CtrlK
BlogDocsLog inGet started
Tessl Logo

document

Write structured Markdown documentation. Use when: creating a README, ADR, design doc, RFC, runbook, playbook, release notes, incident report, API doc, troubleshooting guide, FAQ, onboarding guide, contributing guide, changelog, user guide, meeting notes, Confluence page, JIRA ticket, or any technical document. Handles tables of contents, summaries, conclusions, comparison tables, decision matrices, glossaries, and diagram placeholders.

90

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

92%

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 strong skill description that clearly communicates what it does and when to use it. The extensive enumeration of document types serves as excellent trigger terms, and the explicit 'Use when:' clause ensures completeness. The only weakness is the very broad scope which could create overlap with other documentation or writing-related skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and document types: README, ADR, design doc, RFC, runbook, etc. Also specifies structural elements it handles like tables of contents, summaries, comparison tables, decision matrices, glossaries, and diagram placeholders.

3 / 3

Completeness

Clearly answers both 'what' (write structured Markdown documentation, handles TOCs, summaries, tables, etc.) and 'when' (explicit 'Use when:' clause with an extensive list of document types and a catch-all 'any technical document').

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: README, ADR, design doc, RFC, runbook, playbook, release notes, incident report, API doc, troubleshooting guide, FAQ, onboarding guide, contributing guide, changelog, user guide, meeting notes, Confluence page, JIRA ticket. These are all terms users would naturally use when requesting documentation.

3 / 3

Distinctiveness Conflict Risk

While the focus on structured Markdown documentation is fairly specific, the extremely broad scope ('any technical document') and inclusion of items like 'JIRA ticket' and 'Confluence page' could overlap with project management or wiki-specific skills. The catch-all nature slightly increases conflict risk with other writing or documentation skills.

2 / 3

Total

11

/

12

Passed

Implementation

85%

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

This is a strong, well-architected skill with excellent workflow clarity, high actionability, and good progressive disclosure through a comprehensive reference/template system. The mandatory workflow with explicit gates and feedback loops is particularly well done. Minor conciseness improvements could be made by eliminating the redundant 'Hard rules' section and tightening some phrasing, but overall the content is high quality.

DimensionReasoningScore

Conciseness

The content is mostly efficient and well-structured, but includes some redundancy — for example, the 'Hard rules' section at the bottom repeats what's already stated in the Step 7 checklist. Some phrasing could be tightened (e.g., 'Run every step in order; do not skip or collapse steps even if the user's prompt seems to make one unnecessary' is slightly verbose). Overall it respects Claude's intelligence but has room for trimming.

2 / 3

Actionability

The skill provides highly concrete, step-by-step instructions with specific tool calls (vscode_askQuestions), explicit file references, a detailed reference/template lookup table, a self-review checklist with exact checks, and clear naming conventions (kebab-case examples). Every step is actionable and unambiguous.

3 / 3

Workflow Clarity

The 11-step mandatory workflow is clearly sequenced with explicit validation checkpoints: Step 5 is a mid-review loop until approved, Step 6 begins with a verification gate ('if anything is missing, stop and complete it'), and Step 7 is a detailed self-review checklist with a 'fix and re-validate' feedback loop before writing output. The instruction to stop and go back if a step was missed adds further safety.

3 / 3

Progressive Disclosure

The SKILL.md serves as a clear overview with well-signaled, one-level-deep references to specific files (planning-questions.md, formatting-rules.md, doc-type-catalogue.md, linking-strategy.md, structure-review.md, plus type-specific references and templates). The reference table is well-organized and navigation is straightforward. Content is appropriately split between the overview and referenced files.

3 / 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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
kvokov/ai-toolkit
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.