CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

update-docs

Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/docs/skills/update-docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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.

The content delivers a clear, well-sequenced multi-agent workflow with concrete commands and a quality-review feedback loop, but it is weighed down by hundreds of lines of generic documentation theory that Claude already knows. Splitting reference material into bundle files would materially improve both conciseness and progressive disclosure.

Suggestions

Move the generic documentation philosophy, README/JSDoc best-practice templates, and tool sweet-spot tables into a references/ file (e.g., DOC_PATTERNS.md) and link to it from SKILL.md to cut token load.

Trim or remove sections that restate knowledge Claude already has ('What TO Document', 'What NOT to Document', 'Red Flags') unless they encode project-specific conventions.

Make the agent-launch steps more concrete by providing literal invocation commands or examples instead of only skeleton prompt templates with placeholders.

DimensionReasoningScore

Conciseness

The ~650-line body inlines large blocks of generic documentation philosophy, README/JSDoc best practices, and tool sweet-spots that Claude already knows, going beyond minor over-explanation into noticeably padded territory despite an actionable workflow core.

2 / 5

Actionability

Provides concrete, executable commands (git status -u, git show, find/grep snippets) and detailed agent prompt templates with placeholders, though the agent-launch steps and skeleton templates are not fully copy-paste ready.

4 / 5

Workflow Clarity

Clear sequenced workflow (Preparation → Analysis → Planning → Writing → Verification) with an explicit quality-review feedback loop (step 10 iterate-until-pass); minor gaps keep it just below a perfect 5.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is monolithic, inlining reference material (README patterns, JSDoc examples, index-doc tables, templates) that should be split into separate referenced files; header structure provides some navigation but content is not appropriately offloaded.

3 / 5

Total

13

/

20

Passed

Description

66%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.

The description clearly communicates what the skill does and its scope across documentation types, with good natural trigger terms and low conflict risk. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits completeness.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., 'Use when updating docs after local code changes, or when the user mentions README, JSDoc, or API doc updates').

Replace generic verbs like 'Update and maintain' with more specific actions (e.g., 'Generate, update, and audit') to lift specificity toward 5.

Include more natural synonyms and file extensions (e.g., 'docs', '.md', 'code comments', 'changelogs') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Update and maintain', 'using multi-agent workflow with tech-writer agents') plus coverage of docs/, READMEs, JSDoc, and API documentation, but the verbs remain somewhat generic rather than five distinct concrete actions.

4 / 5

Completeness

Clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause; 'when' is only weakly implied via 'for local code changes', which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms users would say ('documentation', 'READMEs', 'JSDoc', 'API documentation', 'docs/') with good coverage, though a few common synonyms and file extensions are absent.

4 / 5

Distinctiveness Conflict Risk

Tied to a specific niche (documentation for local code changes via multi-agent tech-writer workflow), making it mostly distinct with only minor overlap risk against general documentation skills.

4 / 5

Total

15

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (661 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 missing, 1 suspicious

Warning

Total

13

/

16

Passed

Repository

NeoLabHQ/context-engineering-kit

Path

plugins/docs/skills/update-docs/SKILL.md

Revision

23e2428

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill