project-stage-detect

Analyze project state, detect stage, identify gaps, recommend next steps. 'Where are we in development?'

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/skills/project-stage-detect/SKILL.md

Quality

Content

67%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.

A strong, unusually rigorous workflow body: concrete commands, explicit precedence rules, and careful handling of unresolved checks and tier-dependent semantics. Its main costs are verbosity — repeated minimal-tier rules and rhetorical blockquotes — and a few heuristic steps (completeness percentages, coverage estimates) left without a computation method.

Suggestions

State the minimal-tier 'do not flag optional docs' rule once (e.g. in step 3) and reference it from the other three places it currently repeats, and trim the two blockquotes to their operative instruction.

Define how the report's '[X%]' completeness values are computed (e.g. 'present artifacts ÷ tier-required artifacts') so the template is fully executable.

Replace 'estimate lines of code / test coverage (rough heuristic)' with a concrete heuristic (e.g. `wc -l` totals, test files ÷ source files ratio).

Dimension	Reasoning	Score
Conciseness	Mostly dense, non-obvious instruction (tier-dependent gap rules, artifact-check invocation constraints, confidence precedence), but noticeably padded: the minimal-tier rule is restated in four separate places and two long rhetorical blockquotes (tier resolution, configured-vs-observed) repeat their point multiple times. Fits 'mostly efficient but includes some unnecessary explanation or could be tightened'; not 2 because nothing explains concepts Claude already knows, and not 4 because the repetition is real and trimmable.	3 / 5
Actionability	Concrete throughout: the exact 'bash .claude/scripts/artifact-check.sh' call with invocation constraints, a stage table with numeric thresholds, copy-paste clarifying questions, and a ready-made report template. Falls short of 5 because some steps are unexecutable as written — the report requires Design/Code/Architecture '[X%]' completeness values and 'rough' LOC/coverage estimates with no method for computing them.	4 / 5
Workflow Clarity	Clear 1–6 sequence with strong checkpoints: a first-match Stage Confidence rule, explicit configured-vs-observed comparison with disagreement reporting, a NOT ASSESSED path for unresolved code roots, and an approval gate before the only file write. Not 5 because heuristic steps ('estimate test coverage', 'analyze completeness') have no validation checkpoint, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Well-sectioned body with clear headers, and all external pointers (artifact-check.sh, workflow-modes.md, templates/project-stage-report.md) are one level deep and real project files. Minor gaps: the report template is inlined in full even though the templates file is already cited, a small duplication; and role-filter guidance could sit in a reference. Fits 'good structure; most content appropriately placed; minor organization gaps'; not 5 given that duplication.	4 / 5
	Total	15 / 20 Passed

Description

55%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 concise and action-oriented with a memorable trigger question, but it lacks an explicit 'when to use' clause and undersells the skill's actual game-development context, leaving both trigger coverage and distinctiveness at the midline. Adding an explicit 'Use when…' sentence with the domain and natural trigger phrases would lift completeness and trigger quality together.

Suggestions

Add an explicit trigger clause, e.g. 'Use when starting on an existing game project, onboarding to a codebase, or checking readiness before a milestone.'

State the domain: mention game development (or project stages like Concept/Production) so the description distinguishes itself from generic project-analysis skills.

Include a couple of natural synonyms users would say — 'audit', 'progress check', 'onboarding' — alongside the existing 'Where are we in development?' question.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Analyze project state, detect stage, identify gaps, recommend next steps' — matching the 'several specific actions; minor gaps' anchor. Not 5 because coverage is not comprehensive: the report artifact, the game-development domain, and the role-filter option are all absent from the description.	4 / 5
Completeness	The 'what' is clear (four named actions), but the 'when' is only weakly implied by the quoted question — there is no explicit 'Use when…' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. Not 4: an implied question fragment is weaker than an explicit 'when' that 'could be more specific'.	3 / 5
Trigger Term Quality	Contains one genuinely natural user phrase — 'Where are we in development?' — plus 'project state', 'stage', 'gaps', but misses common variations users would say (onboarding, audit, progress check, milestone readiness). Fits the 'some relevant keywords but missing common variations' anchor; 4 would require broader natural-term coverage.	3 / 5
Distinctiveness Conflict Risk	'detect stage' carves a recognizable niche, but because the description never states the game-development framing, it reads as a generic project-analysis skill and could overlap with project-survey, audit, or onboarding skills. Fits 'somewhat specific but could still overlap'; not 4 since the overlap extends beyond just closely related skills.	3 / 5
	Total	13 / 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
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: 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.