research-report

将deep调研结果汇总为markdown报告，覆盖所有字段，跳过不确定值。

Quality

50%

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/research-zh/research-report/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body gives a well-sequenced, mostly lean workflow with concrete commands, but the core script is specified by requirements rather than provided as executable code and the batch operation lacks a validation/verification step. Both gaps cap the highest-weighted dimensions at 2.

Suggestions

Add a validation/verification step after Step 4: confirm the script exits cleanly and that report.md contains every item from output_dir, re-running or fixing on failure — this batch operation needs a feedback loop.

Provide generate_report.py as an executable, copy-paste-ready script (or a bundled scripts/ file) rather than only as a list of requirements, so the core logic is concrete instead of specified.

Tighten or externalize the hardcoded CATEGORY_MAPPING and formatting rules — either move them to a reference file under references/ or note that the mapping should be derived from fields.yaml rather than hardcoded speculatively.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural without explaining concepts Claude already knows, but the large hardcoded CATEGORY_MAPPING literal and several prescriptive formatting-rule lists are speculative and could be tightened, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	Concrete commands ('python {topic}/generate_report.py') and a real CATEGORY_MAPPING code block are given, but the core generate_report.py is specified as requirements rather than provided as copy-paste executable code, matching 'some concrete guidance but incomplete; missing key details'.	2 / 3
Workflow Clarity	Steps are clearly sequenced (locate outline.yaml, scan fields, generate script, run), but this batch operation has no validation or verification checkpoint (e.g. confirm report.md contains every item, re-run on script error), which per the rubric caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The skill is a single file with clear section organization and no problematic deep references, but no bundle files exist and detailed spec such as the category mapping and formatting rules is inline rather than split into a reference, fitting 'some structure but content that should be separate is inline'.	2 / 3
	Total	8 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 conveys a concrete, specific purpose but is missing explicit 'when to use' trigger guidance and offers limited trigger-term variation. Adding a Use-when clause and broader natural keywords would raise the highest-weighted dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when summarizing deep-research JSON results into a markdown report or when the user asks to aggregate research findings.'

Broaden natural trigger terms to include common phrasings users would say, such as '总结调研结果', '整理研究数据', '生成研究报告', and 'deep research summary'.

Optionally enumerate multiple concrete actions (e.g. scan fields, let user pick summary fields, skip uncertain values, render anchored table of contents) to lift specificity from a single action to a list.

Dimension	Reasoning	Score
Specificity	Quotes '汇总为markdown报告' and '跳过不确定值' name a concrete action and filter rule on the deep-research domain, but only one main action is described rather than multiple concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	The description states what it does (aggregate research into a markdown report covering all fields, skipping uncertain values) but lacks any 'Use when...' or equivalent explicit trigger guidance, which per the rubric guideline caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like '调研', '报告', 'markdown', and '汇总' are reasonably natural, but coverage is thin with no common variations or scenario triggers, fitting 'some relevant keywords but missing common variations' rather than the full-coverage level 3.	2 / 3
Distinctiveness Conflict Risk	The deep-research-to-markdown-report niche is fairly specific, but without explicit triggers it could still overlap with general summarization/reporting skills, matching 'somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: Weizhena/Deep-Research-skills
Path: skills/research-zh/research-report/SKILL.md
Commit: e5479f8

Reviewed: 11 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.