CtrlK
BlogDocsLog inGet started
Tessl Logo

dispatching-parallel-agents

当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用

47

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

67%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 a well-structured, actionable guide with concrete prompt templates, a clear four-step workflow, and explicit validation checkpoints for a batch operation. Main weaknesses are minor: duplicated 不适用 content and implicit rather than explicit error-recovery feedback loops.

Suggestions

Merge the two '不适用场景' lists (under 何时使用 and the standalone section) into one to remove redundancy.

Make the validation feedback loop explicit, e.g. 'if agents edited the same code or the full suite fails, re-dispatch a focused fix agent' so recovery is unambiguous.

Note that the ```dot block will not render as a diagram in most viewers — either flag it as a text-only decision tree or provide an inline bullet-list equivalent.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining basics Claude already knows, but the '不适用场景' content is stated twice — once as bullets under '何时使用' and again as a dedicated section — which could be consolidated, matching 'Mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Concrete guidance is strong: a copy-paste agent prompt template with specific test names, a Task() dispatch example, and good/bad prompt pairs, with only minor gaps (the Task() calls are illustrative rather than fully executable), matching 'Mostly executable guidance; concrete code or commands with minor gaps'.

4 / 5

Workflow Clarity

The four-step pattern (识别 → 创建 → 分派 → 审查与集成) is clearly sequenced and the 验证 section provides an explicit checklist (review summaries, conflict check, full test suite, spot-check), but error-recovery feedback loops ('if conflict, then...') are only implicit, matching 'Clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

No bundle files exist and the skill is appropriately self-contained; section headers are clear and content is well-placed, but the duplicated 不适用 section is a minor organization gap, matching 'Good structure; most content is appropriately placed; minor organization gaps'.

4 / 5

Total

15

/

20

Passed

Description

36%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 well-formed trigger clause that clearly signals when to use the skill, but it omits any statement of what the skill actually does, leaving the 'what' only weakly implied by the skill name. Adding the capability (dispatching/delegating to parallel agents) would lift both completeness and specificity.

Suggestions

Prepend a concrete 'what' clause, e.g. 'Delegates independent tasks to parallel agents with isolated contexts. Use when facing 2+ tasks with no shared state or sequential dependencies.'

Add natural trigger synonyms such as '并行'/'并发'/'parallel'/'concurrent' so the description matches the phrasing users actually say.

Use third-person action verbs ('Dispatches', 'Delegates') to name the capability explicitly rather than relying on the skill name.

DimensionReasoningScore

Specificity

The description names the domain ('2+ independent tasks, no shared state, no dependencies') but lists no concrete actions — it is a pure usage condition with no verb describing what the skill does, matching 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

Only the 'when' is present ('当面对...时使用') with no explicit 'what' — it never states the skill dispatches/delegates parallel agents, matching 'only when is present without what'.

2 / 5

Trigger Term Quality

It uses some natural situational terms ('独立进行', '无共享状态', '顺序依赖') a user might voice, but omits the obvious parallel/concurrent vocabulary ('并行', '并发', '委派') and common synonyms, matching 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The 'independent tasks / no shared state / no dependencies' trigger is fairly specific to parallelization, but because the capability is never named, a general delegation or orchestration skill could also satisfy this condition, matching 'Somewhat specific but could still overlap'.

3 / 5

Total

10

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
jnMetaCode/superpowers-zh
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.