CtrlK
BlogDocsLog inGet started
Tessl Logo

docs-writer

Always use this skill when the task involves writing, reviewing, or editing files in the `/docs` directory or any `.md` files in the repository.

71

1.71x
Quality

58%

Does it follow best practices?

Impact

91%

1.71x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.gemini/skills/docs-writer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

This is a well-structured documentation writing skill with clear phased workflows and highly actionable, project-specific guidance. Its main weakness is length — the inline style guide content, while valuable and specific, makes the file longer than ideal and includes some general writing advice Claude already knows. The workflow phases and verification steps are a notable strength.

Suggestions

Consider extracting the detailed style guide (voice/tone, language/grammar, formatting/syntax sections) into a separate reference file like `references/style-guide.md` and summarizing key rules in the main SKILL.md to improve conciseness and progressive disclosure.

Remove general writing advice Claude already knows (e.g., 'Use simple vocabulary', 'Avoid jargon', 'Use active voice') and keep only project-specific conventions that Claude couldn't infer.

DimensionReasoningScore

Conciseness

The skill is fairly long but most content is project-specific style guidance that Claude wouldn't inherently know (serial comma rules, project naming conventions, callout formatting with prettier-ignore). However, some sections explain concepts Claude already understands well (e.g., 'Use active voice and present tense,' 'Use simple vocabulary,' general writing advice like 'Avoid jargon'). The voice/tone and language/grammar sections could be tightened.

2 / 3

Actionability

The skill provides highly specific, concrete guidance: exact formatting rules (wrap at 80 chars, sentence case for headings), concrete examples of callout syntax for both .md and .mdx files, specific tool usage instructions (use `replace` for small edits, `write_file` for new files), exact commands (`npm run format`), and precise word choice rules ('lets you' instead of 'allows you to'). The guidance is directly executable.

3 / 3

Workflow Clarity

The four-phase workflow (Standards → Preparation → Execution → Verification) is clearly sequenced with explicit validation checkpoints. Phase 2 has numbered preparation steps, Phase 4 includes self-review, link checking, and formatting verification. The feedback loop of checking links when headers change is mentioned in multiple phases, reinforcing the validation pattern.

3 / 3

Progressive Disclosure

The skill references external files like `CONTRIBUTING.md`, `quota-limit-style-guide.md`, `docs-auditing.md`, and `docs/sidebar.json`, which is good progressive disclosure. However, the main SKILL.md itself is quite long (~200+ lines) with detailed style guide content that could potentially be split into a separate reference file (e.g., a style-guide.md), keeping the SKILL.md as a leaner overview. No bundle files were provided to verify referenced paths exist.

2 / 3

Total

10

/

12

Passed

Description

40%

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 description functions primarily as a trigger rule rather than a proper skill description. It tells Claude when to use the skill (files in /docs or .md files) but fails to explain what the skill actually does — what standards it enforces, what templates it uses, or what specific documentation capabilities it provides. Without concrete capability information, Claude cannot make an informed decision about whether this skill is appropriate for a given task beyond simple file path matching.

Suggestions

Add specific capabilities the skill provides, e.g., 'Enforces documentation style guidelines, generates table of contents, applies consistent heading structure, and ensures proper markdown formatting.'

Include natural trigger terms users would say, such as 'markdown', 'documentation', 'README', 'technical writing', 'docs', 'wiki'.

Rewrite to clearly separate what the skill does from when to use it, e.g., 'Writes and maintains project documentation following [specific standards]. Use when working with files in /docs, .md files, or when the user asks about documentation, READMEs, or markdown formatting.'

DimensionReasoningScore

Specificity

The description mentions 'writing, reviewing, or editing files' which are generic actions, and specifies a directory and file type, but does not describe any concrete domain-specific capabilities. It says nothing about what kind of documents, what standards, or what specific operations beyond generic file editing.

1 / 3

Completeness

The 'when' is explicitly stated ('when the task involves writing, reviewing, or editing files in /docs or .md files'), but the 'what' is extremely weak — it doesn't explain what the skill actually does beyond generic file operations. There's no explanation of the skill's unique value or capabilities.

2 / 3

Trigger Term Quality

It includes some relevant keywords like '/docs directory', '.md files', 'writing', 'reviewing', 'editing', which are terms a user might naturally reference. However, it misses common variations like 'markdown', 'documentation', 'README', 'docs', or 'technical writing'.

2 / 3

Distinctiveness Conflict Risk

The scope is narrowed to '/docs' directory and '.md' files, which provides some distinctiveness. However, 'writing, reviewing, or editing' is broad enough that it could overlap with general code editing or writing skills, and any skill that touches markdown files could conflict.

2 / 3

Total

7

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
google-gemini/gemini-cli
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.