add-skill
Create new joelclaw skills with the idiomatic process — repo-canonical, symlinked, git-tracked, slogged. Triggers on 'add a skill', 'create skill', 'new skill', 'canonical skill', 'make a skill for', or any request to formalize a process or domain into a reusable skill.
95
Does it follow best practices?
Validation for skill structure
Discovery
89%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 description excels at trigger term coverage and completeness with an explicit 'Triggers on' clause listing multiple natural phrases. The main weakness is the jargon-heavy capability description ('repo-canonical, symlinked, git-tracked, slogged') which assumes familiarity with the system rather than describing concrete actions in plain language.
Suggestions
Replace jargon terms with concrete actions: instead of 'repo-canonical, symlinked, git-tracked, slogged', describe what the skill actually does like 'creates skill files, sets up symlinks, initializes git tracking, and logs creation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (joelclaw skills) and mentions process characteristics ('repo-canonical, symlinked, git-tracked, slogged'), but these are jargon-heavy rather than concrete actions. Lacks specific verbs describing what operations are performed. | 2 / 3 |
Completeness | Clearly answers both what ('Create new joelclaw skills with the idiomatic process') and when (explicit 'Triggers on...' clause with multiple trigger phrases). The when clause is explicit and comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases: 'add a skill', 'create skill', 'new skill', 'canonical skill', 'make a skill for', plus the broader 'formalize a process or domain into a reusable skill' captures intent-based requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with 'joelclaw skills' as a unique identifier and specific trigger terms like 'canonical skill'. Very unlikely to conflict with generic coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill that demonstrates excellent technical writing for agent consumption. It provides complete, executable guidance with clear workflows, explicit constraints, and appropriate structure. The skill respects token efficiency while including all necessary procedural knowledge and gotchas (symlink behavior, reload requirements, naming conflicts).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only necessary information without explaining concepts Claude already knows. Every section serves a purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash commands, complete SKILL.md template with frontmatter, and specific directory structures. All commands are copy-paste ready with clear placeholders. | 3 / 3 |
Workflow Clarity | Clear 6-step numbered sequence covering the entire skill creation process. Includes validation through git commit and slog tracking. The 'Key Rules' section provides explicit constraints and error prevention (e.g., symlink warnings, /reload requirement). | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections: main process, key rules, updating existing skills, and optional Codex metadata. Content is appropriately structured without needing external references for this scope. Directory structure examples are inline but appropriately concise. | 3 / 3 |
Total | 12 / 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 | |
- 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.