skill-parallel-agents

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

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with clear, validated workflows, but it is far too verbose and monolithic — much of the command/provider/troubleshooting reference should be externalized into reference files and the inline padding trimmed.

Suggestions

Move the Command Reference, Agent Selection, Provider-Aware Routing, and Troubleshooting sections into separate reference files under references/ and link to them one level deep, keeping SKILL.md a lean overview.

Cut the ASCII art diagrams, the full welcome-message templates, and the literal expected provider-detection output; summarize detection routing as a compact table instead.

Remove or relocate time-stamped version numbers (Claude Code 2.1.9, gpt-5.6-sol, gemini-3.1-pro-preview, v4.8) out of the main body so they do not penalize conciseness and decay the skill.

Dimension	Reasoning	Score
Conciseness	The ~760-line body is padded with ASCII diagrams, full welcome-message templates, expected provider-detection output blocks, duplicated command examples, and time-stamped version numbers (e.g. "2.1.9", "gpt-5.6-sol", "v4.8"), matching the verbose/padded anchor rather than the mostly-efficient one.	1 / 3
Actionability	It provides concrete, copy-paste-ready commands throughout (e.g. "orchestrate.sh probe \"...\"", "grapple --principles security \"...\"") with flags and worked examples, satisfying the fully-executable anchor.	3 / 3
Workflow Clarity	The Double Diamond phases (probe -> grasp -> tangle -> ink) are clearly sequenced with explicit quality-gate validation (75% threshold), a preflight check, and troubleshooting feedback for gate failures, meeting the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	No bundle reference files exist and the content is a monolithic wall; command reference, provider tiers, agent selection, and troubleshooting are all inline rather than split into one-level-deep reference files, fitting the 'some structure but content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

90%

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 concise, action-oriented, and clearly answers both what the skill does and when to use it with natural trigger terms. Its only weakness is naming a single capability rather than enumerating several concrete actions.

Dimension	Reasoning	Score
Specificity	Quotes a single concrete action ("Decompose large tasks across parallel agents") with three use-contexts; names the domain and an action but does not list multiple distinct concrete actions, matching the 'names domain and some actions' anchor rather than the multiple-actions anchor.	2 / 3
Completeness	It explicitly states what the skill does ("Decompose large tasks across parallel agents") and when to use it via an explicit "use for ..." clause, satisfying both the what and the when.	3 / 3
Trigger Term Quality	"use for migrations, multi-file refactors, or batch work" supplies natural terms a user would actually say, giving good coverage of trigger phrasings.	3 / 3
Distinctiveness Conflict Risk	The "parallel agents" decomposition framing carves a clear niche; while migrations and refactors are broad, the parallel-multi-agent qualifier makes unintended triggering unlikely.	3 / 3
	Total	11 / 12 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
skill_md_line_count	SKILL.md is long (767 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-parallel-agents/SKILL.md
Commit: 9f39f0c

Reviewed: 2 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.