CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plan-deck-spec

海岚旅行行程方案 PPT 规范(HL-MKT-SPEC-04 V4.2):格式、页序与每页内容、不得出现的内容、顾问质检清单。方案 PPT 由设计同事以店里模板制作,顾问质检通过后交付。

63

Quality

79%

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 ./experimental/simulation/scenarios/travel_agency/materials/plan-deck-spec/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exemplary instruction-only skill body: concrete, tabular, and lean, with a real validation checklist closing the loop. The only real improvement areas are moving version-history details out of the intro and making the checklist's fix-and-recheck loop explicit.

DimensionReasoningScore

Conciseness

The body is a dense, table-driven spec with no padded explanations of things Claude already knows; every line carries spec content. It falls short of 5 only because time-sensitive version history ("2026年9月25日起执行(V4.1:… V4.2:…)") is inlined in the intro rather than placed in a changelog/deprecated section, adding tokens that could be trimmed.

4 / 5

Actionability

Fully concrete, copy-ready guidance for an instruction-only skill: exact filename pattern ("海岚旅行-报价编号.pptx"), a per-page table with required contents, verbatim contact-page text, and explicit sourcing rules ("以计调确认为准", 查证事实注明来源). No abstract directions anywhere.

5 / 5

Workflow Clarity

A clear sequence (格式 → 页序与每页内容 → 不得出现 → 顾问质检清单) ends in an explicit 9-item validation checklist covering price consistency, external-info sourcing, and prohibited content. It sits at 4 rather than 5 because the error-recovery loop — what to do when a checklist item fails, and re-checking after the fix — is implied but never stated.

4 / 5

Progressive Disclosure

The body is 40 lines with no bundle directories (references/, scripts/, assets/ do not exist) and four well-organized sections; referenced external documents (HL-MKT-GUIDE-07, HL-MKT-TPL-08) are org-level specs, not nested skill files. Per the simple-skill note, well-organized sections with no need for external references score 5.

5 / 5

Total

18

/

20

Passed

Description

62%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 clearly and distinctively identifies a well-scoped internal specification, listing its concrete components, but it lacks any explicit trigger guidance for when Claude should load the skill. Adding a 'when to use' clause with natural trigger phrasings would complete it.

Suggestions

Add an explicit trigger clause, e.g. "制作或质检行程方案 PPT(报价方案 .pptx)时使用" — this would lift completeness and trigger term quality.

Include natural user-side synonyms such as 报价方案, 报价单, 演示文稿, and the .pptx extension to broaden trigger coverage.

State the action Claude performs with the spec (e.g., review/QC the proposal PPT against it), not just what the document contains.

DimensionReasoningScore

Specificity

Lists four concrete content areas ("格式、页序与每页内容、不得出现的内容、顾问质检清单") plus the delivery workflow, matching the 'several specific items, minor gaps' anchor. It stops short of 5 because it never states the action Claude itself performs (e.g., checking a proposal PPT against the spec).

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the delivery note ("顾问质检通过后交付") only weakly implies the usage context. Per the guideline, missing trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords like "行程方案 PPT" and "质检" are present, but natural variations a user would say ("报价方案", "演示文稿", ".pptx") are missing. This fits the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor at 4.

3 / 5

Distinctiveness Conflict Risk

Scoped to a named niche with a unique document identifier ("海岚旅行行程方案 PPT 规范(HL-MKT-SPEC-04 V4.2)"), giving it a clear trigger territory with minimal overlap risk with any generic skill.

5 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

EverMind-AI/Raven

Path

experimental/simulation/scenarios/travel_agency/materials/plan-deck-spec/SKILL.md

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.