load-skill
Load, activate, and optionally install an AI skill from a .skill file. Use this skill when the user wants to load, activate, or use a skill file. The user can invoke this skill with slash command `/load-skill [ --install | -i ] SKILLFILE`, where SKILLFILE is the path to a .skill file.
89
88%
Does it follow best practices?
Impact
86%
1.16xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
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 a strong description that clearly communicates what the skill does (load, activate, install .skill files), when to use it (when the user wants to load/activate/use a skill file), and how to invoke it (via slash command with specific syntax). The only minor note is the use of second person 'The user can invoke' which is acceptable as it describes user behavior rather than addressing the user directly.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Load, activate, and optionally install an AI skill from a .skill file.' Also specifies the slash command syntax with flags and arguments. | 3 / 3 |
Completeness | Clearly answers both what ('Load, activate, and optionally install an AI skill from a .skill file') and when ('Use this skill when the user wants to load, activate, or use a skill file'), with explicit trigger guidance including the slash command invocation. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'load', 'activate', 'install', 'skill file', '.skill file', '/load-skill', and the flag variations '--install' and '-i'. Good coverage of terms a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — loading .skill files is a specific operation unlikely to conflict with other skills. The mention of the specific file extension '.skill' and the slash command '/load-skill' make it clearly distinguishable. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, actionable skill with a clear multi-step workflow and concrete commands. Its main weakness is moderate verbosity—some explanatory text could be trimmed since Claude doesn't need to be told what a ZIP archive is or that it is 'the AI agent.' The structure is good but the Notes section feels slightly disconnected from the main workflow.
Suggestions
Trim unnecessary explanations like 'Here's a screenshot of it being used in Claude Code' and 'you (the AI agent) should' to improve conciseness.
Integrate the Notes section content (scripts/, references/ directories, prerequisites) directly into the relevant workflow steps rather than listing them separately at the end.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary verbosity, such as the screenshot mention, the explanatory note about what a .skill file is (ZIP archive), and some over-explanation of steps that Claude could infer. Phrases like 'you (the AI agent) should' and 'Here's a screenshot of it being used in Claude Code' add little value. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (e.g., the `unzip -o` command), clear step-by-step instructions with specific actions at each stage, and explicit examples of invocation. Each step tells Claude exactly what to do rather than describing abstractly. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with logical ordering: parse → validate → extract → locate → read → install → activate → clean up. Validation is explicitly included as step 2, and conditional logic (install flag) is clearly handled. The workflow covers error-adjacent cases like missing paths and prerequisites. | 3 / 3 |
Progressive Disclosure | The content is reasonably well-structured with clear sections (Usage, How to Process, Examples, Notes), but everything is in a single file with no references to external documentation. The Notes section contains information that could be better integrated into the workflow steps rather than appended separately. | 2 / 3 |
Total | 10 / 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
- fpl9000/ai-skills
- Commit
3d82fcd
- 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.