skill-creator

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

Quality

87%

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

Quality

Content

85%

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

A highly actionable, well-structured meta-skill with strong workflow sequencing and validation checkpoints. Its main weakness is verbosity: the directory structure and Accomplish save-path guidance are repeated across multiple sections, inflating token cost.

Suggestions

Consolidate the skill anatomy / directory-tree description into a single location instead of repeating it in 'Core Principles', 'Skill Creation Process', and 'Saving Skills'.

State the Accomplish OS save paths once and reference them rather than re-listing macOS/Windows/Linux paths in both 'Saving Skills in Accomplish' and the verification steps.

Trim 'What Skills Provide' and introductory 'About Skills' text that restate concepts a capable model already knows, to better respect the token budget.

Dimension	Reasoning	Score
Conciseness	At ~290 lines it restates the skill anatomy/directory structure multiple times (Core Principles, Skill Creation Process, Saving Skills) and re-explains the Accomplish OS paths twice; it is mostly efficient but padded with repetition and detail a competent model largely already knows.	2 / 3
Actionability	It provides copy-paste-ready frontmatter templates, concrete directory trees, and explicit verification actions (e.g. 'Use the Read tool to read the SKILL.md file'), giving fully executable guidance.	3 / 3
Workflow Clarity	A clear sequenced 6-step process with an explicit MANDATORY verification stage containing checkpoints (read file, verify path, validate frontmatter) and a feedback loop ('If verification fails: diagnose the issue and fix it before re-verifying').	3 / 3
Progressive Disclosure	No bundle files exist, but the single SKILL.md is well-organized into clearly headed sections with no nested references; per the rubric's simple-skill note, well-organized sections are sufficient here.	3 / 3
	Total	11 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-formed description that explicitly states both capability and trigger conditions in third-person voice. The only weakness is that the listed actions ('create', 'update') are somewhat abstract compared to fully concrete capability enumerations.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('create a new skill', 'update an existing skill') plus capability types (knowledge, workflows, tool integrations), but the actions are relatively abstract rather than copy-paste concrete like the level-3 'Extract text...fill forms...merge documents' anchor.	2 / 3
Completeness	It explicitly answers both 'what' ('Guide for creating effective skills') and 'when' ('Use when users want to create a new skill (or update an existing skill)') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Phrases like 'users want to create a new skill' and 'update an existing skill' are natural terms a user would actually say, giving good coverage of trigger language.	3 / 3
Distinctiveness Conflict Risk	The skill-creation niche is distinct with clear triggers, making it unlikely to fire for unrelated 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: accomplish-ai/coworker
Path: apps/desktop/bundled-skills/skill-creator/SKILL.md
Commit: 2cf74d0

Reviewed: 1 day 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.