create-control-manifest

After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

Quality

76%

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/create-control-manifest/SKILL.md

Quality

Content

85%

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

The body is a well-sequenced, highly actionable instruction-only skill with strong validation checkpoints and feedback loops; its only weakness is minor verbosity in a few explanatory passages that could be tightened without losing clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and does not explain concepts Claude already knows, but passages like the Manifest Version explanation ('Always matches Last Updated — they are the same date, serving different consumers') and the redundant 'When to run' note could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: exact globs ('docs/architecture/adr-*.md'), exact file paths, explicit extraction rules ('Every must, should, required to, always statement'), full AskUserQuestion option text, and a complete output template with table structures, matching the 'fully executable/specific examples' anchor for an instruction-only skill.	3 / 3
Workflow Clarity	A clear Phase 1→6 sequence is paired with explicit validation checkpoints (Director Gate TD-MANIFEST, the Phase 4 preview summary, confirm-before-write) and feedback loops (CONCERNS/REJECT → fix and re-present), matching the 'clear sequence with explicit validation steps and feedback loops' anchor for a destructive write operation.	3 / 3
Progressive Disclosure	No bundle files are provided and none are needed; the single self-contained file is organized into clearly delineated, navigable sections with no nested (2+ level) references, matching the well-organized single-file case.	3 / 3
	Total	11 / 12 Passed

Description

67%

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, third-person, and clearly distinct, but it omits an explicit 'Use when…' trigger clause, leaving the 'when to use it' half only implied and capping both completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when architecture review has passed and ADRs are in Accepted status, or when ADRs change and the programmer rules sheet needs regenerating.'

Surface a couple of natural user phrases (e.g. 'control manifest', 'rules for programmers', 'regenerate from ADRs') so the description matches terms users would actually say.

Consider trimming the comparative closer 'More immediately actionable than ADRs (which explain why)' — useful context, but the space could carry trigger guidance instead.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions — 'produces a flat actionable rules sheet for programmers', 'what you must do, what you must never do, per system and per layer', 'Extracted from all Accepted ADRs, technical preferences, and engine reference docs' — matching the 'lists multiple specific concrete actions' anchor; third-person voice is used throughout.	3 / 3
Completeness	The 'what' is clearly stated but the 'when' is only implied with no explicit 'Use when…' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain keywords appear (ADRs, architecture, rules sheet) but the description lacks a natural 'Use when…' phrasing and common user variations; the trigger is only implied via 'After architecture is complete', matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche — a programmer rules sheet extracted from Accepted ADRs and engine reference docs — with distinct triggers unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 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/create-control-manifest/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.