CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quick-design

Lightweight spec for small changes — tuning adjustments, minor mechanics. Embeds directly into stories; skips full GDD.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/quick-design/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is an exceptionally actionable, well-sequenced workflow: concrete templates for every change category, exact prompts and option lists, explicit approval gates, and clear redirect rules. Its main weaknesses are duplicated redirect/next-step passages that could be tightened and a single-file structure whose template bulk could be split into reference files.

Suggestions

State the redirect criteria once (Pipeline Notes) and have section 1 reference them, removing the duplicated classification-escape list.

Drop either the "Recommended Next Steps" section or the "Next step" line inside the section 5 handoff block — they repeat the same /story-readiness and /dev-story guidance.

Move the three spec templates to references/templates/ (e.g. tuning.md, tweak-addition.md, new-small-system.md) and point to them from section 3, cutting SKILL.md roughly in half.

DimensionReasoningScore

Conciseness

The guidance is mostly efficient with no concept over-explanation, but redirect criteria appear twice ("If the change does NOT fit these categories" in section 1 and "Redirect to the full pipeline if any of the following" in Pipeline Notes), the /story-readiness next step is stated in both the section 5 handoff block and "Recommended Next Steps", and "Verdict: **REDIRECTED**" is repeated three times — matching anchor 3 ("could be tightened") rather than 4's "minor instances", since the redundancy spans multiple sections.

3 / 5

Actionability

Fully executable instruction-only guidance: complete copy-paste spec templates for all four change categories, exact AskUserQuestion prompts with enumerated options, exact output paths and filename patterns ("jump-height-tuning-2026-03-10"), and verbatim report strings ("Found GDD at [path]. Relevant section: [section name]") — matching anchor 5, "specific examples cover the common cases".

5 / 5

Workflow Clarity

Five clearly sequenced steps (Classify, Context Scan, Draft, Approval and Filing, Handoff) with explicit validation checkpoints: the user confirms the inferred classification, an approve/revise/re-present feedback loop in section 4, and a separate explicit approval gate before any GDD edit ("Do not make GDD edits without explicit approval") — matching anchor 5's "explicit validation steps; feedback loops for error recovery".

5 / 5

Progressive Disclosure

Well-organized numbered sections with no nested references and a single self-contained file (no bundle files exist to reference). The ~305-line body inlines three full spec templates that could live in a references/ file to slim SKILL.md, and the trailing "Recommended Next Steps" section is loosely attached — matching anchor 4 ("good structure; minor organization gaps") rather than 5, since there is no overview/references split for the template bulk.

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 communicates a clear niche — lightweight specs for small game-design changes — and explicitly positions against the full GDD path. However, it lacks an explicit "use when" trigger clause and natural trigger-term coverage ("tweak", "balance change", "small feature"), capping completeness and trigger quality at moderate levels.

Suggestions

Add an explicit trigger clause, e.g. "Use when a change is too small for /design-system — a tuning value, mechanic tweak, or small feature — but too meaningful to implement without a written rationale."

Include natural synonyms users would actually say ("tweak", "balance change", "small feature", "quick spec") alongside "tuning adjustments, minor mechanics" to broaden trigger-term coverage.

Replace "Embeds directly into stories" (which conflicts with the body's separate-file output under design/quick-specs/) with a concrete action like "Writes a one-page spec to design/quick-specs/" to sharpen specificity and accuracy.

DimensionReasoningScore

Specificity

Quotes: "Lightweight spec for small changes", "Embeds directly into stories; skips full GDD". It names the domain (lightweight design spec) and a couple of concrete behaviors, but does not enumerate several specific actions — matching anchor 3 ("Names domain and 1-2 concrete actions, but not comprehensive") rather than 4, which requires several listed actions with only minor gaps.

3 / 5

Completeness

Quotes: "Lightweight spec for small changes — tuning adjustments, minor mechanics." The "what" is clear, but there is no "Use when..." clause or equivalent explicit trigger guidance; the "when" is only weakly implied by "for small changes", which caps completeness at 3 per the judging guidelines. Not 4, because the when is implicit rather than explicit.

3 / 5

Trigger Term Quality

Quotes: "small changes", "tuning adjustments, minor mechanics", "GDD". Some natural phrases are present, but common variations a user would actually say — "tweak", "balance change", "small feature", "quick spec" — are missing, matching anchor 3 ("Some relevant keywords but missing common variations or synonyms") rather than 4's good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

Quotes: "skips full GDD", "tuning adjustments, minor mechanics". Explicitly positioning against the full-GDD path plus niche game-design vocabulary carves a mostly distinct niche with only minor overlap risk against a sibling design-spec skill — matching anchor 4 rather than 3, since the contrast with the heavyweight path is stated rather than left implicit.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

13

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/quick-design/SKILL.md

Reviewed

Table of Contents

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.