dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

1.17x

Quality

48%

Does it follow best practices?

Impact

100%

1.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/dispatching-parallel-agents/SKILL.md

The canonical home for this skill is dispatching-parallel-agents in obra/superpowers

Quality

Content

56%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 well-structured and highly actionable with concrete dispatch patterns and verification steps, but it is padded with redundant when/when-not and duplicate real-example sections, and it makes no use of progressive disclosure despite its length.

Suggestions

Collapse the redundant 'Don't use when' and 'When NOT to Use' sections into one, and merge the 'Real Example from Session' and 'Real-World Impact' sections which currently duplicate each other

Move the full example agent prompt and session walkthrough into a referenced file (e.g. examples.md) to keep SKILL.md a lean overview

Specify the Task dispatch form more precisely or note it is illustrative, so the executable guidance maps to the real API

Dimension	Reasoning	Score
Conciseness	The ~175-line body is noticeably padded: when/when-not guidance is repeated across 'When to Use', 'Don't use when', and a separate 'When NOT to Use' section, and the 'Real Example from Session' and 'Real-World Impact' sections are near-duplicates.	2 / 5
Actionability	Concrete, copy-paste-ready patterns are provided (Task('...') calls and a full example agent prompt with specific test names and constraints), though the Task() form is a simplified illustration rather than the exact API shape.	4 / 5
Workflow Clarity	A clear four-step sequence (Identify → Create → Dispatch → Review) is paired with an explicit verification checklist (check conflicts, run full suite, spot check) for this batch operation, with only minor gaps in error-recovery guidance.	4 / 5
Progressive Disclosure	No bundle files exist and no external references are used; the skill is a single monolithic document over 50 lines that inlines a long example session and prompt template that could live in separate reference files.	3 / 5
	Total	13 / 20 Passed

Description

40%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 a pure trigger clause with no explicit statement of what the skill does, which caps completeness and specificity. It is reasonably distinctive but leans on technical jargon over natural user phrasing.

Suggestions

Lead with what the skill does, e.g. 'Dispatches one subagent per independent problem domain to work them in parallel'

Add natural trigger phrasing such as 'Use when the user has several unrelated failures to fix at once, or asks to run tasks in parallel / concurrently'

Keep the '2+ independent tasks without shared state' trigger but pair it with an explicit action verb so both what and when are present

Dimension	Reasoning	Score
Specificity	The description states only a trigger condition ('facing 2+ independent tasks that can be worked on without shared state or sequential dependencies') and names the domain, but no concrete capability actions are stated — the action (dispatching agents) lives in the name, not the description text.	2 / 5
Completeness	Only a 'when' clause is present; the description never states what the skill does, matching the anchor for 'only when is present without what'.	2 / 5
Trigger Term Quality	'independent tasks' is a reasonably natural phrase, but 'shared state' and 'sequential dependencies' are technical jargon, and common natural variations like 'in parallel', 'concurrent', or 'at the same time' are missing.	3 / 5
Distinctiveness Conflict Risk	The trigger '2+ independent tasks without shared state or sequential dependencies' carves a fairly specific niche with only minor overlap risk against general task-management skills.	4 / 5
	Total	11 / 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: roman01la/skills-agents
Path: skills/dispatching-parallel-agents/SKILL.md
Commit: aa6f9d3

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.