researchclaw

Run the ResearchClaw autonomous research pipeline from a topic, config, and output directory.

Quality

65%

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 ./.claude/skills/researchclaw/SKILL.md

Quality

Content

80%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 lean, highly actionable, and well-organized with copy-paste-ready CLI and Python examples, but it lacks an explicit error-recovery feedback loop for gate stages and keeps everything inline rather than splitting into bundle reference files.

Suggestions

Add an explicit validate->fix->retry feedback loop for gate stages (5, 9, 20) instead of only offering '--auto-approve'.

Move the detailed Python API, experiment-modes, and output-structure sections into separate reference files (e.g., PYTHON_API.md, OUTPUT_STRUCTURE.md) and link to them from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is dense with executable commands, code, option tables, and an output tree, with no padding explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Provides fully executable CLI commands ('researchclaw run --topic ... --auto-approve') and complete Python API code with imports, plus a troubleshooting table — copy-paste ready.	3 / 3
Workflow Clarity	Sequenced prerequisites and three run options are present with a config-validation checkpoint, but there is no explicit validate->fix->retry feedback loop for the gate stages (5, 9, 20) beyond '--auto-approve', leaving checkpoints implicit.	2 / 3
Progressive Disclosure	No bundle files exist and the 125-line body is monolithic; it references tool runtime outputs rather than skill bundle references, and content like the Python API / output structure could be split into separate one-level-deep reference files.	2 / 3
	Total	10 / 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 clearly states what the skill does in third person but omits an explicit 'Use when...' trigger clause and only lists one high-level action, leaving it at the middle tier across all dimensions.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to research a topic, write a research paper, or run an autonomous research pipeline.'

List more concrete capabilities (e.g., literature review, experiment design, paper writing) to lift specificity to a score-3 level.

Include common natural user phrasings like 'write a paper about [topic]' or 'investigate [topic]' as trigger terms.

Dimension	Reasoning	Score
Specificity	Names the action ('Run the ResearchClaw autonomous research pipeline') and inputs ('topic, config, and output directory'), but describes a single high-level action rather than multiple concrete actions, matching the score-2 anchor.	2 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes 'ResearchClaw' and 'research pipeline' but lacks common natural user phrasings like 'write a paper' or 'research a topic' that the body lists as triggers, so it has some keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	'ResearchClaw' is a distinct proper-noun niche unlikely to conflict, but the bare word 'research' is generic and could overlap with other research-related skills, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 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: aiming-lab/AutoResearchClaw
Path: .claude/skills/researchclaw/SKILL.md
Commit: e2e23c9

Reviewed: 6 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.