common-skill-creator

Standardizes the creation and evaluation of high-density Agent Skills (Claude, Cursor, Windsurf). Ensures skills achieve high Activation (specificity/completeness) and Implementation (conciseness/actionability) scores. Use when: writing or auditing SKILL.md, improving trigger accuracy, or refactoring skills to reduce redundancy and maximize token ROI.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/common/common-skill-creator/SKILL.md

Quality

Content

78%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.

The body is a lean, well-organized instruction skill with strong progressive disclosure (real, navigable references) and clear sequenced workflows for both new and existing skills. It is kept out of the top band on conciseness/actionability/workflow by minor redundancy, one garbled fragment, and implicit rather than explicit validation checkpoints.

Suggestions

Fix the garbled step text 'what it , when it trigger, expected output format?' to read e.g. 'what it does, when it triggers, expected output format?'.

Consolidate the '>10 lines move to references/' rule to a single location to remove the triple repetition across Description Quality, Anti-Patterns, and Quality Checklist.

Add an explicit validation gate to the test/iterate loop (e.g., 'Only proceed when pass rate >=80% AND tokens decreased; else rewrite and rerun').

Dimension	Reasoning	Score
Conciseness	The body is aggressively telegraphic (caveman compression, dropped articles, snippets) and explicitly forbids re-explaining concepts Claude already knows, but it loses a point to a garbled fragment ('what it , when it trigger') and triple repetition of the '>10 lines to references' rule across Description Quality, Anti-Patterns, and Quality Checklist.	4 / 5
Actionability	Concrete commands and file paths are given (e.g., 'cp -r <skill-dir> <workspace>/skill-snapshot/', links to TEMPLATE.md), but several steps remain abstract directives ('spawn parallel subagents', 'web-search domain best practices') without copy-paste-ready commands or templates.	4 / 5
Workflow Clarity	Both new-skill and existing-skill flows are clearly sequenced as numbered lists, and a snapshot-before-edit safety step exists for the destructive edit case, but validation checkpoints in the test/evaluate/iterate loop are mostly implicit rather than explicit gates.	4 / 5
Progressive Disclosure	The body stays under 100 lines and routes detail to 8 well-signaled one-level-deep references that all exist, each annotated with a 'load when...' navigation cue, making discovery and navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

70%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.

The description uses correct third-person voice and clearly answers both what the skill does and when to use it, with concrete trigger phrases anchored to SKILL.md. It is held back from the top band by somewhat abstract, quality-goal-framed capabilities and minor internal redundancy.

Suggestions

Replace the quality-goal framing ('Ensures skills achieve high Activation...and Implementation...scores') with 5-8 distinct concrete action verbs (e.g., 'Drafts SKILL.md, audits trigger accuracy, extracts content to references/, runs parallel subagent evals').

Add a natural-synonym trigger phrase such as 'create skill' alongside 'writing or auditing SKILL.md' to broaden keyword coverage.

Remove the redundant restating of 'specificity/completeness' and 'conciseness/actionability' since they duplicate the same two metrics.

Dimension	Reasoning	Score
Specificity	Third-person verbs ('Standardizes the creation and evaluation', 'Ensures skills achieve high Activation...and Implementation...scores') name the domain and a couple of concrete actions, but the capabilities are framed as quality goals rather than 5-8 distinct concrete verbs, and 'specificity/completeness' and 'conciseness/actionability' restate the same dimensions.	3 / 5
Completeness	Both a clear 'what' (standardizes creation/evaluation, ensures activation and implementation scores) and an explicit 'when' clause with concrete triggers are present; held below 5 because the 'what' is quality-goal framing rather than a tight capability enumeration and contains redundancy.	4 / 5
Trigger Term Quality	'Use when: writing or auditing SKILL.md, improving trigger accuracy, or refactoring skills' gives good natural keyword coverage including a concrete filename, though a few common synonyms (e.g. 'create skill') are missing.	4 / 5
Distinctiveness Conflict Risk	The skill targets a specific niche (Agent Skills for Claude/Cursor/Windsurf, tied to SKILL.md files) with distinct triggers; only minor overlap risk with general skill-tooling helpers.	4 / 5
	Total	15 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Path: .github/skills/common/common-skill-creator/SKILL.md
Commit: fa8f0ec

Reviewed: 3 days 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.