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

81%

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

81%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 tight, well-sequenced audit procedure with explicit checkpoints and a concrete output contract, and it usefully reuses an existing overlap gate rather than inventing a metric. Its main gap is reliance on external cross-references (blocks, council script, octo commands) that are not part of this skill's bundle and may be unavailable in adapted hosts.

Suggestions

Make the external cross-references resolvable: either bundle the referenced material (e.g. a short council.sh excerpt or a local overlap-gate snippet) or explicitly mark each external path as host-dependent with a fallback procedure.

Trim the aphoristic phrasings ('overhead wearing the costume of consensus', 'the burden of proof falls on the boundary') to plain statements to recover tokens without losing meaning.

Add a brief concrete example boundary-table row so the output contract is unambiguous to produce on a first pass.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, avoiding basic-concept padding, with a few aphoristic flourishes ('overhead wearing the costume of consensus') that could be trimmed. Not 5 because those flourishes cost a few tokens beyond strict necessity.	4 / 5
Actionability	Provides a concrete audit procedure: six named cost terms, four named gain terms, a specific reuse mechanism (council_persona_overlap_score via scripts/lib/council.sh with a 0.65 Jaccard threshold), and an ordered output contract. Not 5 because several referenced files/commands lie outside this skill's bundle and may not exist for the reader.	4 / 5
Workflow Clarity	A clear five-step numbered sequence (draw boundaries, name losses, name gains, compare against the single-expert null, reuse the overlap gate) is paired with explicit Stop/Checkpoint Rules and a Verification checklist with feedback checks, matching the top anchor.	5 / 5
Progressive Disclosure	The single file is well-organized into clearly headed sections with signaled cross-references, but no bundle files exist and the referenced paths point to other skills/blocks outside this skill's bundle, so it is not a clean one-level-deep split of its own detail. Not 5 for that reason; not 3 because structure and signaling are genuinely good.	4 / 5
	Total	17 / 20 Passed

Description

82%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 well-formed: it states a distinctive concrete action and pairs it with explicit, natural-language trigger conditions. Its only weakness is that it names a single audit action rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-agent setup') and one concrete action ('audit whether ... earns its coordination cost'), but does not list several distinct actions, matching the 1-2-action anchor. Not 4 because it is not a list of several specific actions.	3 / 5
Completeness	Explicitly answers both what ('Audit whether a multi-agent setup earns its coordination cost') and when ('use before adding an agent, or when a workflow feels slow or agents agree without adding signal') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say — 'adding an agent', 'workflow feels slow', 'agents agree without adding signal' — giving good keyword coverage. Not 5 because it lacks synonyms or extension-style variants of these triggers.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (multi-agent topology auditing) with distinctive triggers unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	17 / 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: 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.