propagate-design-change

When a GDD is revised, scans all ADRs and the traceability index to identify which architectural decisions are now potentially stale. Produces a change impact report and guides the user through resolution.

Quality

85%

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, highly actionable multi-phase workflow with strong validation checkpoints and feedback loops. The chief weakness is conciseness: the length, the detailed template blocks, and the redundant Collaborative Protocol section could be trimmed.

Suggestions

Remove or condense the "Collaborative Protocol" section since each principle (read silently, show report first, ask per-ADR, ask before writing, non-destructive) is already demonstrated in the numbered phases.

Move the large output templates (change summary, impact entry, impact report) into a reference file or collapse them to compact specs to reduce inline token weight while keeping the workflow intact.

Trim placeholder-heavy template blocks to their essential structure rather than full scaffolded markdown.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation padding, but ~230 lines with large templated output blocks and a closing "Collaborative Protocol" that restates behaviors already encoded in the numbered phases could be tightened.	2 / 3
Actionability	Provides concrete executable guidance throughout — the `git show HEAD:...` command, fixed file paths (docs/architecture/, architecture-traceability.md), a concrete status-classification table, and copy-ready output templates with specific AskUserQuestion options.	3 / 3
Workflow Clarity	A clearly sequenced 10-phase workflow with explicit validation checkpoints (argument/file existence, git-history check, TD-CHANGE-IMPACT gate) and feedback loops (REJECT → re-analyze, CONCERNS → revise) for a batch operation across all ADRs.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single well-organized file with one-level signal to an external gate doc (`.claude/docs/director-gates.md`); sections are cleanly partitioned with no nested references.	3 / 3
	Total	11 / 12 Passed

Description

85%

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, specific description that clearly states both capability and trigger for a narrow domain. The main weakness is trigger-term variation: it leans on abbreviation jargon without spelling out the natural-language forms a user might say.

Suggestions

Add natural-language variations of the key terms (e.g. "game design document" alongside "GDD", "architecture decision records" alongside "ADRs") so the description triggers on phrasings users actually say.

Consider an explicit "Use when a game design document is revised..." clause to mirror the trigger pattern of the strongest reference examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "scans all ADRs and the traceability index", "identify which architectural decisions are now potentially stale", "Produces a change impact report", "guides the user through resolution" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does (scans ADRs/traceability, produces impact report, guides resolution) and when to use it ("When a GDD is revised"), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Relevant domain keywords are present ("GDD", "ADRs", "traceability index", "architectural decisions") but they are jargon abbreviations without common natural-language variations (e.g. "game design document", "design doc"), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	A clear niche — propagating GDD revisions to ADRs and the traceability matrix — with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	11 / 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/propagate-design-change/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.