CtrlK
BlogDocsLog inGet started
Tessl Logo

document

Technical documentation expert for creating clear, comprehensive documentation including API docs (OpenAPI), ADRs, system architecture docs, developer guides, and runbooks. Use when creating or improving technical documentation.

50

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/dev-skills/skills/document/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%Scale 1-5

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

This skill is a broad documentation guide that covers many documentation types but suffers from verbosity and over-explanation of concepts Claude already understands. The templates (OpenAPI, ADR) provide some concrete value, but much of the content reads like a general documentation best-practices guide rather than a focused, actionable skill. The lack of progressive disclosure means everything is crammed into one long file, and the workflow lacks concrete validation steps.

Suggestions

Remove the 'Documentation Principles' section entirely — Claude already knows to write clearly, use examples, and structure with headings. Focus tokens on project-specific conventions or non-obvious constraints.

Split the detailed templates (OpenAPI example, ADR template, runbook template, onboarding template) into separate referenced files (e.g., templates/api.yaml, templates/adr.md) and keep only brief summaries in SKILL.md.

Add concrete validation steps to the workflow, such as 'Verify all endpoints in code are documented' or 'Check that every error code has a description' rather than the vague 'Review for Clarity'.

Trim the OpenAPI example to a minimal but complete snippet (e.g., one endpoint with one response) rather than the extended version with multiple response codes and server configurations.

DimensionReasoningScore

Conciseness

The skill is significantly verbose, explaining many concepts Claude already knows (what API documentation is, what an ADR is, general documentation principles like 'use clear, concise language'). The documentation principles section and much of the template content is padding that doesn't add actionable value. The full OpenAPI example is unnecessarily long when a shorter example would suffice.

2 / 5

Actionability

The skill provides some concrete templates (OpenAPI YAML, ADR markdown) which are useful, but much of the guidance remains at the level of checklists and bullet points rather than executable instructions. The 'Task Execution' section describes what to do at a high level but lacks specific commands or concrete steps for gathering information from code.

3 / 5

Workflow Clarity

The Task Execution section provides a rough workflow (identify audience → choose format → gather info → structure → add examples → review → include next steps), but validation/review steps are vague ('Review for Clarity' with no concrete checks). The conditional logic for different flags is clear but lacks verification steps to ensure documentation accuracy or completeness.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with no references to supporting files. The lengthy OpenAPI example, full ADR template, and detailed checklists for each documentation type would benefit from being split into separate template files. There are no bundle files to support this, and no references to external resources.

2 / 5

Total

10

/

20

Passed

Description

75%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.

This is a solid description that clearly identifies its domain and lists specific documentation types, making it reasonably easy for Claude to select. The 'when' clause exists but is somewhat generic—it essentially restates the 'what' rather than providing additional trigger context. The description would benefit from richer trigger terms and a more detailed 'when' clause.

Suggestions

Expand the 'Use when...' clause with more specific trigger phrases, e.g., 'Use when the user asks to write docs, create API specifications, record architecture decisions, or build operational runbooks.'

Add common synonyms and variations users might say, such as 'README', 'docs', 'write documentation', 'document an API', or 'operational playbook'.

DimensionReasoningScore

Specificity

Lists several specific documentation types (API docs with OpenAPI, ADRs, system architecture docs, developer guides, runbooks), providing good coverage of concrete outputs. Minor gap in not describing actions beyond 'creating' and 'improving'.

4 / 5

Completeness

Has a clear 'what' (creating various types of technical documentation) and a 'when' clause ('Use when creating or improving technical documentation'), but the 'when' is fairly generic and could be more specific with additional trigger phrases like 'when the user mentions API specs, architecture decisions, or operational procedures'.

4 / 5

Trigger Term Quality

Includes good natural keywords like 'API docs', 'OpenAPI', 'ADRs', 'runbooks', 'developer guides', 'technical documentation'. Missing some synonyms users might say like 'README', 'how-to guide', 'troubleshooting guide', 'docs', or 'write documentation'.

4 / 5

Distinctiveness Conflict Risk

The enumeration of specific documentation types (ADRs, runbooks, OpenAPI) creates a fairly distinct niche. Minor overlap risk with general writing skills or API-specific skills, but the combination of documentation types makes it reasonably distinguishable.

4 / 5

Total

16

/

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

9

/

11

Passed

Repository
rikdc/ai-skills
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.