CtrlK
BlogDocsLog inGet started
Tessl Logo

ralph-wiggum-v2

Autonomous TDD development loop with parallel agent swarm, category evolution, and convergence detection. Use when running autonomous game development, quality improvement loops, or comprehensive codebase reviews.

62

Quality

73%

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/ralph-wiggum-v2/SKILL.md

The canonical home for this skill is ralph-wiggum-v2 in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

58%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 skill has excellent workflow clarity with explicit validation and feedback loops, and offers concrete schemas and commands for actionability. Its weaknesses are verbosity and poor progressive disclosure: large reference catalogues are inlined rather than split into separate referenced files.

Suggestions

Move the Review Styles catalog and Game-Specific Categories mappings into separate reference files (e.g. references/review-styles.md, references/game-categories.md) and link to them from SKILL.md to improve progressive disclosure and conciseness.

Externalize the full state/categories/agent-output JSON schemas into a references file, keeping only a minimal example inline, to reduce token load on the main skill.

Add a couple of executable code snippets (e.g. a concrete Task-tool spawn example and a state-file read/write snippet) to lift actionability from mostly-executable to fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body inlines large reference catalogues (40+ review styles, game-specific category mappings, full schemas) that pad the file and would be tighter if externalized, though it does avoid explaining basic concepts.

2 / 5

Actionability

Provides concrete schemas (state.json, categories.json, agent output format), an explicit quick-start command, and a sequenced iteration loop, though it relies on JSON specs and steps rather than copy-paste runnable code.

4 / 5

Workflow Clarity

The multi-step loop is clearly sequenced with explicit validation checkpoints (all tests passing, no critical/major findings), feedback on failure, and a final verification checklist, satisfying the batch/feedback-loop requirement.

5 / 5

Progressive Disclosure

No bundle files exist and the body references none; large reference material (review styles, game categories, detailed schemas) that belongs in separate files is inlined into one monolithic document.

2 / 5

Total

13

/

20

Passed

Description

88%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 is strong: it concisely states concrete capabilities and includes an explicit 'Use when...' trigger clause covering the main use cases. Trigger term coverage is good but could add more synonyms and file extensions to fully distinguish from generic review skills.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete mechanisms ('parallel agent swarm, category evolution, and convergence detection'), giving comprehensive coverage of capabilities within its niche.

5 / 5

Completeness

Explicitly states both what it does (the TDD loop with swarm/evolution/convergence) and when to use it via a concrete 'Use when...' clause with trigger phrases.

5 / 5

Trigger Term Quality

Provides natural user-facing phrases ('autonomous game development, quality improvement loops, or comprehensive codebase reviews') with good coverage, but misses some synonyms and file/extension variations.

4 / 5

Distinctiveness Conflict Risk

The agent-swarm/convergence niche is fairly distinct, but 'quality improvement loops' and 'comprehensive codebase reviews' overlap with general code-review skills, giving minor conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fernandezbaptiste/Skrillz
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.