CtrlK
BlogDocsLog inGet started
Tessl Logo

dispatching-parallel-agents

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

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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 content is a well-structured, actionable guide with concrete agent-prompt examples and a clear multi-step workflow backed by an explicit verification section. It is efficient and appropriately organized, with only minor redundancy and the dispatch syntax being illustrative rather than executable.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete examples and no padding about concepts Claude already knows; minor redundancy between 'When to Use', 'When NOT to Use', and 'Common Mistakes' sections could be trimmed.

4 / 5

Actionability

It provides copy-paste-ready agent prompts with specific test names and concrete dispatch examples, but the 'Subagent (general-purpose): ...' dispatch syntax is illustrative rather than a literally executable command.

4 / 5

Workflow Clarity

A clear four-step sequence (identify domains, create tasks, dispatch, review) is paired with a verification section containing explicit checkpoints (check conflicts, run full suite, spot check), though validation lives in a separate section rather than inline in the main flow.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is well-organized with clear section headers; at ~160 lines all content is inline with good structure, though the detailed real-session example could arguably live in a reference file.

4 / 5

Total

16

/

20

Passed

Description

28%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 essentially a trigger clause with no statement of what the skill actually does, which caps both specificity and completeness. Trigger terms lean technical rather than natural, and distinctiveness is moderate because the niche is identifiable but the capability is unstated.

Suggestions

Lead with the concrete capability before the trigger, e.g. 'Dispatches multiple specialized agents to work independent problems in parallel. Use when facing 2+ independent tasks with no shared state or sequential dependencies.'

Add natural trigger phrases users would actually say ('multiple unrelated failures', 'run these in parallel', 'concurrent tasks') alongside the technical terms.

Include synonyms and concrete verbs (dispatch, fan out, parallelize) to improve both specificity and distinctiveness.

DimensionReasoningScore

Specificity

The description only names the domain ('2+ independent tasks that can be worked on without shared state or sequential dependencies') and gives no concrete actions, mirroring the score-2 anchor where the domain is named but actions are minimal or generic.

2 / 5

Completeness

It provides a clear 'when' ('Use when facing 2+ independent tasks...') but entirely omits the 'what' — it never says the skill dispatches parallel agents — matching the score-2 anchor where only 'when' is present without 'what'.

2 / 5

Trigger Term Quality

'independent tasks' and 'parallel' are somewhat relevant, but 'shared state' and 'sequential dependencies' are technical jargon rather than natural user phrasing, missing common variations like 'run in parallel' or 'concurrent'.

2 / 5

Distinctiveness Conflict Risk

The trigger condition (independent parallel tasks with no shared state) is somewhat specific and niche, but the absence of any stated capability makes it hard to distinguish cleanly from general parallel-execution or task-management skills.

3 / 5

Total

9

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
obra/superpowers
Reviewed

Table of Contents

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.