grug-brained-dev

Use when reviewing PRs, simplifying over-engineered code, judging architecture, or renaming unclear concepts — inline fake helpers, delete meatless ceremony, rename lying names, merge over-split files, reject premature abstraction, say no to speculative config/modes/layers, then end with the smallest safe next change. Triggers when code is too fancy, too abstract, too clever, too many files/helpers/layers, or too well-factored but painful to change. Embody Grug brain: complexity very bad, small words, no consultant speak, no hard pivot to opposite dogma.

1.65x

Quality

88%

Does it follow best practices?

Impact

81%

1.65x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear review workflow and concrete output template, but it is verbose for the token budget and monolithic with no progressive disclosure into reference files. Weakest on conciseness and progressive disclosure.

Suggestions

Trim the persona narrative and intentional repetition (e.g. the "Complexity bad/very bad/very, very bad" cadence and the opening fire/pager story) to reduce tokens while keeping the voice in the actionable sections.

Split the long reference catalogs (squint-at names, demon-clothes list, good/bad cut-point criteria) into a references file linked from a concise overview, enabling one-level-deep progressive disclosure.

Consider moving the "What Grug hunts" detail catalog behind a signaled reference so SKILL.md stays a lean overview pointing to deeper material.

Dimension	Reasoning	Score
Conciseness	The actionable lists and verdicts are lean, but the extended persona narrative ("Grug remember", fire/back/pager prose) and deliberate repetition ("Complexity bad. Complexity very bad. Complexity very, very bad.") add tokens that could be tightened without losing function, so it sits at the mostly-efficient anchor rather than lean.	2 / 3
Actionability	Concrete verdict examples ("This helper fake. It hide one line. Inline.", "Name lie. Code updates issues, not tracker. Rename folder issues/."), explicit good/bad cut-point and helper-earning criteria, and a copy-paste output template give fully executable, specific guidance.	3 / 3
Workflow Clarity	A clear review sequence is laid out (become Grug → first questions → hunt → judge → report in fixed sections → next bonk) with explicit checkpoints such as "what check proves still works", "Run tests", and "Code still work after bonk", and a concrete stop point.	3 / 3
Progressive Disclosure	It is a single ~555-line file with no bundle references and no signaled navigation to deeper material; section headers organize it well (not a monolithic wall), but content that could be split (name lists, demon-clothes catalog, persona narrative) is inline, fitting the some-structure anchor rather than a 3.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 specific, trigger-rich, and fully answers what and when in third-person imperative voice. It is a strong, distinctive skill description with no obvious weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "inline fake helpers, delete meatless ceremony, rename lying names, merge over-split files, reject premature abstraction, say no to speculative config/modes/layers" — matching the score-3 anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the inline/delete/rename/merge/reject actions) and when via two explicit trigger clauses ("Use when reviewing PRs..." and "Triggers when code is too fancy..."), satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Natural user phrases are well covered: "reviewing PRs, simplifying over-engineered code, judging architecture, renaming unclear concepts" plus "code is too fancy, too abstract, too clever, too many files/helpers/layers" — terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The Grug-brained simplification niche with its distinctive triggers (over-engineered/too-clever/too-many-files code) is unlikely to collide with other skills, matching the clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (561 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: joshuadavidthomas/agent-skills
Path: grug-brained-dev/SKILL.md
Commit: 516dee7

Reviewed: 11 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.