packmind-skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends CoPilot's capabilities with specialized knowledge, workflows, or tool integrations.

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 ./.github/skills/packmind-skill-creator/SKILL.md

Quality

Content

67%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 content delivers a well-structured, actionable 7-step skill-creation workflow with real bundled scripts and a validation feedback loop. Its chief weakness is conciseness, with conceptual framing sections that over-explain what CoPilot already knows.

Suggestions

Trim the 'About Skills', 'What Skills Provide', and directory-tree anatomy sections, which restate concepts CoPilot already knows; keep only the non-obvious procedural guidance.

Tighten Step 1 (Understanding) with concrete example prompts to evaluate rather than open-ended question lists.

Move detailed reference-style material (naming conventions, validation rules, distribution internals) into a references/ file and link from SKILL.md to better leverage progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance, but sections like 'About Skills', 'What Skills Provide', and the directory-tree diagram restate structural concepts CoPilot largely already knows and could be trimmed.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands referencing real bundled scripts (init_skill.py, quick_validate.py, packmind-cli), though Step 1's guidance is more descriptive than executable.	4 / 5
Workflow Clarity	A clear 7-step sequenced process with prerequisite checks and a validate-fix-retry loop in Step 5, though Step 6 (Iterate) lacks explicit checkpoints.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview pointing to two real bundled scripts at one level of depth; no references/ or assets/ exist, and some conceptual content is inlined that could move to reference files.	4 / 5
	Total	15 / 20 Passed

Description

82%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 clearly conveys what the skill does and when to use it with explicit trigger phrasing in proper third-person voice. Its main weakness is specificity, where the actions remain high-level rather than enumerating concrete capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain ('specialized knowledge, workflows, or tool integrations') and the actions 'create' and 'update' skills, but the concrete actions remain minimal and generic rather than a comprehensive list.	3 / 5
Completeness	It explicitly answers both 'what' ('Guide for creating effective skills') and 'when' ('This skill should be used when users want to create a new skill (or update an existing skill)...') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	It includes the natural phrase 'create a new skill (or update an existing skill)' that users would say, but misses common synonyms and variations like 'build a skill' or 'skill template'.	4 / 5
Distinctiveness Conflict Risk	Skill-creation/updating is a distinct meta-skill niche with explicit triggers and minimal overlap risk against domain skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	15 / 16 Passed

Repository: cteyton/packmind
Path: .github/skills/packmind-skill-creator/SKILL.md
Commit: e198635

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.