sn-report-format-discovery

用于研究任务的最终呈现形式未知时。比较研究报告、学术论文、表格优先报表、决策备忘录或自定义形式，并用权威标准与真实范例支持推荐。

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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 skill body is operationally rich, with concrete search queries, a structural validation protocol, explicit exit conditions, and a complete output schema. Its weaknesses are moderate redundancy in the principles/boundary sections and a monolithic structure that inlines reference-like content instead of splitting it into linked files.

Suggestions

Trim redundancy in 核心原则 (principles 4–6 restate the container/form/paradigm orthogonality already covered in 呈现形式判断) and 职责边界 to reduce token load.

Move the 锚点注册表 and the full JSON output examples into reference files (e.g., anchors.md, format_proposal.schema.json) and link to them from the body, so the long anchor/schemas content loads only when needed.

Tighten the workflow steps from descriptive prose toward command-level instructions (e.g., exact verification commands or script invocations) to lift workflow clarity toward the explicit-checklist anchor.

Dimension	Reasoning	Score
Conciseness	The body is dense and prescriptive with no padding about concepts Claude already knows, but 核心原则 (principles 4–6 restate container/form/paradigm orthogonality) and 职责边界 overlap earlier statements, so it could be tightened past the 'mostly efficient' anchor.	3 / 5
Actionability	Highly actionable: copy-paste search strings ('site:equator-network.org {report_type} reporting guideline'), structural detection rules for is_primary_source (count heading levels, match '10.xxxx/', URL path checks), and a fully specified JSON output schema; minor gaps (e.g., no executable script for signal detection) keep it at 4 rather than 5.	4 / 5
Workflow Clarity	A clear 6-step workflow with an explicit validation checkpoint (步骤 4: 验证 is_primary_source), a feedback loop (验证失败处理 → discard and continue), and concrete exit conditions (≥3 verified sources, 8-round budget); the steps are descriptive rather than command-level, which holds it at 4 instead of 5.	4 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, but at ~360 lines it is monolithic — no bundle/reference files exist, and substantial reference-like material (the full 锚点注册表 and two complete JSON schemas) is inlined rather than split into one-level-deep reference files.	3 / 5
	Total	14 / 20 Passed

Description

70%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 states a specific niche and supplies an explicit use-condition plus concrete candidate format names. It is strong on distinctiveness and trigger coverage, but the 'when' is an abstract condition rather than natural user phrasing, and the action list is slightly under-comprehensive.

Suggestions

Add natural-language trigger phrases a user would actually say (e.g., '该用研究报告还是论文交付' / '不确定最终呈现形式') alongside the abstract '最终呈现形式未知时' condition.

Name one or two more concrete actions the skill performs — e.g., '提取 defining features 并写出 format_proposal.json' — to lift specificity above the two-action anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('呈现形式') and two concrete actions — '比较研究报告、学术论文、表格优先报表、决策备忘录或自定义形式' and '用权威标准与真实范例支持推荐' — but does not enumerate the fuller set of actions the skill performs (extracting defining features, writing format_proposal.json), so it sits at the 1-2-actions anchor rather than 4.	3 / 5
Completeness	Both 'what' (compare formats and support recommendation with standards/examples) and 'when' ('用于研究任务的最终呈现形式未知时') are present and explicit; the 'when' is a condition rather than a concrete user utterance, so it does not reach the explicit-trigger-phrase anchor of 5.	4 / 5
Trigger Term Quality	Good keyword coverage via concrete format names ('研究报告、学术论文、表格优先报表、决策备忘录') that users would naturally say; the trigger condition '最终呈现形式未知时' is somewhat abstract, keeping it just below the comprehensive-synonym anchor of 5.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and specific (research-deliverable format discovery with named candidate formats), giving minimal conflict risk with adjacent research skills; it stops at 4 because 'research task' framing could mildly overlap with general research/planning skills.	4 / 5
	Total	15 / 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: 61b60bb

Reviewed: 8 days 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.