local-dev

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

Quality

73%

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

76%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 skill is highly actionable and token-efficient, giving Claude ready-to-run commands for every common dev task. Its main gap is the destructive/batch operations (notably --clean) which lack an explicit validate-before-proceeding checkpoint, capping workflow clarity.

Suggestions

Add an explicit validation step to the destructive database-reset flow, e.g. run './scripts/dev-runner.sh --verify' (and confirm no running stack) before './opik.sh --clean', and re-verify after restart.

Move the detailed Platform (EM) configuration into a separate reference file and keep only a one-line pointer plus the core command in the body, improving both conciseness and progressive disclosure.

For build-fail and database-issues troubleshooting, include a short feedback loop (run --verify after the fix; re-run --restart and check the health URL) to satisfy the destructive/batch validation expectation.

Dimension	Reasoning	Score
Conciseness	The body is dominated by copy-paste commands, tables, and terse annotations with no padding about concepts Claude already knows; only the inlined Platform-mode paragraph leans slightly dense and could be trimmed or moved.	4 / 5
Actionability	Every section provides fully executable, copy-paste-ready commands (dev-runner flags, tail logs, env exports, maven/npm rebuilds) covering the common start/stop/build/lint/migrate/logs/troubleshoot cases.	5 / 5
Workflow Clarity	Sequences are clearly ordered and a --verify tool exists, but the destructive flow (stop -> --clean 'deletes data' -> restart) lacks an explicit validation checkpoint, so the destructive-operations cap of 3 applies.	3 / 5
Progressive Disclosure	Content is well-sectioned into Quick Start, Modes, URLs, Build, Logs, SDK, and Troubleshooting, and it points one level deep to './scripts/dev-runner.sh --help' for env-var detail, though the sizable Platform-mode content is inlined rather than split into a reference.	4 / 5
	Total	16 / 20 Passed

Description

70%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 cleanly states both purpose and trigger conditions with natural, user-facing keywords. It is slightly generic on the 'what' side and could list more specific capabilities to reach the top anchor.

Suggestions

Replace the generic 'setup and commands' with two or three concrete capabilities (e.g., 'start and stop the dev stack, run builds, apply DB migrations') to lift specificity.

Add a couple of common synonyms to the trigger clause (e.g., 'run the app locally', 'start the backend') to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Local development environment setup and commands') and surfaces a couple of concrete actions, but 'setup and commands' stays generic rather than listing several specific capabilities.	3 / 5
Completeness	It answers both what ('Local development environment setup and commands') and when ('Use when helping with dev server, Docker, or local testing') explicitly, but the 'what' portion is terser than the fully comprehensive anchor 5 example.	4 / 5
Trigger Term Quality	'dev server, Docker, or local testing' are natural terms users would actually say, giving good keyword coverage, though common synonyms like 'run the app' or 'start the backend' are absent.	4 / 5
Distinctiveness Conflict Risk	Scoped to local-dev tooling with concrete triggers, making it mostly distinct with only minor overlap risk against general test/build skills.	4 / 5
	Total	15 / 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: 50de943

Reviewed: 2 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.