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

60

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The content has a clear, well-validated workflow and clean single-file organization, but is padded with redundant sections and a dated log, and its dispatch examples are illustrative rather than executable. Trimming redundancy and grounding examples in real invocation syntax would raise the weaker dimensions.

Suggestions

Consolidate the overlapping When to Use / When NOT to Use / Common Mistakes / Verification sections and remove the dated session log to reduce redundancy.

Replace the illustrative dispatch text blocks with a concrete, copy-pasteable invocation example matching the actual subagent tool syntax.

Tighten the Real Example and Real-World Impact sections, which largely restate the Key Benefits.

DimensionReasoningScore

Conciseness

The body is efficient in places but carries redundant sections (When to Use / When NOT to Use / Common Mistakes / Verification overlap) and a dated session log, so it could be tightened to respect token budget.

2 / 3

Actionability

It gives concrete agent-prompt examples and do/don't contrasts, but the dispatch blocks are illustrative text rather than executable commands tied to a real invocation syntax, leaving key details implied.

2 / 3

Workflow Clarity

A clear 4-step sequence (Identify → Create → Dispatch → Review) with a decision flowchart and explicit verification checkpoints (review summaries, check conflicts, run full suite, spot check).

3 / 3

Progressive Disclosure

A single self-contained file with cleanly organized sections and no nested references; with no bundle files needed, the one-level structure is appropriate.

3 / 3

Total

10

/

12

Passed

Description

72%

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 has a strong, natural trigger clause and a distinct niche, but it omits an explicit capability statement, leaving the "what" only implied by the skill name. Adding a concrete action clause would lift completeness and specificity.

Suggestions

Lead with a concrete capability clause, e.g. "Dispatches parallel subagents for independent tasks" before the "Use when" trigger so the description states both what and when.

Add a few natural trigger variations ("parallel tasks", "concurrent investigations", "multiple unrelated failures") to broaden keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain ("independent tasks", "without shared state or sequential dependencies") but states triggering conditions rather than concrete actions the skill performs, so it is not a comprehensive capability list.

2 / 3

Completeness

It has an explicit "when" trigger but no explicit statement of what the skill does — the capability is only implied by the skill name rather than stated in the description.

2 / 3

Trigger Term Quality

"Use when facing 2+ independent tasks" uses natural phrasing a user would actually say ("independent tasks", "parallel"), giving good coverage of likely trigger language.

3 / 3

Distinctiveness Conflict Risk

The niche is clear (dispatching parallel agents for independent, stateless tasks) and the triggers are specific enough to be unlikely to fire for unrelated skills.

3 / 3

Total

10

/

12

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.