agent-capability-analyzer

Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.

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

76%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.

Highly actionable and well-structured, with executable commands and a clear output format. Weakest on workflow validation (no verify step for the batch write+dump) and a missing referenced resource file.

Suggestions

Add an explicit validation step after the dump (e.g. assert the JSON contains an entry for every spawned agent) and a failure-recovery path for Tasks that error or return no capabilities.

Ship the missing './resources/describe-your-capabilities.template.md' referenced throughout the body, or remove the references and inline the prompt template.

De-duplicate the mermaid flowchart against the 'Single-agent mode / Multi-agent mode / Template usage' prose — keep one as the authoritative source and reference it from the other.

Dimension	Reasoning	Score
Conciseness	Largely lean and command-driven, but the mermaid flowchart and the following 'Single-agent mode / Multi-agent mode / Template usage' prose repeat the same content, and the Category 1 'Possible causes' prose could be trimmed.	4 / 5
Actionability	Fully executable copy-paste commands throughout (populate/dump/update scripts, a node -e lookup), explicit AGENT_ID_HERE substitution, and a concrete gap-analysis output template covering common cases.	5 / 5
Workflow Clarity	Sequencing is clear (numbered workflow, 'Wait for ALL Tasks to complete' gate, mermaid decision branches), but this batch operation lacks a validation/verification step confirming the dump captured all agents or error recovery for failed Tasks — the rubric caps batch ops without validation at 3.	3 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references to two existing scripts; however the repeatedly referenced './resources/describe-your-capabilities.template.md' is absent from the bundle (no resources/ directory), a real navigation gap.	4 / 5
	Total	16 / 20 Passed

Description

92%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 description: concrete actions, explicit 'Use when' triggers, and a distinctive niche. Trigger-term quality is the only slightly weaker dimension, leaning toward compound technical phrasing over everyday synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'spawns all Claude Code agents simultaneously to collect self-reported capabilities', 'compares them against static frontmatter descriptions' — with comprehensive coverage of the experiment lifecycle.	5 / 5
Completeness	Explicitly answers 'what' (spawn agents, collect capabilities, compare to frontmatter) and 'when' via a concrete 'Use when...' clause enumerating four trigger scenarios.	5 / 5
Trigger Term Quality	'measuring description drift', 're-running the capability collection experiment', 'analyzing a specific agent's self-reported capabilities' are natural trigger phrases, but coverage leans slightly compound/technical and lacks broader synonyms.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (description-drift experiment / agent-capability auditing) with distinct triggers and minimal overlap risk with general skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Jamie-BitFlight/claude_skills
Path: plugins/plugin-creator/skills/agent-capability-analyzer/SKILL.md
Commit: c337daf

Reviewed: 3 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.