skill-parallel-agents

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-parallel-agents/SKILL.md

Quality

Content

71%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-sequenced with real validation checkpoints, but the body is verbose and monolithic for a skill this size. Splitting reference material into bundled files and trimming diagrams and compliance prose would materially improve it.

Suggestions

Move the Command Reference, Agent Selection, Provider-Aware Routing, and provider-tier/config tables into separate reference files under references/ and link to them from a concise overview, reducing the inline token load.

Remove or shrink the ASCII-art diagrams (Double Diamond, grapple) and the "MANDATORY COMPLIANCE / DO NOT SKIP" prose; keep the imperative routing rule as a single concise line.

De-duplicate the when-not-to-use guidance, which already appears in the frontmatter trigger field, and tighten the "Note for Claude Code users" block into one line.

Dimension	Reasoning	Score
Conciseness	Mostly actionable reference content, but padded with large ASCII-art diagrams, a heavy "MANDATORY COMPLIANCE" rant, a conversational "Note for Claude Code users" block, and a when-not-to-use list that duplicates the frontmatter trigger.	3 / 5
Actionability	Provides many copy-paste-ready bash commands with full paths and arguments across probe/grasp/tangle/ink/embrace/grapple/squeeze/auto, plus tables of options, agents, and routing flags covering the common cases.	5 / 5
Workflow Clarity	The Double Diamond sequence is clearly ordered with explicit validation (prerequisites detect-providers with stop conditions, quality-gate thresholds, preflight); the main flow lacks an explicit fix-and-retry loop, which is relegated to a separate troubleshooting section.	4 / 5
Progressive Disclosure	Well-sectioned with clear headers, but it is a monolithic 674-line file with no bundle/reference files and no cross-file links, so command reference, provider tiers, and agent selection that belong in separate files are inlined.	3 / 5
	Total	15 / 20 Passed

Description

75%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 concise, specific description that clearly conveys both capability and triggering use cases, using appropriate third-person voice. It is just short of the top anchor because the "when" clause lists task categories rather than natural user-mention trigger phrases.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Decompose large tasks across parallel agents") and several specific use cases ("migrations, multi-file refactors, or batch work"), with only minor coverage gaps.	4 / 5
Completeness	Explicitly states both what ("Decompose large tasks across parallel agents") and when ("use for migrations, multi-file refactors, or batch work"), with the "when" being concrete but task-type rather than user-utterance style.	4 / 5
Trigger Term Quality	Includes natural terms users would say ("migrations", "multi-file refactors", "batch work", "parallel agents"); a few common synonyms or phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (parallel multi-agent decomposition) with specific triggers; minor overlap risk with general refactor or migration skills.	4 / 5
	Total	16 / 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
skill_md_line_count	SKILL.md is long (675 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-parallel-agents/SKILL.md
Commit: 805d58c

Reviewed: 22 hours 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.