CtrlK
BlogDocsLog inGet started
Tessl Logo

triage

将复合任务拆解为检索、计算、编程和写作等阶段,并选择下一个 Skill。

56

Quality

63%

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 ./chapter10/multi-role-transfer/skills/triage/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 body is a concise, well-sequenced orchestration procedure with no padding, but its actionability suffers from the absence of a concrete switch-request example and explicit validation/handoff checkpoints. Adding one worked example and labeled subsections would lift actionability and progressive_disclosure.

Suggestions

Add one short worked example showing the exact phrasing of a stage-switch request and its one-sentence reason.

Break the three paragraphs into labeled subsections (e.g., '## Process', '## Stage transitions', '## Completion') for clearer navigation.

Add an explicit verification checkpoint before declaring completion, e.g., confirm all acceptance criteria are met before giving the final answer.

DimensionReasoningScore

Conciseness

The body is lean and instruction-only with no concept padding — every line instructs behavior and assumes Claude's competence, matching the 'every token earns its place' anchor.

5 / 5

Actionability

It gives concrete process guidance (identify goals/dependencies/acceptance criteria, stage order, one-sentence switch reason) but lacks a concrete example of an actual switch request, leaving key execution details implicit.

3 / 5

Workflow Clarity

The sequence (identify goals → staged switching → one-at-a-time with stated reason → final answer) is clear with implicit checkpoints ('after each stage completes', acceptance criteria); this is not a destructive/batch skill so no cap applies, with only minor validation gaps.

4 / 5

Progressive Disclosure

As a simple under-50-line single-purpose skill with no bundle files, it is reasonably organized, though it could use explicit subsection headers instead of plain paragraphs for better navigation.

4 / 5

Total

16

/

20

Passed

Description

51%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 states concrete actions and occupies a distinct orchestration niche, but it lacks any explicit 'when to use' trigger guidance and only generic trigger terms. Adding a 'Use when...' clause with natural user phrases would raise both completeness and trigger_term_quality.

Suggestions

Append an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when a task spans multiple domains or needs staged retrieval, computation, and writing').

Add user-natural synonyms (e.g., 'multi-step tasks', 'complex tasks', 'split into stages') to improve trigger_term_quality.

Include the trigger context in the same sentence as the capability list so both 'what' and 'when' are immediately visible.

DimensionReasoningScore

Specificity

It lists several concrete actions — decomposing tasks into 'retrieval, computation, programming, writing' stages and 'selects the next Skill' — with only minor coverage gaps, matching the anchor that lists several specific actions.

4 / 5

Completeness

It gives a clear 'what' (decompose into stages and pick the next skill) but no 'Use when...' or equivalent trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It offers only a couple of generic terms ('compound tasks') with no natural trigger phrases a user would actually say, falling noticeably below the midpoint anchor for keyword coverage.

2 / 5

Distinctiveness Conflict Risk

The triage/orchestration niche (selecting and switching between specialist skills) is mostly distinct with only minor overlap risk against other meta-coordination skills.

4 / 5

Total

13

/

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
bojieli/ai-agent-book
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.