research-report

Summarize deep research results into markdown report, cover all fields, skip uncertain values.

Quality

66%

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-en/research-report/SKILL.md

Quality

Content

72%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 content is concise, well-structured, and self-contained, with concrete formatting and skip rules. Its main gaps are the lack of an executable script template and missing validation/verification checkpoints for the batch report-generation step.

Suggestions

Add a validation checkpoint after Step 4 — e.g. verify report.md was written, confirm every JSON item appears in the TOC, and re-run the script on failure.

Provide a starter template for generate_report.py (at least the skeleton: load JSON, load fields.yaml, build TOC, render sections, write report.md) instead of only a requirements list.

Specify the TOC anchor-link generation rule explicitly so item names map deterministically to anchors.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with actionable spec, assuming Claude's competence and avoiding explanation of concepts Claude already knows; the only code block (CATEGORY_MAPPING) earns its place.	3 / 3
Actionability	Concrete requirements and a real mapping block are provided, but the core deliverable (generate_report.py) is specified as a requirements list rather than an executable template, and key details like TOC anchor generation and error handling are missing.	2 / 3
Workflow Clarity	Steps 1–4 are clearly sequenced, but there is no validation or verification checkpoint (e.g. confirm report.md exists, verify all items present) for a batch operation over many JSON files.	2 / 3
Progressive Disclosure	The skill is self-contained with well-organized sections (Trigger, Workflow, Output) and no need for external bundle files, which is appropriate for a skill of this size.	3 / 3
	Total	10 / 12 Passed

Description

60%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 concrete actions and a clear purpose, but omits any explicit trigger guidance and relies on a narrow set of keywords. It is reasonably distinct yet could overlap with broader summarization skills.

Suggestions

Add an explicit "Use when..." clause naming natural triggers (e.g. "Use when summarizing deep research results into a report, or when the user asks to compile research findings into markdown").

Broaden trigger terms to include common user phrasings like "research", "report", "summary", and "compile findings".

Sharpen distinctiveness by referencing the TOC/field-coverage output format that sets this apart from generic summarization.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Summarize deep research results into markdown report", "cover all fields", and "skip uncertain values" — rather than vague language.	3 / 3
Completeness	It clearly states what the skill does but lacks any explicit "Use when..." trigger guidance, so the "when" is missing rather than merely implied.	2 / 3
Trigger Term Quality	"deep research results" and "markdown report" are relevant keywords, but common variations a user would naturally say (e.g. "research", "report", "summary") are missing.	2 / 3
Distinctiveness Conflict Risk	The research-report niche is somewhat specific, but it could still overlap with general summarization or report-generation skills.	2 / 3
	Total	9 / 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-en/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.