dev-server

Manage Next.js dev servers across worktrees. Start, stop, and read logs from dev servers. Agents can access logs from any running session, regardless of who started it.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/dev-server/SKILL.md

Quality

Content

63%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 highly actionable with executable commands and well-sequenced, validated workflows, but it is markedly verbose and monolithic, inlining many subsystems that should be split into separate reference files.

Suggestions

Split distinct subsystems (RGB Proxy, Auth Hub, Env modes, Worktrees, In-place branch switching) into separate reference files and keep SKILL.md as a concise overview with one-level-deep links.

Move or remove inline time-sensitive narrative ('Measured on 2026-08-16', specific node versions) into an 'old patterns'/'history' section or trim it, to satisfy the conciseness guidance.

Tighten the prose storytelling ('That is not academic. Measured on a dev box...') into the operational rule the agent needs, cutting padding while keeping the measured numbers as evidence.

Dimension	Reasoning	Score
Conciseness	At ~720 lines the body is noticeably verbose, with padded narrative sections ('That is not academic. Measured on a dev box...') and inline time-sensitive details (dates like 2026-08-16, version 26.7.0) not placed in a deprecated/old-patterns section, which the rubric penalizes.	2 / 5
Actionability	Fully executable, copy-paste-ready commands throughout (Quick Start, CLI command table, self-test invocations, env examples) covering the common cases; references to scripts resolve to real bundle files.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (numbered branch-switch steps 1-4, unwedge lifecycle) with validation checkpoints ('only after a WEDGED verdict', re-probe after restart); minor gaps keep it just below a 5.	4 / 5
Progressive Disclosure	Section structure exists and script references are one-level-deep and real, but the document is a 720-line monolith inlining several distinct subsystems (RGB proxy, auth hub, env modes, worktrees, branch switching) that clearly belong in separate reference files.	3 / 5
	Total	14 / 20 Passed

Description

66%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 is specific and distinctive, naming a clear niche and concrete actions in proper third-person voice. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits completeness.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g. starting/stopping a Next.js dev server, reading dev server logs, working across git worktrees).

Mention the probe/unwedge diagnostic capabilities to round out the action coverage.

Consider including common synonyms like 'dev server' and 'running session' for stronger trigger-term match.

Dimension	Reasoning	Score
Specificity	Names the domain ('Next.js dev servers across worktrees') and lists several concrete actions ('Start, stop, and read logs from dev servers'), with minor coverage gaps (e.g. probe/unwedge not surfaced).	4 / 5
Completeness	The 'what' is clear (manage/start/stop/read logs) but there is no 'Use when...' or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('Next.js dev servers', 'worktrees', 'logs', 'start/stop') with good coverage, though a few common synonyms ('dev server', 'running server') are not explicit.	4 / 5
Distinctiveness Conflict Risk	'Next.js dev servers across worktrees' is a clear niche with mostly distinct triggers; only minor overlap risk with generic Next.js or worktree tooling skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (726 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: civitai/civitai
Path: .claude/skills/dev-server/SKILL.md
Commit: ebb84ff

Reviewed: 5 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.