CtrlK
BlogDocsLog inGet started
Tessl Logo

technical-writer

AI DevKit · Review and improve documentation for novice users. Use when users ask to review docs, improve documentation, audit README files, evaluate API docs, review guides, or improve technical writing.

80

Quality

100%

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

100%Weight 40%Scale 1-3

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

A well-crafted, compact instruction skill: it is lean, gives concrete review guidance plus a copy-paste output template, includes an approval gate before any rewrite, and is cleanly sectioned with no need for external references. Adding a single fully worked example review (filled ratings + issues + fixes) would push actionability from strong to exemplary, but nothing currently falls below the top anchor.

DimensionReasoningScore

Conciseness

The ~46-line body is lean and assumes Claude's competence — it never explains what documentation is or how reviews work — and the 3-row "Red Flags and Rationalizations" table earns its place as actionable guardrail rather than padding, matching the score-3 anchor.

3 / 3

Actionability

Concrete, copy-paste-ready guidance throughout — explicit hard rules, defined review dimensions, a priority rubric, "Do Instead" counter-guidance, and a filled-format Output Template — so the instruction-only skill is fully actionable even without code; it is not a 2 because nothing is pseudocode or merely descriptive.

3 / 3

Workflow Clarity

The single review task is unambiguous with an explicit approval checkpoint ("Do not rewrite documentation until the user approves the suggested fixes"); per the rubric's simple-skills note, an under-50-line single-purpose skill with clear organization scores 3 without an explicit multi-step workflow.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the body is split into clearly labeled sections (Hard Rules, Review Dimensions, Priority, Red Flags, Output Template), which the rubric's simple-skills note explicitly allows to score 3 for a short, well-organized skill with no external references.

3 / 3

Total

12

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong description: it names concrete capabilities, includes an explicit "Use when…" trigger with natural user phrasings, and targets a clear niche. The only minor blemish is the "AI DevKit ·" brand prefix, which adds no trigger value but is too brief to be penalized as fluff.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Review and improve documentation", "audit README files", "evaluate API docs", "review guides", "improve technical writing" — matching the score-3 anchor for multiple specific concrete actions rather than the partial coverage of a 2.

3 / 3

Completeness

Explicitly answers both what ("Review and improve documentation for novice users") and when (an explicit "Use when…" trigger), which is the score-3 anchor; it is not a 2 because the when is explicit, not implied.

3 / 3

Trigger Term Quality

The "Use when users ask to review docs, improve documentation, audit README files, evaluate API docs, review guides, or improve technical writing" clause covers natural phrasings a user would actually say, matching the good-coverage anchor; the "AI DevKit ·" prefix is harmless noise that does not reduce it.

3 / 3

Distinctiveness Conflict Risk

The novice-user documentation-review framing with concrete targets (README files, API docs, guides) carves a distinct niche unlikely to fire for the wrong skill; mild overlap with generic writing skills keeps it from being unambiguously conflict-free but it sits closer to the score-3 anchor than the 2.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
codeaholicguy/ai-devkit
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.