local-dev

Local development environment setup and commands. Use when helping with dev server, Docker, or local testing.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/local-dev/SKILL.md

Quality

Content

83%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.

A strongly operational skill: every section is executable, copy-paste-ready, and free of padding, with genuinely project-specific detail (ports, modes, the Comet platform stack) Claude could not infer. The two weaknesses are the destructive '--clean' database-reset flow lacking a validation checkpoint before data loss, and a Platform section plus an unbundled script reference that would sit better in a dedicated reference file.

Suggestions

Add an explicit validation checkpoint before the destructive './opik.sh --clean' step, e.g., confirm with the user that data loss is acceptable or back up the DB volume first, and re-run '--verify' after restart to confirm recovery.

Move the Platform (EM) mode details (env vars, port map, architecture) into a references file (e.g., references/platform-mode.md) and keep a two-line summary plus link in SKILL.md.

Bundle or verify 'scripts/dev-runner.sh' (and './opik.sh') so the commands the skill instructs Claude to run actually resolve from the skill's own directory.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-first: annotated one-liners ('./scripts/dev-runner.sh --restart # First time / full rebuild'), a compact modes table, and log/tail commands. The only prose paragraph (Platform mode) covers project-specific architecture ('comet mode', JDK versions, sibling checkouts) that Claude cannot be assumed to know, so it earns its tokens.	5 / 5
Actionability	Every block is copy-paste executable: quick-start flags, build/lint/migrate commands, log tail commands with exact file paths ('tail -f /tmp/opik-backend.log'), a concrete health URL, and per-symptom troubleshooting recipes with exact commands ('lsof -i :8080', 'rm -rf node_modules && npm install').	5 / 5
Workflow Clarity	Sequences are clear and '--verify' serves as a status checkpoint, but the 'Database issues' flow is destructive ('./opik.sh --clean # WARNING: deletes data') with no validation step before wiping data — the rubric's cap for destructive operations without validation applies. Not 4 because the destructive path lacks a confirm/backup checkpoint; the warning label alone is not validation.	3 / 5
Progressive Disclosure	Content is well-sectioned (Quick Start, Modes, URLs, Build, Logs, SDK Config, Troubleshooting) and appropriately inline for a ~90-line operational reference, with deeper detail delegated to './scripts/dev-runner.sh --help'. Not 5: the file exceeds the 'under 50 lines' simple-skill allowance, the Platform-mode section is substantial enough to warrant its own reference file, and the referenced './scripts/dev-runner.sh' is not present in the bundle.	4 / 5
	Total	17 / 20 Passed

Description

61%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.

The description follows the good pattern of a what-clause plus an explicit 'Use when' trigger clause, with natural trigger terms like 'dev server' and 'Docker'. Its main weakness is the vague 'what': 'setup and commands' enumerates no concrete capabilities, and terms like 'local testing' are broad enough to risk overlap with other dev-workflow skills.

Suggestions

Replace the generic 'setup and commands' with concrete capabilities, e.g., 'Start, stop, and rebuild the local dev stack (backend, frontend, Docker services), run DB migrations, and check service health and logs.'

Broaden trigger coverage with natural synonyms users would say, such as 'run the app locally', 'restart the backend', or 'the dev server won't start'.

Sharpen distinctiveness by anchoring triggers to this specific project's dev workflow (e.g., naming the dev-runner script or Opik stack) rather than broad terms like 'local testing'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Local development environment') but the actions are minimal and generic ('setup and commands') — no concrete capabilities such as starting/stopping the dev stack, running migrations, or viewing logs are enumerated. It matches anchor 2 ('Names the domain but actions are minimal or generic') better than anchor 3, which requires at least 1-2 concrete named actions.	2 / 5
Completeness	Both parts are present: the what ('Local development environment setup and commands') and an explicit when ('Use when helping with dev server, Docker, or local testing'). Not 5 because the 'what' is high-level rather than a concrete list of trigger-able capabilities; the 'when' clause is present and reasonably specific.	4 / 5
Trigger Term Quality	'dev server', 'Docker', and 'local testing' are natural phrases users would actually say, giving good keyword coverage. Not 5 because common synonyms and variations are missing (e.g., 'run the app', 'restart the backend', 'localhost', 'build the project').	4 / 5
Distinctiveness Conflict Risk	'dev server' is fairly distinctive, but 'Docker' and 'local testing' are broad terms that many general development, container, and testing skills would also match, creating overlap risk with closely related skills. Not 4 because the trigger surface is broad; not 2 because it is anchored to a specific local-dev environment context.	3 / 5
	Total	13 / 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: comet-ml/opik
Path: .agents/skills/local-dev/SKILL.md
Commit: 657e319

Reviewed: 3 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.