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

78%

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

82%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-structured overview that exemplifies progressive disclosure — every detail is pushed to clearly-signaled, one-level-deep reference files that actually exist. It is highly actionable and concisely written, with only minor workflow-validation gaps preventing top marks on the remaining dimensions.

Suggestions

Add an explicit validation/verify step after edits in the Existing-skill workflow (e.g., confirm the snapshot diff or run the eval gate before iterating) to lift workflow_clarity to 5.

Provide the exact subagent spawn command for the 'Test' step so the actionability gaps close.

Trim the Standard-vs-Caveman token-count aside or move it to references/ to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body uses telegraphic 'Caveman Compression' and avoids restating concepts Claude already knows, with most lines earning their place; minor instances of explanatory padding (e.g., the Standard vs Caveman token-count aside) keep it just below the lean 5-anchor.	4 / 5
Actionability	Most guidance is concrete and copy-paste ready (snapshot command `cp -r <skill-dir> <workspace>/skill-snapshot/`, thresholds like '≥80% accuracy', line limits), but a few steps (e.g., 'Test — spawn parallel subagents') describe procedure without the exact commands, leaving minor gaps.	4 / 5
Workflow Clarity	The 15-step workflow is a clear ordered sequence with evaluation/iteration feedback loops and a final hardening checkpoint; it lacks an explicit destructive-operation validation checkpoint (the snapshot is a guard but no verify step before edits), so it sits below the validate-fix-retry 5-anchor.	4 / 5
Progressive Disclosure	The body is a compact overview that consistently pushes detail to one-level-deep references in references/ (TEMPLATE.md, anti-patterns.md, eval-workflow.md, etc.), all of which exist as real bundle files, with each link labeled by when to load it.	5 / 5
	Total	17 / 20 Passed

Description

75%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 pairs a clear capability statement with an explicit "Use when" trigger clause, covering both what and when. It is specific and distinguishable but stops short of the comprehensive, synonym-rich top anchors.

Suggestions

Add file-extension or keyword trigger hints (e.g., 'Use when: SKILL.md, evals/evals.json, or trigger-rate optimization') to lift trigger_term_quality and completeness toward 5.

Enumerate 5-8 concrete capabilities (e.g., 'Audits trigger accuracy, compresses token bloat, structures references') to reach comprehensive specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Standardizes the creation and evaluation", "improving trigger accuracy", "refactoring skills") and specific capabilities; minor gaps in enumerated capability breadth keep it just below the comprehensive 5-anchor.	4 / 5
Completeness	It has a clear "what" (standardizes creation/evaluation of Agent Skills) and an explicit "Use when" clause listing triggers; the "when" could be more specific (no keyword or file hints in the description itself), so it sits below the fully concrete 5-anchor.	4 / 5
Trigger Term Quality	The "Use when" clause names natural phrases ("writing or auditing SKILL.md", "improving trigger accuracy", "refactoring skills") that users would say, but lacks synonyms and file-extension triggers, missing a few natural variations.	4 / 5
Distinctiveness Conflict Risk	The skill targets a fairly distinct niche (Agent Skill creation/evaluation/optimization) with specific triggers; minor overlap risk with generic linting/auditing skills keeps it just below the clear-niche 5-anchor.	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
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: 405cdd5

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.