project-stage-detect

Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts. Use when user asks 'where are we in development', 'what stage are we in', 'full project audit'.

Quality

92%

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

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable diagnostic workflow with clear sequencing, an approval checkpoint, and clean one-level references. Its main weakness is redundancy: the collaborative-ask-first protocol is repeated across the intro, step 6, and the closing section.

Suggestions

Consolidate the collaborative/approval protocol into a single section — it currently appears in the intro, section 6 ('Request Approval Before Writing'), and the closing 'Collaborative Protocol' section.

Trim the 'It's especially useful when' intro list, which restates trigger phrasing already present in the YAML description.

Remove the duplicated 'May I write to production/project-stage-report.md?' phrasing so the approval prompt appears once.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and actionable, but the collaborative 'ask before writing' protocol is stated three times (intro, section 6, and the closing Collaborative Protocol section) and the 'especially useful when' intro repeats trigger info already in the description — it could be tightened.	2 / 3
Actionability	Concrete, specific guidance throughout — exact glob patterns ('design/gdd/*.md'), directory checks (core/, gameplay/, ai/), a stage table with file-count thresholds, and a copy-paste report template; absence of code is appropriate for this read-only diagnostic skill.	3 / 3
Workflow Clarity	Six clearly sequenced steps with an explicit approval checkpoint before writing (step 6) and a PASS/CONCERNS/FAIL confidence classification; the stage.txt override check provides an explicit decision branch, fitting the score-3 anchor.	3 / 3
Progressive Disclosure	Well-organized into navigable sections with one-level-deep, clearly signaled references (the external template path '.claude/docs/templates/project-stage-report.md' and follow-up skills like /map-systems) and no nested reference chains; no bundle files exist to evaluate.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, four concrete capabilities, and an explicit 'Use when' clause with natural trigger phrases. It clearly answers what the skill does and when to invoke it with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'analyze project state, detect stage, identify gaps, and recommend next steps' — matching the multi-action anchor rather than the single-domain score-2 example.	3 / 3
Completeness	Explicitly answers both what (analyze state / detect stage / identify gaps / recommend next steps) and when ('Use when user asks...'), with an explicit trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Natural user phrasings 'where are we in development', 'what stage are we in', and 'full project audit' are exactly what a user would say, giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The project-stage-detection niche with stage/gap triggers is clearly distinct from other skills; 'full project audit' is slightly generic but the stage-specific triggers keep conflict risk low.	3 / 3
	Total	12 / 12 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
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	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/project-stage-detect/SKILL.md
Commit: 984023d

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.