project-dev

How to develop, test, lint, and build the imas-codex project. Use when making code changes, running tests, or building the project.

2.63x

Quality

73%

Does it follow best practices?

Impact

100%

2.63x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/project-dev/SKILL.md

Quality

Content

79%

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

This is a strong development skill that provides comprehensive, actionable guidance for the imas-codex project. Its greatest strengths are conciseness and actionability — every section delivers concrete commands and patterns without unnecessary explanation. The main weaknesses are limited validation/feedback loops in workflows beyond the schema workflow, and the content could benefit from better progressive disclosure by splitting reference tables into separate files.

Suggestions

Add explicit validation/feedback loops to the git workflow (e.g., 'run linting before committing, fix issues, then re-run') to strengthen workflow clarity.

Consider splitting the project structure table and test markers into a referenced file (e.g., REFERENCE.md) to improve progressive disclosure and keep the main skill focused on essential commands and workflows.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient throughout. It assumes Claude knows what pytest, ruff, git, and LinkML are without explaining them. Every section delivers actionable information without padding. Tables are used effectively for compact reference.	3 / 3
Actionability	Every section provides concrete, copy-paste-ready commands. Testing, linting, schema workflow, dependency management, and git workflow all have executable bash commands. Key patterns section provides exact import paths. The 'Never Do' list gives specific, unambiguous constraints.	3 / 3
Workflow Clarity	The schema workflow has a clear sequence with a validation step (rebuild models → verify compliance), but other workflows like git commits lack explicit validation checkpoints. The testing section doesn't specify what to do if tests fail. For a project with auto-generated files and parallel agent work, more explicit feedback loops would strengthen the guidance.	2 / 3
Progressive Disclosure	The content references AGENTS.md for additional testing guidance, which is good. However, the skill is fairly long (~130 lines of content) and some sections like the full project structure table and test markers could potentially be split into referenced files. Without bundle files, the single reference to AGENTS.md is the only progressive disclosure mechanism.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 functional and covers the basics with a clear 'Use when' clause, which is its strongest aspect. However, it relies on generic development lifecycle terms without specifying concrete tools, commands, or unique aspects of the imas-codex project that would help distinguish it. Adding more specific trigger terms and concrete actions would significantly improve skill selection accuracy.

Suggestions

Add specific tool or command names used in the project (e.g., 'Run pytest, mypy type checking, ruff linting') to improve specificity and trigger term quality.

Include file types or technology stack details (e.g., 'Python project', 'TypeScript', 'Rust crate') to improve distinctiveness and help Claude differentiate this from other project build skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('imas-codex project') and lists some actions ('develop, test, lint, and build'), but these are generic development lifecycle terms rather than concrete, specific actions like 'run pytest with coverage' or 'execute ESLint checks'.	2 / 3
Completeness	Clearly answers both 'what' (develop, test, lint, and build the imas-codex project) and 'when' ('Use when making code changes, running tests, or building the project') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'test', 'lint', 'build', and 'code changes' that users might naturally say, but misses common variations like 'compile', 'CI', 'format', 'check', 'run tests', or specific tool names that would improve matching.	2 / 3
Distinctiveness Conflict Risk	The project name 'imas-codex' provides some distinctiveness, but the actions described (develop, test, lint, build) are very common across any software project, so it could overlap with other project-specific development skills if multiple exist.	2 / 3
	Total	9 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: iterorganization/imas-codex
Commit: b0d769b

Reviewed: 27 days 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.