brownfield

Scan and manage brownfield repository/worktree defaults for interviews

Quality

67%

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 ./.claude-plugin/skills/brownfield/SKILL.md

Quality

Content

77%

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 concrete tool calls, commands, and a well-sequenced workflow including validation checkpoints. Its main weaknesses are monolithic structure with no reference split-out and some repetition in the deferred-schema guard that could be tightened.

Suggestions

Move the per-subcommand implementation details and the detect flow into a reference file (e.g. SUBCOMMANDS.md) referenced one level deep, leaving an overview in SKILL.md.

Tighten the deferred-schema guard section, which restates the same re-load-before-every-call rationale multiple times.

Condense the scan-boundaries bullet list, which partially restates details already embedded in the scan step.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious operational detail (MCP calls, rendering constraints, scan boundaries) rather than Claude-known concepts, but the deferred-schema guard explanation is repetitive and overall length could be trimmed.	2 / 3
Actionability	It provides exact MCP tool calls with literal argument objects, exact bash commands (uvx --from ouroboros-ai ouroboros detect), and copy-paste-ready display grids and prompts.	3 / 3
Workflow Clarity	The default flow is a clearly sequenced Step 1/2/3 process with explicit checkpoints (re-load guard before each call, stop conditions, parse-retry loop, confirmation display, and a detect failure fallback).	3 / 3
Progressive Disclosure	Content is well-sectioned but monolithic at ~240 lines with no external reference files, and detail that could be split out (subcommand specs, detect implementation) remains inline.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 states a clear, distinctive niche and a concrete scan action, but relies on technical terms and omits an explicit "Use when..." trigger. Adding natural trigger phrasing and listing a couple more concrete actions would round it out.

Suggestions

Add an explicit "Use when..." clause naming natural triggers (e.g. "Use when scanning for existing repos or setting default repo context for interviews").

Replace the vague verb "manage" with concrete actions (e.g. "scan, list, and set default repositories").

Soften jargon by including the natural term "repos" alongside "repository/worktree".

Dimension	Reasoning	Score
Specificity	"Scan and manage brownfield repository/worktree defaults" names a concrete domain and the action "Scan", but "manage" is vague and it stops short of listing multiple specific actions like the score-3 anchor.	2 / 3
Completeness	The "what" is stated clearly, but the "when" is only implied via "for interviews" with no explicit "Use when..." trigger, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Terms like "brownfield", "repository", "worktree", and "defaults" are relevant but lean technical and miss the more natural variations (e.g. "repos") a user would actually say.	2 / 3
Distinctiveness Conflict Risk	"brownfield repository/worktree defaults for interviews" carves out a clear, narrow niche with distinct triggers that is unlikely to overlap with other skills.	3 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Q00/ouroboros
Path: .claude-plugin/skills/brownfield/SKILL.md
Commit: f09fa36

Reviewed: about 3 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.