dispatching-parallel-agents

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

Quality

57%

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 ./eval/local/skills/benchmarks/dependency/superpowers/dispatching-parallel-agents/SKILL.md

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

Quality

Content

75%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 concrete templates and a worked example, and the workflow is clearly sequenced with a verification checklist. Its main weakness is redundancy across several sections and a stray time-sensitive date that bloats the token budget.

Suggestions

Merge the duplicated sections: collapse 'When NOT to Use' into 'Don't use when', fold 'Verification' into pattern step 4, and remove 'Real-World Impact' since it restates 'Real Example from Session'.

Remove or relocate the hard-coded date '2025-10-03' (and the session-specific framing) so the example stays evergreen.

Dimension	Reasoning	Score
Conciseness	The core guidance is mostly efficient and does not belabor beginner concepts, but three section pairs are redundant ('Don't use when' vs 'When NOT to Use', 'Review and Integrate' vs 'Verification', 'Real Example from Session' vs 'Real-World Impact') and a time-sensitive date ('2025-10-03') sits outside any deprecated section, fitting 'mostly efficient but could be tightened'; not 2 because the actionable material genuinely earns its place.	3 / 5
Actionability	It provides a copy-paste-ready agent prompt template with specific test names and instructions, concrete dispatch examples, and paired ❌/✅ do-and-don't illustrations covering the common cases, matching 'fully executable; copy-paste ready; specific examples cover the common cases'.	5 / 5
Workflow Clarity	'The Pattern' lays out a clear 4-step numbered sequence and a dedicated 'Verification' checklist (review summaries, check conflicts, run full suite, spot check); not 5 because the error-recovery feedback loop ('if fixes conflict or suite fails, then...') is implied rather than explicitly spelled out.	4 / 5
Progressive Disclosure	The body is well-sectioned with clear headers and logical flow, and inline content is appropriate for a procedural pattern skill with no bundle files present; not 5 because it is a single ~180-line file with no one-level-deep references to split out the bulky worked example or prompt template.	4 / 5
	Total	16 / 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 statement of capability: it tells Claude when to invoke the skill but not what the skill does. It is reasonably distinct but underspecified on both actions and natural trigger terms.

Suggestions

Add a 'what' clause naming the concrete action, e.g. 'Dispatches parallel subagents, one per independent task domain, so they investigate concurrently.'

Replace technical jargon ('shared state', 'sequential dependencies') with natural user phrases like 'parallel tasks', 'concurrent agents', or 'multiple unrelated problems'.

Lead with the capability before the trigger so the description answers both 'what' and 'when' in one line.

Dimension	Reasoning	Score
Specificity	The description names the domain ('2+ independent tasks', 'without shared state or sequential dependencies') but states zero concrete capabilities — it never says what the skill does (e.g. dispatch agents, run tasks in parallel), matching the 'names the domain but actions are minimal or generic' anchor rather than the entirely-vague score 1.	2 / 5
Completeness	It provides an explicit 'when' ('Use when facing 2+ independent tasks...') but no 'what' — it never describes what the skill does, exactly matching the 'only when is present without what' anchor; not 3 because that anchor requires a clear 'what', which is entirely missing.	2 / 5
Trigger Term Quality	It contains a relevant keyword ('independent tasks') but leans on technical jargon ('shared state', 'sequential dependencies') and omits the natural phrases users would say ('parallel', 'agents', 'dispatch', 'concurrent'), fitting 'some relevant keywords but missing common variations or synonyms'; not a 4 because the core natural trigger terms are absent.	3 / 5
Distinctiveness Conflict Risk	The precise conditions ('2+ independent tasks', 'no shared state', 'no sequential dependencies') carve a fairly distinct parallel-dispatch niche with only minor overlap risk against general delegation/subagent skills; not 5 because it never names 'agents' or 'parallel' explicitly, which weakens trigger distinctiveness.	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: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/superpowers/dispatching-parallel-agents/SKILL.md
Commit: 2ff42ff

Reviewed: 1 day 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.