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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

70%

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

The content is well-structured with clear progressive disclosure and a strongly sequenced, iterative workflow backed by real reference files. Its weaknesses are internal redundancy (the same rules restated across sections) and partly abstract actionability, both of which keep conciseness and actionability at the mid level.

Suggestions

De-duplicate the >10-line code-block rule so it appears once (e.g., only in Content Quality) and have Anti-Patterns/Checklist reference it, improving conciseness.

Fix the broken step 2 text ('what it , when it trigger, expected output format?') and add a concrete execution hint to abstract steps like 'Research' and 'Iterate' to raise actionability.

Tighten the Quality Checklist so it verifies rather than restates rules from earlier sections, cutting repeated tokens.

Dimension	Reasoning	Score
Conciseness	The body deliberately uses telegraphic 'Caveman' compression and avoids explaining known concepts, but the >10-line-code-block rule is repeated across Content Quality, Anti-Patterns, and the Quality Checklist, and step 2 contains broken text ('what it , when it trigger'), so it could be tightened further.	2 / 3
Actionability	It gives some concrete guidance — `cp -r <skill-dir> <workspace>/skill-snapshot/`, thresholds (≥80% trigger rate, ≤100 lines), and the parallel with/without-skill eval setup — but many workflow steps ('Research', 'Capture intent', 'Iterate') remain abstract directives without concrete execution detail, and the broken step 2 leaves a gap.	2 / 3
Workflow Clarity	Both the New-skill (1–8) and Existing-skill (9–15) flows are clearly numbered with explicit evaluate→iterate→optimize feedback loops and a pre-edit snapshot safeguard, matching the score-3 anchor of clear sequence with feedback loops for error recovery.	3 / 3
Progressive Disclosure	The body is an overview pointing to one-level-deep, clearly signaled references (TEMPLATE.md, anti-patterns.md, size-limits.md, resource-organization.md, testing.md, eval-workflow.md, lifecycle.md, web-search-research.md), all of which exist as real files with 'load when...' navigation cues — matching the score-3 anchor.	3 / 3
	Total	10 / 12 Passed

Description

85%

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 is strong: it covers multiple concrete capabilities and an explicit 'Use when' trigger clause with a clear, distinct niche. Its main weakness is trigger-term quality, where jargon-heavy phrasing ('Activation', 'Token ROI') is less natural than the terms a user would actually say.

Suggestions

Soften jargon in the trigger clause toward natural user phrasing (e.g., add 'Use when the user says create skill, audit skill, or improve trigger rate') to lift trigger_term_quality from 2 to 3.

Keep the description under its already-good length but consider dropping the meta-terms 'Activation' and 'Implementation scores' in favor of plain outcomes a user would recognize.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Standardizes the creation and evaluation', 'writing or auditing SKILL.md', 'improving trigger accuracy', 'refactoring skills to reduce redundancy and maximize token ROI' — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Standardizes the creation and evaluation... Ensures skills achieve high Activation... and Implementation...') and when ('Use when: writing or auditing SKILL.md, improving trigger accuracy, or refactoring skills...'), matching the score-3 anchor.	3 / 3
Trigger Term Quality	Phrases like 'writing or auditing SKILL.md', 'improving trigger accuracy', and 'refactoring skills' are relevant but lean technical/jargony ('Activation', 'Implementation', 'Token ROI', 'high-density Agent Skills'), missing the plain user variations a person would naturally say.	2 / 3
Distinctiveness Conflict Risk	The niche — creating/evaluating/optimizing Agent Skills (Claude, Cursor, Windsurf) SKILL.md files — is distinct with specific triggers unlikely to collide with other skills.	3 / 3
	Total	11 / 12 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
Commit: 611f52a

Reviewed: 4 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.