Name: write-a-skill
Rating: 62.4 (1 reviews)
Author: alirezarezvani

write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/write-a-skill/SKILL.md

The canonical home for this skill is write-a-skill in alirezarezvani/claude-skills

Quality

Content

71%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.

A well-structured, actionable authoring skill with a clear workflow, concrete templates, and a review checklist. Its main weakness is progressive disclosure: the body signals companion reference and script files that are absent from the bundle, breaking navigation.

Suggestions

Ship the referenced bundle files (references/companion_tooling.md and scripts/skill_review_checklist_runner.py) or remove/guard the links so signaled navigation resolves to real files.

Tighten the few explanatory sentences (e.g., 'Scripts save tokens and improve reliability vs generated code') to push conciseness toward the lean anchor.

Add an explicit 'validate, then proceed' checkpoint inside the Draft → Review flow (e.g., run the checklist runner and only finalize once it passes) to make the workflow's validation gates explicit.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and list-driven with minimal padding; only a few sentences ('Scripts save tokens and improve reliability vs generated code', 'The bad example gives your agent no way to distinguish...') could be trimmed, keeping it just below the 'every token earns its place' anchor.	4 / 5
Actionability	It provides a copy-paste SKILL.md template, a directory tree, and concrete commands ('python scripts/skill_review_checklist_runner.py', '/cs:book-to-skill'), but the template contains placeholders rather than fully executable code, so it is mostly—but not fully—copy-paste ready.	4 / 5
Workflow Clarity	The three-phase Gather → Draft → Review process is clearly sequenced and backed by a Review Checklist and programmatic validation runner; checkpoints are present though not framed as explicit validate-then-proceed gates, leaving a minor gap below the top anchor.	4 / 5
Progressive Disclosure	References are one-level-deep and clearly signaled ('See references/companion_tooling.md', 'python scripts/skill_review_checklist_runner.py'), but the referenced bundle files do not exist in ./references or ./scripts, so the actual bundle structure does not match the signaled navigation and discovery is incomplete.	3 / 5
	Total	15 / 20 Passed

Description

78%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.

A strong, well-formed description that clearly states capability and gives explicit, natural-language triggers with good synonym coverage. Its only weakness is that the 'what' relies on one verb plus quality modifiers rather than enumerating multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Create new agent skills') and a few concrete attributes ('proper structure, progressive disclosure, and bundled resources'), but these are modifiers on a single verb rather than multiple distinct actions like extract/fill/merge, so it stops at the '1-2 concrete actions' anchor.	3 / 5
Completeness	It explicitly answers both 'what' ('Create new agent skills with proper structure, progressive disclosure, and bundled resources') and 'when' ('Use when user wants to create, write, build, or author a new skill') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	'Use when user wants to create, write, build, or author a new skill' supplies four natural synonyms a user would actually say; coverage is good but not maximally comprehensive (no file-type or extension triggers apply to this domain), landing just below the top anchor.	4 / 5
Distinctiveness Conflict Risk	'Create new agent skills' is a clear, narrow niche with distinct triggers, but it sits alongside a sibling authoring skill (book-to-skill referenced in the body), creating minor overlap risk rather than zero conflict.	4 / 5
	Total	16 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/write-a-skill/SKILL.md
Commit: 19392f7

Reviewed: ~14 hours ago

Table of Contents

Discovery Implementation Validation

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.