brainstorming-research

Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue

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/brainstorming-research/SKILL.md

Quality

Content

77%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 highly actionable and well-sequenced with explicit validation gates and a feedback loop, but it carries redundancy across repeated dialogue constraints and references a templates.md file that is not present in the bundle.

Suggestions

Remove redundant restatements of the 'one question at a time' and 'wait for the answer' rules by consolidating them into the core-principles section and trimming per-question repeats.

Either provide templates.md in the references/ bundle or replace the '从 templates.md 读取' instruction with inline default structures so the reference is not dangling.

Consider moving the per-question dialogue scripts and the project-overview.md template into a references/ file to reduce the SKILL.md footprint and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the 'one question at a time' rule and 'wait for answer' reminders are restated many times (core principles, EXTREMELY-IMPORTANT block, key principles, and repeated per-question) and could be tightened.	2 / 3
Actionability	Provides copy-paste-ready concrete guidance: exact quoted dialogue for each question, a language-defaults table, and a full project-overview.md template with explicit file/directory creation steps, which is highly actionable for an instruction-only skill.	3 / 3
Workflow Clarity	A clear 11-step checklist plus a DOT flowchart with an explicit confirmation gate (HARD-GATE) and a feedback loop ('需要修改' routes back to '问论文类型') provide explicit validation checkpoints and error recovery.	3 / 3
Progressive Disclosure	No bundle files exist, yet the body references a non-existent templates.md ('从 templates.md 读取') and keeps large inline content (per-question dialogue, the overview template) that could be split out; sections are organized but references are not clearly signaled or backed by real files.	2 / 3
	Total	10 / 12 Passed

Description

77%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 clearly states what the skill does and when to use it with an explicit trigger and several concrete actions. Its main weaknesses are broad trigger language that invites overlap and missing common user vocabulary for paper types.

Suggestions

Add natural user vocabulary such as "thesis", "dissertation", "essay", "research paper", or "manuscript" so the description matches terms users actually say.

Sharpen the trigger to reduce overlap with general writing skills, e.g. "Use before drafting any academic paper to plan structure and scope".

Keep the explicit 'Use before...' clause; it is the strongest part of the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "clarifies paper type, discipline, topic, methodology, and chapter structure", naming five specific things the skill does, matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue") and when ("Use before writing any paper"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Contains some natural terms ("writing any paper", "paper type", "topic") but misses common variations a user would actually say ("thesis", "essay", "research paper", "manuscript"), and "discipline"/"methodology" lean technical.	2 / 3
Distinctiveness Conflict Risk	The "before writing" pre-planning niche is somewhat distinct, but "any paper" is broad and could overlap with general writing skills rather than being a clear non-conflicting niche.	2 / 3
	Total	10 / 12 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: Norman-bury/research-writing-skill
Path: skills/brainstorming-research/SKILL.md
Commit: 6f79595

Reviewed: 10 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.