skill-agent-topology

Audit whether a multi-agent setup earns its coordination cost — use before adding an agent, or when a workflow feels slow or agents agree without adding signal

Quality

82%

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

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.

The body is a well-structured, actionable diagnostic workflow with strong checkpoints and verification, written concisely. Its main weakness is several inline references to bundle files that do not exist in this skill's bundle.

Suggestions

Resolve or remove references to files outside the bundle (scripts/lib/council.sh, skills/blocks/frontier-model-routing.md, skill-intent-contract, skill-decision-support), or add them to the references/ directory so the body's citations are verifiable.

Trim the occasional rhetorical flourishes (e.g., 'overhead wearing the costume of consensus') for tighter token efficiency.

Consider moving the cited research framing (Liu 2026, effect-size caveat) into a one-level-deep reference file to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Lean, efficient prose that assumes competence and avoids explaining basics; a few rhetorical flourishes ('overhead wearing the costume of consensus') could be trimmed, so not a 5.	4 / 5
Actionability	Concrete, specific guidance—enumerate boundaries, name cost/gain terms, compare to the single-expert null, and reuse council_persona_overlap_score with a concrete 0.65 threshold and script path; no literal code, but the skill is instruction-only so that is acceptable.	4 / 5
Workflow Clarity	A numbered 5-step workflow with explicit Stop/Checkpoint rules, a verification section, and feedback loops ('If the table shows no earned boundary and the verdict is keep as is, one of the two is wrong').	5 / 5
Progressive Disclosure	Sections are well organized, but references to scripts/lib/council.sh, skills/blocks/frontier-model-routing.md, skill-intent-contract, and skill-decision-support point outside the bundle, which has no references/, scripts/, or assets/ directories; references are present but not verifiable against the bundle.	3 / 5
	Total	16 / 20 Passed

Description

87%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 concrete, third-person, and answers both what and when with natural trigger phrases. It is distinctive and well-scoped to multi-agent coordination audits.

Dimension	Reasoning	Score
Specificity	Names the concrete audit action ('Audit whether a multi-agent setup earns its coordination cost') plus several specific trigger scenarios; not a 5 because it states one audit action rather than a list of multiple distinct operations.	4 / 5
Completeness	Explicitly answers both what (audit coordination cost) and when (use before adding an agent, or when a workflow feels slow or agents agree) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('before adding an agent', 'a workflow feels slow', 'agents agree without adding signal'); good coverage with a few synonyms/variations missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (multi-agent topology audits) with distinct triggers and minimal conflict risk, written in third person ('Audit whether...').	5 / 5
	Total	18 / 20 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
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-agent-topology/SKILL.md
Commit: 0093dab

Reviewed: 5 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.