CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

design-system

Section-by-section GDD authoring for one system — walks through each required section, cross-references dependencies.

Quality

74%

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/design-system/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 a well-architected orchestration layer: it sequences seven phases, delegates per-phase detail to real one-level-deep reference files, and hard-codes collaboration checkpoints, validation, and crash recovery. Its only real weakness is minor token inefficiency from boilerplate repeated across the phase headers and mostly-deferred executable detail.

DimensionReasoningScore

Conciseness

The body is dense and operational — no concept explanations, exact thresholds ("context at or above 70%"), tool-specific instructions, and load-bearing tables — matching anchor 4. Not 5: the sentence "Read it again if the conversation was compacted or resumed during this phase" is repeated verbatim five times across phases 1-5 and could be stated once; the agent-spawning preamble also runs slightly long. Not 3: nothing explains what Claude already knows or pads without purpose.

4 / 5

Actionability

Concrete throughout: exact file paths (production/session-state/active.md, design/gdd/[system-name].md), an executable Grep recipe ("pattern `^#`, content mode" with offset/limit Read), verbatim AskUserQuestion texts, and named roles in the routing tables — anchor 4. Not 5: most phase-level executable detail is delegated to the reference files, so the body itself carries relatively few fully executable commands beyond the recovery and routing sections.

4 / 5

Workflow Clarity

Seven explicitly sequenced phases, a dedicated Post-Design Validation phase (§5 with self-check re-reading the file from disk), approval checkpoints at every decision point, incremental writes with session-state updates, and a Recovery & Resume section with a concrete detection procedure — matching anchor 5 (explicit validation steps, error-recovery loops, checklists). Not 4: validation checkpoints are explicit and central, not merely present with minor gaps.

5 / 5

Progressive Disclosure

The body is a true overview: each phase's steps live in a well-named reference file (references/1-parse-arguments.md through 5-post-design.md, plus four lens files — all verified to exist), each signaled with "Read ... now and follow it". References are one level deep (reference files point only to project content and lens files SKILL.md itself also names), matching anchor 5. Not 4: navigation is explicit and the split is clean, with no buried or ambiguous references.

5 / 5

Total

18

/

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 states a clear, domain-specific capability but reads more like an internal synopsis than a trigger-optimized skill description. It answers "what" well and is distinct within its skill family, yet completely lacks a "when to use" clause and natural trigger phrasing, which caps its completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when designing or authoring a game system's GDD, writing a design document for a system in systems-index.md, or when the user asks to design/spec a system."

Include natural synonyms and phrasings users would actually say — "game design document (GDD)", "design doc", "spec out a system" — to improve trigger term coverage.

Mention one or two more concrete actions (e.g. creates the GDD skeleton, validates the finished document, resumes interrupted sessions) to raise specificity from 1-2 actions to several.

DimensionReasoningScore

Specificity

"Section-by-section GDD authoring for one system — walks through each required section, cross-references dependencies" names the domain plus two concrete actions (section walkthrough, dependency cross-referencing), matching anchor 3. Not 4: it omits several specific actions the skill actually performs (skeleton creation, approval loops, post-design validation, specialist-lens review). Not 2: the actions named are concrete rather than minimal or generic.

3 / 5

Completeness

The "what" is clear (section-by-section GDD authoring with dependency cross-referencing), but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description, capping completeness at 3 per the rubric guideline. Not 4: the "when" is entirely absent, not merely implicit; not 2 because the "what" is specific, not vague.

3 / 5

Trigger Term Quality

"GDD authoring" and "system" are relevant keywords, but common natural variations are missing — "game design document" spelled out, "design doc", "write/create a GDD", "design a system". Matches anchor 3 (some relevant keywords, missing common variations/synonyms); not 4 because coverage lacks the synonyms users would naturally say.

3 / 5

Distinctiveness Conflict Risk

"GDD authoring for one system" carves a clear niche distinct from sibling skills like /design-review, /consistency-check, and /map-systems, so overlap risk is minor. Not 5: "cross-references dependencies" brushes against consistency-check territory and the description offers no explicit distinguishing triggers; not 3 because the GDD-authoring domain is specific, not broadly overlapping.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

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

Total

14

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/design-system/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.