sn-report-format-discovery

用于用户希望推荐研究成品形式，或最终形式无法从需求中直接判断时。把需求解析为一个简短的 format 字符串，不创建格式文件或 schema。

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-report-format-discovery/SKILL.md

Quality

Content

92%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 concise, well-structured, and gives a clear actionable decision procedure with a precise output format. Only minor gap is the absence of a worked input→output example to make guidance fully copy-ready.

Suggestions

Add one short worked example mapping a sample query to the expected one-line 'format: ...' output to make the guidance fully copy-ready.

Optionally clarify how the chosen format relates back to the request context (e.g., confirm it is passed alongside language and not persisted).

Dimension	Reasoning	Score
Conciseness	Lean body with three short sections (输入/规则/输出); no padding or explanations of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	Concrete, actionable rules (priority order, default 'report', listed common values, explicit non-actions) and a precise one-line output spec, though a worked input→output example would make it fully copy-ready.	4 / 5
Workflow Clarity	Single-purpose skill with an unambiguous priority-ordered decision procedure (user-specified → inferred → 'report'); no destructive/batch operation, so the simple-skill exception applies.	5 / 5
Progressive Disclosure	Under 50 lines, single task, no external references needed; content is well-organized into clear sections, satisfying the simple-skill exception for a top score.	5 / 5
	Total	19 / 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 conveys both what the skill does and when to use it, with reasonable distinctiveness. It would benefit from more concrete trigger phrasing and broader keyword coverage to raise completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause with concrete user-phrased triggers (e.g., 'Use when the user asks for a report, paper, table, memo, or is unsure what form the research output should take').

List a few natural synonyms or example phrasings users might say to broaden trigger term coverage.

Sharpen the 'what' with a compact enumeration of concrete actions (parse query → infer form → emit one-line format string).

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('把需求解析为一个简短的 format 字符串') plus an explicit non-action (no schema/file creation), but does not list several specific actions.	3 / 5
Completeness	Clearly states both the 'what' (parse requirement into a short format string, create no files/schema) and an explicit 'when' clause, though the trigger phrasing could be more concrete.	4 / 5
Trigger Term Quality	Provides relevant trigger language ('用户希望推荐研究成品形式', '最终形式无法从需求中直接判断时'), but lacks common synonym or extension variations users might say.	3 / 5
Distinctiveness Conflict Risk	Targets a narrow niche (recommending a research deliverable format string) with mostly distinct triggers; only minor overlap risk with related research skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: OpenSenseNova/SenseNova-Skills
Path: skills/sn-report-format-discovery/SKILL.md
Commit: 5b4cb5b

Reviewed: 8 hours ago

Table of Contents

Discovery Implementation Validation

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.