agent-instructions

Design, audit, and validate repository guidance across AGENTS.md, CLAUDE.md, and `.agents/skills`. Use when creating skills, tuning descriptions, or reviewing instruction sprawl and routing.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A well-architected instruction skill: lean rule-plus-reason prose, executable commands, explicit validation feedback loops, and exemplary one-level-deep progressive disclosure backed by real bundle files. Main gaps are length and hardcoded absolute paths in examples.

Suggestions

Move the handoff near-miss anecdote (the `enlistment-hand-off-near-miss` reproduction detail) into references/evaluation.md and keep only the actionable rule in SKILL.md to tighten conciseness.

Replace hardcoded `/Users/braden/Code/epicenter` paths in command examples with a placeholder like `<repo-root>` so the commands are copy-paste portable.

Consider promoting the "Compose With" and "Keep The Format Open" sections into a reference if the body is meant to stay near the 100-line practical target.

Dimension	Reasoning	Score
Conciseness	The body is dense rule-plus-reason prose that assumes Claude's competence and avoids explaining basic concepts, but at ~375 lines it exceeds its own "under 100 when practical" target and includes a lengthy empirical anecdote (the handoff near-miss) that could be trimmed or moved to a reference.	4 / 5
Actionability	It gives copy-paste-ready commands (`bun x --package skills skills init`, `ln -s ...`, audit scripts), file trees, and frontmatter examples, but several commands hardcode `/Users/braden/Code/epicenter` absolute paths, reducing portability and capping it below 5.	4 / 5
Workflow Clarity	Multiple workflows are explicitly sequenced (Create, Design with Diverge/Converge/Extract, Evaluate loop, Update) with an explicit validation feedback loop ("If the skill does not appear, fix `SKILL.md` and run the command again") and an Exit Gate checklist, matching the top anchor.	5 / 5
Progressive Disclosure	The body points to three real reference files (instruction-placement.md, evaluation.md, composition-audit.md) each with a concrete load condition, and documents real scripts (audit-skill-links.ts, run-trigger-eval.ts verified present); references are one level deep and well-signaled, matching the top anchor.	5 / 5
	Total	18 / 20 Passed

Description

83%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.

A strong, concrete description that states both capability and explicit trigger conditions in third person. It distinguishes its niche well with only minor overlap risk against adjacent skill-management skills.

Dimension	Reasoning	Score
Specificity	"Design, audit, and validate repository guidance across AGENTS.md, CLAUDE.md, and `.agents/skills`" names three concrete actions and three concrete targets, matching the "several specific actions; minor gaps" anchor rather than the fully comprehensive 5.	4 / 5
Completeness	It explicitly answers what ("Design, audit, and validate repository guidance...") and when ("Use when creating skills, tuning descriptions, or reviewing instruction sprawl and routing") with concrete trigger phrases, matching the top anchor; the explicit "Use when..." clause avoids the completeness cap.	5 / 5
Trigger Term Quality	"creating skills, tuning descriptions, reviewing instruction sprawl and routing" are natural phrases users would say, with good but not exhaustive synonym coverage, fitting the "good keyword coverage; a few natural terms missing" anchor.	4 / 5
Distinctiveness Conflict Risk	The AGENTS.md/CLAUDE.md/`.agents/skills` niche with sprawl-and-routing triggers is mostly distinct, but "creating skills" has minor overlap with related skills like skill-installer and plugin-creator, placing it just below the minimal-conflict 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/agent-instructions/SKILL.md
Commit: ecba024

Reviewed: 12 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.