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

49

Quality

54%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/dispatching-parallel-agents/SKILL.md

The canonical home for this skill is dispatching-parallel-agents in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 delivers concrete, actionable guidance — a usable prompt template, a decision tree, and clear sequencing with verification — but is held back by significant duplication of the same worked example across multiple sections and a stray time-sensitive date. Structure is good for a single-file skill, though trimming would improve it.

Suggestions

Collapse 'Real Example from Session' and 'Real-World Impact' into one section; the 3-file abort/batch/approval example is already shown under 'The Pattern' and need not be repeated twice more.

Remove or generalize the hardcoded date '2025-10-03' (and the frontmatter date_added) since time-sensitive specifics penalize conciseness when not in a deprecated/old-patterns section.

Fix the malformed graphviz fence (```dot) so the decision tree renders, and consider replacing it with a short bulleted decision list to save tokens.

DimensionReasoningScore

Conciseness

The same 3-file example (agent-tool-abort / batch-completion / tool-approval-race-conditions) is restated across "The Pattern", "Real Example from Session", and "Real-World Impact", and a time-sensitive date ("2025-10-03") sits outside any deprecated section, matching anchor 2 for noticeable verbosity with several padded sections.

2 / 5

Actionability

It provides a copy-pasteable agent prompt template, concrete Task("...") dispatch calls, a decision tree, and specific do/don't pairs; the Task calls are illustrative rather than literal executable code and the graphviz fence is malformed, leaving minor gaps consistent with anchor 4.

4 / 5

Workflow Clarity

A clear 4-step sequence (Identify domains, Create tasks, Dispatch, Review/integrate) is paired with a Verification section containing checkpoints; validation is present so the batch-operation cap at 3 does not apply, but it is not framed as an explicit validate-fix-retry loop, matching anchor 4.

4 / 5

Progressive Disclosure

No bundle files exist, so this is scored on structure: the body is one well-sectioned file with clear headers and no nested references, but at over 50 lines with some redundant sections it has minor organization gaps, matching anchor 4.

4 / 5

Total

14

/

20

Passed

Description

48%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 has an explicit, specific trigger ("Use when facing 2+ independent tasks...") which is its main strength, but it never states what the skill actually does, relying on the skill name to convey the action. Trigger keyword coverage is decent but misses common natural synonyms.

Suggestions

Add an explicit 'what' clause naming the concrete action, e.g. 'Dispatch one subagent per independent problem domain so they work concurrently' before the 'Use when' trigger.

Broaden trigger terms with natural synonyms users actually say: 'parallel tasks', 'concurrent agents', 'fan out', 'multiple independent failures'.

Tighten the trigger so it reads as both what and when: 'Dispatches one parallel agent per independent problem domain. Use when facing 2+ independent failures (different test files or subsystems) with no shared state.'

DimensionReasoningScore

Specificity

The description states the scenario ("2+ independent tasks that can be worked on without shared state or sequential dependencies") but names no concrete actions the skill performs, matching anchor 2 where the domain is named but actions are minimal.

2 / 5

Completeness

It gives a specific, explicit "when" clause but no explicit "what" action in the description text (the action is only implied by the skill name, which per the judging guidelines must not be inferred), placing it between anchor 2 and a fully-specified example.

3 / 5

Trigger Term Quality

It opens with an explicit "Use when" and includes "independent tasks" and "shared state," but omits common natural synonyms users would say such as "parallel," "concurrent," "fan out," or "multiple agents," matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

The niche of dispatching parallel agents for independent tasks without shared state is mostly distinct with only minor overlap risk against closely related orchestration skills, matching anchor 4.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.