skill-authoring
Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or define a skill template for Claude Code agents.
82
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/core/src/methodology/packs/meta/skill-authoring/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities (YAML frontmatter, decision trees, verification checklists, etc.), provides comprehensive trigger terms covering natural user phrasings, and includes an explicit 'Use when...' clause. The description occupies a distinct niche that minimizes conflict risk with other skills. It uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Creates and structures SKILL.md files', 'YAML frontmatter', 'trigger phrases', 'directive instructions', 'decision trees', 'code examples', and 'verification checklists'. These are all concrete, specific deliverables. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates and structures SKILL.md files with specific components) and 'when' (explicit 'Use when...' clause listing five distinct trigger scenarios). Both halves are well-developed. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'write a new skill', 'create a skill file', 'author agent capabilities', 'generate skill documentation', 'define a skill template', 'Claude Code agents', 'SKILL.md'. These cover multiple natural phrasings a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — SKILL.md files for AI coding agents is a very specific domain. The triggers ('skill file', 'skill template', 'SKILL.md', 'agent capabilities') are unlikely to conflict with general documentation or coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent meta-skill for authoring SKILL.md files with good structure, useful templates, and appropriate progressive disclosure to companion files. Its main weaknesses are moderate verbosity (explaining concepts Claude likely already knows about writing style and anti-patterns) and a lack of a fully worked, end-to-end example of a complete SKILL.md that would make the guidance more immediately actionable.
Suggestions
Add a complete, end-to-end example of a finished SKILL.md (frontmatter + body) for a concrete skill, so the agent can see the full output format rather than just skeleton templates.
Trim the 'Voice and Tone' and 'Anti-Patterns' sections — Claude already knows active voice and good writing practices; replace with a single line like 'Use direct, imperative instructions (e.g., "Write the test first").'
Add an explicit sequential workflow with validation gates: e.g., '1. Draft frontmatter → 2. Validate fields against constraints table → 3. Write body sections → 4. Run publication checklist → 5. If any check fails, revise and re-check.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary explanations that Claude already knows (e.g., voice and tone guidance like 'use second person, present tense, active voice' and the anti-patterns table which restates general writing advice). Some sections like 'Writing Effective Triggers' could be tightened. | 2 / 3 |
Actionability | Provides structural templates and examples of good/bad patterns, but the guidance is largely meta-instructional (how to write skills) rather than executable. The code examples are illustrative placeholders rather than copy-paste ready artifacts. The markdown template structure is helpful but incomplete — it shows skeleton outlines rather than a fully worked example of a complete SKILL.md. | 2 / 3 |
Workflow Clarity | The skill has a logical sequence (anatomy → triggers → content → testing → publishing) and includes checklists, but lacks explicit validation checkpoints between steps. The process for actually creating a skill is implicit rather than explicitly sequenced with feedback loops (e.g., 'write frontmatter → validate → write body → test triggers → iterate'). | 2 / 3 |
Progressive Disclosure | Good use of progressive disclosure with clear references to external files (PACKS.md for pack organization, MAINTENANCE.md for versioning policy) that are one level deep and well-signaled. The main content is appropriately scoped as an overview with pointers to detailed materials. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rohitg00/skillkit
- Commit
dfa8d12
- Reviewed
Table of Contents
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.