repo-skill-authoring
Create and update repo-local skills that follow the MetaMask Mobile standard. Use for new repo-local skills, skill entrypoints, or harness shims in this repository.
76
70%
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 ./.agents/skills/repo-skill-authoring/SKILL.mdQuality
Discovery
75%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 well-structured with both 'what' and 'when' clauses, and targets a very specific niche (MetaMask Mobile repo-local skills). However, the specific actions beyond 'create and update' are somewhat vague, and the trigger terms lean heavily on project-specific jargon that users may not naturally use when requesting help.
Suggestions
Add more concrete actions describing what creating/updating a skill involves, e.g., 'Generate SKILL.md files with proper YAML frontmatter, write skill entrypoint scripts, and create test harness shims'.
Include more natural trigger terms users might say, such as 'new skill', 'SKILL.md', 'skill template', 'add a skill file', or 'scaffold a skill'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (repo-local skills for MetaMask Mobile) and some actions (create, update), but doesn't elaborate on what creating/updating entails or list comprehensive concrete actions beyond mentioning 'skill entrypoints' and 'harness shims'. | 2 / 3 |
Completeness | Clearly answers both 'what' (create and update repo-local skills following MetaMask Mobile standard) and 'when' ('Use for new repo-local skills, skill entrypoints, or harness shims in this repository'), with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'repo-local skills', 'skill entrypoints', 'harness shims', and 'MetaMask Mobile', but these are fairly technical/project-specific. Missing more natural user phrases like 'add a new skill', 'write a skill file', or 'SKILL.md'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to MetaMask Mobile repo-local skills, skill entrypoints, and harness shims — a very clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid meta-skill for repo-local skill authoring with good actionability through concrete file structures, naming rules, and copy-paste-ready templates. Its main weaknesses are the lack of explicit validation mechanisms (no scripts or commands to verify a newly created skill is well-formed) and some verbosity in the decision-making guidance sections that could be tightened. The workflow would benefit from concrete validation checkpoints rather than just listing 'Validation' as a required output section.
Suggestions
Add a concrete validation step or script (e.g., a checklist command or linting script) that verifies the created skill has correct frontmatter, matching folder/name, and valid shim pointers — this would improve workflow_clarity.
Tighten the 'When To Use This vs Native Skill Creator' and 'Purpose' sections by merging them into a single concise decision table or bullet list to reduce token overhead.
Add an explicit feedback loop in the Agent Execution Standard: if the sanity check in step 5 fails, specify what to fix and how to re-validate.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary elaboration. The 'When To Use This vs Native Skill Creator' section and parts of the 'Purpose' section explain decision-making context that could be tightened. The 'Authoring principle' callout restates what's already implied. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete directory structures, exact file paths, naming rules, minimal examples with real YAML and markdown content, and a clear step-by-step agent execution standard with required response sections. The examples are copy-paste ready templates for creating new skills. | 3 / 3 |
Workflow Clarity | The 5-step Agent Execution Standard provides a clear sequence, and step 5 includes a sanity check. However, there are no explicit validation commands or feedback loops for error recovery — the 'Validation' is listed as a required response section but no actual validation steps or scripts are defined. For a skill about creating other skills (which could introduce structural errors), this is a gap. | 2 / 3 |
Progressive Disclosure | The skill describes a structure with optional `scripts/` and `references/` directories and mentions loading content on demand, but no bundle files are provided and no external references are linked. The content is all inline in a single file, which is acceptable for this skill's complexity, but the skill itself advocates for splitting content deliberately without demonstrating it. The organization within the file is decent with clear sections. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- MetaMask/metamask-mobile
- Commit
dedb5dd
- 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.