skill-creator

Guide for creating effective skills. Use this skill when users need to create a new skill or reshape a draft skill package before hardening, benchmarking, or distribution.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable and workflow-clear, with executable commands and explicit validation feedback loops. It is held back by mild verbosity for a navigation-first entrypoint and by progressive-disclosure signposts that point to reference files absent from the bundle.

Suggestions

Move the dense governance/output-contract detail into references/ and leave only the operational surface in the body to improve conciseness.

Bundle the referenced files (references/foundations.md, creation-playbook.md, factory-governance-spine.md, openai_yaml.md, etc.) so the progressive-disclosure signposts resolve to real, one-level-deep documents.

Consolidate the duplicated examples-and-gotchas.md signposts (Examples, References, Gotchas sections) into a single pointer to reduce repeated navigation noise.

Dimension	Reasoning	Score
Conciseness	Assumes Claude's competence and avoids explaining basic concepts, but at ~260 lines the body packs governance posture, output-contract fields, and procedure detail that borders on reference-grade material, matching the 'mostly efficient but could be tightened' anchor rather than the lean 3.	2 / 3
Actionability	Provides fully executable commands with specific flags (init_skill.py, generate_openai_yaml.py, validate_role.sh, quick_validate.py, 'ask skills audit --level strict --robot') plus concrete output-contract field lists, matching the 'copy-paste ready' 3 anchor.	3 / 3
Workflow Clarity	The numbered Procedure gives an explicit sequence with a dedicated Validation section, fail-fast checkpoints ('Stop at the first failed gate', 'Re-run validation after each fix'), and a forward-testing step, matching the clear-sequence-with-explicit-validation 3 anchor.	3 / 3
Progressive Disclosure	The body is well-organized with 'Read when:' signposts and a per-purpose References list designed as one-level-deep pointers, but the referenced files (references/foundations.md, creation-playbook.md, etc.) are not present in the bundle, so the actual structure is incomplete and cannot reach the well-signaled-real-references 3 anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 clear and correctly pairs a 'what' statement with an explicit 'when' trigger clause, achieving full completeness. It is slightly held back on specificity, trigger-term coverage, and distinctiveness because the action list and natural-keyword coverage are not comprehensive.

Suggestions

Add concrete actions to the 'what' clause (e.g., 'scaffold, structure, and validate skill packages') to lift specificity toward the multi-action 3 anchor.

Broaden natural trigger keywords (e.g., 'scaffold a skill', 'clean up a draft SKILL.md', 'package a skill for reuse') to improve trigger-term coverage.

Sharpen the boundary against sibling skills in the description itself (e.g., 'before hardening or distribution — for hardening/benchmarking use skill-builder') to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions like 'creating effective skills' and 'reshape a draft skill package', but does not enumerate a comprehensive set of specific operations, so it falls short of the multi-action anchor at 3 and above the vague 1.	2 / 3
Completeness	Explicitly answers both what ('Guide for creating effective skills') and when ('Use this skill when users need to create a new skill or reshape a draft skill package'), with an explicit 'Use when...' clause, matching the 3 anchor; not capped at 2 because the trigger guidance is present.	3 / 3
Trigger Term Quality	Includes some natural phrasing users would say ('create a new skill', 'reshape a draft skill package') but lacks coverage of common variations and surface keywords, matching the 'some relevant keywords but missing common variations' anchor rather than full 3 coverage.	2 / 3
Distinctiveness Conflict Risk	Has a clear niche (skill creation/reshaping before hardening) with distinct triggers, but could overlap with adjacent skill-builder/skill-installer skills that it must route away from, fitting the 'somewhat specific but could still overlap' anchor at 2 rather than the unambiguous 3.	2 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 17 missing, 2 suspicious	Warning
referenced_paths_exist	Referenced path issues: 21 missing	Warning

	Total	13 / 16 Passed

Repository: jscraik/Agent-Skills
Commit: 5a6027f

Reviewed: 5 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.