task-runner
Run project commands with just. Check for justfile in project root, list available tasks, execute common operations like test, build, lint. Triggers on: run tests, build project, list tasks, check available commands, run script, project commands.
88
82%
Does it follow best practices?
Impact
100%
1.40xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
92%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 well-structured skill description that clearly identifies the tool (just/justfile), lists concrete capabilities, and includes explicit trigger terms. Its main weakness is that several trigger terms ('run tests', 'build project', 'run script') are generic enough to potentially conflict with other task runner or build system skills. Adding more just-specific differentiators would help.
Suggestions
Add differentiating language to reduce conflict with other task runners, e.g., 'Use this skill specifically when a justfile is present, as opposed to Makefile, package.json scripts, or other task runners.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: check for justfile, list available tasks, execute operations like test/build/lint. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (run project commands with just, check for justfile, list tasks, execute operations) and 'when' (explicit 'Triggers on:' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would actually say: 'run tests', 'build project', 'list tasks', 'check available commands', 'run script', 'project commands'. These cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | While 'just' and 'justfile' are distinctive, trigger terms like 'run tests', 'build project', and 'run script' are generic enough to overlap with Makefile, npm scripts, or other task runner skills. The description could conflict with similar build/task runner tools. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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 skill that provides clear, actionable commands for using just as a task runner. Its main weakness is some unnecessary content (the example justfile definitions, the explanatory purpose line) and slight redundancy between sections. The workflow could be tightened by consolidating the discovery and 'when to use' guidance into a clearer sequence.
Suggestions
Remove the example justfile section — Claude doesn't need to see how justfiles are written to run them, and this nearly doubles the skill's length.
Consolidate 'When to Use' and 'Best Practice' into the main workflow, establishing a clear sequence: check if justfile exists → list available recipes → run the appropriate one.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary content. The 'Purpose' line explaining what just is ('simpler than make and works cross-platform') is information Claude already knows. The example justfile showing recipe definitions is arguably unnecessary since the skill is about running just, not writing justfiles. The 'When to Use' section largely repeats the usage examples. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready commands throughout. The bash examples are concrete and specific, covering listing recipes, running them, passing arguments, and discovery commands. No pseudocode or vague instructions. | 3 / 3 |
Workflow Clarity | For a simple skill this is adequate, but the workflow is somewhat scattered. The 'When to Use' section hints at a sequence (first check, then run) but doesn't clearly establish it as a workflow. The discovery commands are separated from the 'When to Use' guidance, and there's no validation step (e.g., checking if just is installed or if a justfile exists before attempting to run recipes). | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines of meaningful content, the organization is clean with well-labeled sections (Basic Usage, Common justfile Recipes, Discovery, When to Use, Best Practice). No external references are needed and the content is appropriately scoped. | 3 / 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
- NeverSight/skills_feed
- Commit
f772de4
- 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.