Manage local skills - list, add, remove, search, edit, setup wizard
33
30%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skill/SKILL.mdQuality
Discovery
32%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 a terse list of actions without context or trigger guidance. While it names specific operations (list, add, remove, search, edit, setup wizard), it lacks a 'Use when...' clause and doesn't explain what 'local skills' are, making it difficult for Claude to reliably select this skill from a large pool.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to manage, install, create, or configure Claude skills on their local machine.'
Expand the description to clarify what 'local skills' means and provide more context about each action, e.g., 'Manages skill files (.md) in the local project — lists available skills, adds new ones from templates, removes unused skills, searches skill content, and runs an interactive setup wizard.'
Include natural trigger terms users might say, such as 'install skill', 'create skill', 'skill configuration', 'skill setup', or 'manage .md skill files'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists several actions (list, add, remove, search, edit, setup wizard) but they are terse and lack detail about what 'local skills' means or what each action entails concretely. | 2 / 3 |
Completeness | Provides a brief 'what' (manage local skills with listed actions) but completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 2, and the 'what' is also weak, so this scores 1. | 1 / 3 |
Trigger Term Quality | Terms like 'skills', 'add', 'remove', 'search', 'edit' are somewhat natural but 'local skills' is domain-specific jargon. Missing common user phrasings like 'install skill', 'create skill', 'skill management', or 'configure skills'. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'local skills' provides some specificity to a niche domain, but 'manage', 'list', 'add', 'remove', 'edit' are very generic verbs that could overlap with many management-type skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive in coverage but severely bloated—it tries to be both a reference manual and an instructional guide in a single file with no progressive disclosure. The content includes redundant sections (Related Skills listed twice, Future Enhancements that aren't actionable), explanatory material Claude doesn't need (Benefits of Local Skills, generic tips), and large template blocks that should be in separate files. The workflows are reasonably clear but lack validation checkpoints for destructive or file-writing operations.
Suggestions
Extract the four skill templates (Error Solution, Workflow, Code Pattern, Integration) into a separate TEMPLATES.md file and reference it from the main SKILL.md
Remove the 'Benefits of Local Skills', 'Tips for Users', and 'Future Enhancements' sections entirely—these explain concepts Claude already knows or describe unimplemented features
Add explicit validation steps to /skill add (validate generated YAML), /skill edit (validate after write), and /skill sync (verify copy succeeded) workflows
Remove the duplicate 'Related Skills' section and consolidate the example session, usage examples, and usage modes sections into a single concise reference
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines. Contains extensive template boilerplate, redundant sections (Related Skills appears twice), a 'Benefits of Local Skills' section explaining concepts Claude already understands, 'Tips for Users' that are generic advice, and 'Future Enhancements' that are not actionable. The skill quality guidelines, while useful, are lengthy and could be drastically condensed. Much of this content could be in separate reference files. | 1 / 3 |
Actionability | Provides concrete examples of expected output formats and interactive flows, and the bash scripts in /skill setup are executable. However, much of the content is descriptive behavioral specifications rather than executable instructions—it describes what Claude should do in prose rather than providing copy-paste-ready implementations. The templates are useful but are more structural scaffolding than executable code. | 2 / 3 |
Workflow Clarity | Each subcommand has numbered steps and clear sequencing. The /skill remove command includes a confirmation checkpoint, which is good. However, several workflows lack explicit validation/error recovery steps—e.g., /skill add doesn't validate the generated YAML is well-formed, /skill sync doesn't verify successful copy operations, and /skill edit doesn't validate after writing changes back. The error handling section is generic rather than integrated into each workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being 500+ lines. The four skill templates, the bash scanning scripts, the quality guidelines, and the benefits section could all be split into separate referenced files. Everything is inlined, making this extremely long for a single SKILL.md with no bundle files to support it. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (848 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
3e94567
Table of Contents
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.