skill-parallel-agents

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

Quality

64%

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 ./skills/skill-parallel-agents/SKILL.md

Quality

Content

53%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 highly actionable with extensive copy-paste commands and clear high-level sequencing, but it is padded with redundant compliance and setup text, lacks validation feedback loops for batch operations, and inlines content that should be split into reference files that do not exist.

Suggestions

Collapse the 'MANDATORY COMPLIANCE' block and the duplicated provider-setup/welcome text into a single concise statement to cut the most visible padding.

Add an explicit validate->fix->retry feedback loop for the tangle quality gate and batch operations so workflow_clarity can rise above the batch-operation cap of 3.

Move the command reference, provider config YAML, and agent-selection tables into separate reference files under references/ (and create the missing skills/blocks/codex-host-adapter.md) so SKILL.md becomes a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The ~775-line body has noticeably verbose, padded sections: the 'MANDATORY COMPLIANCE' block restates the same prohibition four ways, provider setup/welcome text is duplicated across the first-time message and Scenarios A/B, cost-awareness tables appear twice, and full detect-providers expected output is reproduced verbatim. This fits the 'noticeably verbose; several unnecessary explanations or padded sections' anchor rather than the more efficient 3.	2 / 5
Actionability	It is packed with copy-paste-ready commands (orchestrate.sh probe/grasp/tangle/ink/embrace/grapple/squeeze/auto with concrete prompts), full command-reference and options tables, and a complete YAML providers config example, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	The Double Diamond phases and prerequisites scenario routing are clearly sequenced with a tangle quality gate, but this is a batch/parallel-orchestration skill and the rubric caps workflow_clarity at 3 when batch operations lack explicit validate->fix->retry feedback loops; the quality-gate failure handling and graceful-degradation paths omit concrete recovery checkpoints.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent) and everything is inlined into one monolithic file — full command reference, provider config, agent selection, and troubleshooting that clearly belong in separate files — while the only markdown reference (skills/blocks/codex-host-adapter.md) is dangling/not in the bundle, fitting the 'content that clearly belongs in separate files is inlined' anchor.	2 / 5
	Total	12 / 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.

The description is concise, third-person, and clearly answers both what the skill does and when to use it, with concrete trigger terms. It is solid but stops just short of the fully comprehensive top anchor on coverage and trigger synonym breadth.

Dimension	Reasoning	Score
Specificity	Names the domain ('Decompose large tasks across parallel agents') plus several concrete use cases ('migrations, multi-file refactors, or batch work'), giving multiple specific actions with only minor coverage gaps, matching the anchor for 'several specific actions; minor gaps'.	4 / 5
Completeness	Explicit 'what' ('Decompose large tasks across parallel agents') and explicit 'when' ('use for migrations, multi-file refactors, or batch work') are both present and concrete; the 'when' trigger list is specific but could be fuller, matching the 'both what and when; when could be more explicit' anchor rather than the fully comprehensive 5.	4 / 5
Trigger Term Quality	Natural terms users would say ('migrations', 'multi-file refactors', 'batch work') are present with good coverage, though a few common synonyms or variations are missing, fitting the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The parallel-agent decomposition framing is a fairly distinct niche with clear triggers, but 'batch work' and 'multi-file refactors' could overlap with general coding/refactor skills, giving minor overlap risk consistent with the 'mostly distinct; minor overlap' anchor.	4 / 5
	Total	16 / 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
skill_md_line_count	SKILL.md is long (781 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/skill-parallel-agents/SKILL.md
Commit: 242e51d

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.