and a clearly delegated owner document. Its weaknesses are the missing validation loop around destructive deletion operations and a sole external reference that is not bundled with the skill, making the router's target unverifiable from the skill itself.

Suggestions

Add a validation step to the workflow: after applying remediation/deletions, re-run `pnpm run verify:docs` to confirm a clean result, and include a review or dry-run checkpoint before deleting any document.

Bundle the owner standard (developing/README.md) into the skill's references/ directory, or state explicitly where it lives relative to the repo, so the router's single reference resolves from the skill itself.

Include a brief example of linter output and the expected remediation decision so the "interpret every result" step is actionable even before the owner document is opened.

DimensionReasoningScore

Conciseness

The body is a lean router: "Read `developing/README.md` before acting", "Do not restate those rules here", plus two exact commands. Every token earns its place and nothing explains concepts Claude already knows, matching anchor 5; there are no over-explanation instances that would drop it to 4.

5 / 5

Actionability

Concrete copy-paste commands are provided ("pnpm run verify:docs" and "pnpm run verify:docs -- --strict"), but the substantive remediation guidance is delegated to a file outside the skill bundle and no example of linter output or failure handling is given. Mostly executable with minor gaps matches anchor 4; anchor 5's "specific examples cover the common cases" is not met because the common case (acting on linter results) has no in-body example.

4 / 5

Workflow Clarity

A sequence is present (read the owner standard, run the linter, "Interpret every result through the owner standard above"), but the skill applies README deletion rules — a destructive, potentially batch operation — with no pre-deletion verification, dry-run, or post-remediation re-run of the linter. Per the rubric's cap for destructive/batch workflows missing validation, workflow_clarity cannot exceed 3.

3 / 5

Progressive Disclosure

The thin-router structure is clean with a clearly signaled one-level reference ("Read `developing/README.md` before acting. It owns document classification, lifecycle markers, deletion conditions, and remediation."). However, the referenced file is not part of the skill bundle (no references/ directory exists) and its path basis is ambiguous, leaving a minor organization gap that keeps it below anchor 5.

4 / 5

Total

16

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, well-constructed description that explicitly covers both what the skill does and when to use it, with natural trigger phrases and a distinct docs-lifecycle niche. Its only weaknesses are limited action coverage (two actions) and a slightly broad "docs health" trigger that invites minor overlap with general documentation skills.

DimensionReasoningScore

Specificity

"runs the lifecycle linter and applies the README deletion rules" names the docs-lifecycle domain and two concrete actions, but coverage is not comprehensive (classification, markers, and remediation outcomes are unnamed). Anchor 4 requires several specific actions, which two does not meet; anchor 2's generic actions fit worse since both actions are specific.

3 / 5

Completeness

Explicitly answers both: what ("runs the lifecycle linter and applies the README deletion rules") and when ("Use when closing out a feature, tidying developing/ documentation, or asked to check docs health") with three concrete trigger phrases. The 'when' is fully explicit, so this matches anchor 5 rather than anchor 4 where the trigger guidance would be less specific.

5 / 5

Trigger Term Quality

"closing out a feature", "tidying developing/ documentation", and "asked to check docs health" are natural phrases a user would say, giving good keyword coverage across three trigger scenarios. Common variations like "stale docs", "outdated documentation", or "docs cleanup" are missing, so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The niche framing ("lifecycle linter", "README deletion rules", "developing/ documentation") is clearly distinguishable, but "asked to check docs health" is broad enough to overlap with general documentation-hygiene skills. Minor overlap risk with closely related skills matches anchor 4; anchor 5's minimal-conflict bar is not met.

4 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

amplifthq/opentag

Path

.claude/skills/docs-lifecycle-scan/SKILL.md

Reviewed

Table of Contents

Is this your skill?

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.