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.

1.40x

Quality

72%

Does it follow best practices?

Impact

100%

1.40x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/task-runner/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and well-structured, with concrete just commands throughout. It loses points for padded generic recipe examples, the absence of validation/safety guidance around destructive recipes, and a recipe catalog that slightly overstays the inline overview role.

Suggestions

Trim or replace the 'Common justfile Recipes' block — Claude already knows how to write pytest/npm/ruff commands — keeping only just-specific syntax (e.g. argument syntax `{{env}}`).

Add a validation/safety checkpoint before destructive recipes: advise running 'just --show <recipe>' to inspect a recipe before executing 'clean' or 'deploy', and warn that recipes can run arbitrary shell commands.

Tighten the Purpose line by dropping the 'simpler than make and works cross-platform' comparison, which does not change how Claude uses the skill.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the 'Common justfile Recipes' block inlines generic recipes (pytest tests/, npm run build, ruff check, rm -rf dist/) that Claude already knows, and the Purpose line adds 'simpler than make and works cross-platform' fluff. Not a 4 because the padded recipe block could be trimmed, not a 2 because the bulk is useful command reference.	3 / 5
Actionability	Concrete copy-paste commands cover the common cases — 'just', 'just test', 'just --list', 'just --show test', 'just --justfile backend/justfile test'. Not a 5 because guidance on arguments/variables and failure handling is absent.	4 / 5
Workflow Clarity	A rough discover-then-run sequence exists ('First check: just', 'just --list'), but there are no explicit validation checkpoints, and destructive recipe examples ('clean: rm -rf', 'deploy') are shown without caution — invoking the destructive-ops cap. Not a 4 because checkpoints are missing rather than minor.	3 / 5
Progressive Disclosure	No bundle files exist; content is organized into clear sections (Purpose, Tools, Usage Examples, When to Use, Best Practice) with appropriately inline material. Not a 5 because at ~90 lines the inlined recipe catalog is borderline content that clearer signaling or a reference file would tighten.	4 / 5
	Total	14 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed description that clearly states capabilities and provides explicit trigger phrases in third person. The main gap is missing tool-specific synonyms (just, justfile) that would push trigger quality and distinctiveness to the top level.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Check for justfile in project root, list available tasks, execute common operations like test, build, lint' — with only minor coverage gaps (no recipe authoring/editing). Not a 5 because coverage is not comprehensive, and not a 3 because more than 1-2 specific actions are named.	4 / 5
Completeness	It explicitly answers both what ('Run project commands with just... list available tasks... execute common operations') and when via concrete 'Triggers on:' phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The 'Triggers on:' clause supplies natural phrases users would say ('run tests, build project, list tasks, check available commands, run script, project commands'). Not a 5 because synonyms and tool-specific terms like 'just', 'justfile', and 'make' are missing.	4 / 5
Distinctiveness Conflict Risk	The just/justfile niche and its triggers are mostly distinct from other skills, though 'project commands' and 'run script' are broad enough to invite minor overlap with generic shell-execution skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/task-runner/SKILL.md
Commit: 2f57aec

Reviewed: about 22 hours ago

Table of Contents

Discovery Implementation Validation

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.