adopt

Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks compliance not existence.

Quality

72%

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/skills/adopt/SKILL.md

Quality

Content

81%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.

An exceptionally actionable, well-sequenced audit workflow: every step has concrete commands, exact patterns, exit-code handling, and validation checkpoints with feedback loops, and the destructive migration path is carefully guarded and reversible. The main weaknesses are repetition of the minimal-tier rules across four sections and the lack of any progressive-disclosure split for a 560-line single-file body.

Suggestions

Consolidate the minimal-tier rules into one authoritative section (e.g. a small tier table near the workflow resolution) and reference it from Phases 2, 4, and Step 3 instead of restating it, trimming the body noticeably.

Move the full Phase 6 plan template into a references/ file (e.g. references/adoption-plan-template.md) and keep only the structural summary inline, reducing the main body's token footprint.

Deduplicate the repeated gate-check 'Concept is the default stage, nothing to run' parenthetical and the 'existing stories' note (state the rule once in Phase 4 and reference it from the Phase 6 template).

Dimension	Reasoning	Score
Conciseness	The body is dense with non-inferable, project-specific operational detail (exit codes, grep anchors, tier logic) and does not explain concepts Claude already knows, but it could be tightened: minimal-tier rules are restated in four places ('At minimal, scope the audit...' in Phase 2, the 2e note, the Phase 4 special case, and the Step 3 template), and the gate-check Concept parenthetical and the 'existing stories' note each appear twice. This matches the 'mostly efficient but could be tightened' anchor rather than the 'minor instances' of score 4.	3 / 5
Actionability	Guidance is fully executable: copy-paste commands ('bash .claude/scripts/gdd-structure-check.sh [path-to-gdd]', 'migrate-v1-config.sh --dry-run/--finalize'), exact grep patterns ('^>?[[:space:]]\\Status\\*:'), exit-code semantics for exit 3/4/0, exact AskUserQuestion texts, and a complete output template for the plan file. Specific examples cover the common cases with error paths explicitly handled.	5 / 5
Workflow Clarity	Phases 1-7 are clearly sequenced with explicit validation checkpoints (discovery-failure vs. format-gap distinction, dry-run before any write, ask-before-write, Gap Preview before committing, re-run verification) and genuine feedback loops for error recovery (exit-3 triage with 'do not work around it', --finalize deleting nothing on mismatch, reversibility via git checkout). Matches the top anchor including its destructive-operation safeguards.	5 / 5
Progressive Disclosure	Single-file skill with no bundle files, but strong in-body structure (numbered phases, tables, blockquoted callouts, fenced templates) and clearly signaled one-level references to external docs (.claude/docs/automation-modes.md, templates/game-brief.md, workflow-modes.md). Falls short of 5 because the ~80-line Phase 6 plan template and the per-tier required-section rules are inlined in a 560-line body where a references/ split would ease navigation; still well above anchor 3 since references that do exist are clearly signaled and structure is good.	4 / 5
	Total	17 / 20 Passed

Description

53%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 delivers a crisp, differentiated 'what' with an excellent explicit contrast against the nearest sibling skill, but it omits any 'Use when...' trigger guidance and leans on the jargon term 'brownfield', which caps completeness and trigger-term quality at the middle anchor. Adding an explicit trigger clause with natural synonyms would lift the two heaviest-weighted dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when adopting this template for an existing project with existing GDDs/ADRs/stories, or when the user asks to audit or migrate an existing project's artifacts.'

Replace or gloss the jargon term 'brownfield' with natural phrasing users would actually say (e.g. 'existing project', 'existing codebase') to improve trigger-term quality.

Name one or two more concrete actions beyond the audit itself (e.g. classifies gaps by severity, bootstraps missing infrastructure artifacts) to raise specificity from 1-2 actions to several.

Dimension	Reasoning	Score
Specificity	Names the domain ('Brownfield audit') and 1-2 concrete actions ('checks compliance not existence', 'Numbered migration plan') but coverage is not comprehensive — no mention of gap classification, infrastructure auditing, or plan writing. Fits the 'domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor above it.	3 / 5
Completeness	The 'what' is clear (audits existing artifacts for format compliance and produces a numbered migration plan), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by 'Brownfield'. Per the judging guideline, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains some relevant keywords ('audit', 'migration plan', 'existing artifacts') but misses natural variations and synonyms users would say ('adopt', 'migrate', 'existing project'), and 'brownfield' is technical jargon many users would not naturally utter. Not score 2 because more than one relevant keyword is present; not score 4 because synonym coverage is absent.	3 / 5
Distinctiveness Conflict Risk	'Unlike /project-stage-detect, checks compliance not existence' explicitly disambiguates from the most closely related skill, and 'brownfield audit' carves a niche. Falls between anchors 4 and 5: mostly distinct with minor overlap risk, since the thin trigger phrasing leaves some ambiguity against other audit/migration skills.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (575 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/adopt/SKILL.md
Commit: b21fa0f

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.