CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

content-audit

Audit GDD content counts against what's implemented — planned vs built.

Quality

70%

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/content-audit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable, well-sequenced audit workflow with strong validation and fail-open handling. Its weaknesses are repetition of the no-data rationale, which costs tokens on every invocation, and a monolithic single-file layout that inlines template and engine-variant content a references/ bundle would absorb.

Suggestions

State the NOT ASSESSED rule once (e.g. in the 'Insufficient input' section) and reference it elsewhere in one line instead of restating it in the blockquote, Phase 3, and Phase 5.

Move the full report template and the per-engine glob variants into references/ files (e.g. references/report-template.md, references/engine-scans.md) and link to them from the phases.

Trim the justification paragraphs (false-clean-pass examples, 'absence of evidence' aphorism) to a single sentence each; the rules themselves already carry the instruction.

DimensionReasoningScore

Conciseness

The instructions are mostly concrete commands, but the NOT-ASSESSED doctrine is repeated four times (top blockquote, 'Insufficient input', Phase 3, Phase 5) and includes philosophical justification ('Absence of evidence is never evidence of absence', the false-clean-pass hypothetical) that could be trimmed without losing the rule.

3 / 5

Actionability

Copy-paste-ready Grep patterns with exact regexes, per-engine Glob variants (Unreal Content/, Unity Assets/, web data/), explicit status thresholds with percentage bands, table templates, and exact user-facing prompts — fully executable and covering the common engine cases.

5 / 5

Workflow Clarity

Five clearly sequenced phases with explicit validation checkpoints (the FOUND/ABSENT input checklist before any report, the fail-open denominator check, 'stop if the check fails') and error-recovery paths (NOT ASSESSED verdicts, unresolved-code-root handling).

5 / 5

Progressive Disclosure

The single ~325-line file is well-sectioned, but everything is inlined: the full report template, per-content-type scan lists, and engine-specific glob variants are candidates for reference files, and there are no bundled references to lean on (the .claude/docs/*.md pointers are repo docs, clearly signaled but external).

3 / 5

Total

16

/

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, distinct capability but reads as a terse label rather than a full trigger description. It lacks any 'when to use' guidance and natural trigger phrases that would help both users and Claude select it.

Suggestions

Add a 'Use when...' clause, e.g. "Use when checking how much specified game content is actually implemented, comparing GDD specs to the codebase."

Include natural trigger terms and synonyms: "game design document (GDD)", "content progress", "spec vs implementation", "audit content".

Optionally enumerate the concrete outputs (gap table, HIGH PRIORITY flags, per-system breakdown) to sharpen the 'what'.

DimensionReasoningScore

Specificity

"Audit GDD content counts against what's implemented — planned vs built" names the domain and one concrete comparison action, but stops short of listing several specific actions (scan implementation, gap report, priority flags), matching the 1-2-concrete-actions anchor.

3 / 5

Completeness

The "what" is clear (audit planned vs built content counts), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Terms like "GDD", "content", "audit", "implemented" are relevant but domain-jargon-leaning; common natural variations ("game design document", "spec", "content progress", "how much is built") are missing.

3 / 5

Distinctiveness Conflict Risk

"GDD content counts" and "planned vs built" carve a fairly distinct niche unlikely to fire for unrelated skills; minor overlap risk remains with adjacent game-design tooling skills like design or systems-mapping skills.

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: 12 missing

Warning

Total

13

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/content-audit/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.