research-refine-pipeline

Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

92%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.

A well-organized orchestration skill with a clear phased workflow, explicit validation checkpoints, and disciplined progressive disclosure via sibling skills. The only soft spot is that executable mechanics live in the referenced skills rather than this body, which is appropriate for a pipeline-composition skill.

Dimension	Reasoning	Score
Conciseness	Lean, checklist-driven body that assumes Claude's competence and explains no background concepts; every section earns its place with no padding.	5 / 5
Actionability	Provides concrete filenames, exit criteria, and a copy-paste-ready PIPELINE_SUMMARY template, but defers the executable stage mechanics to sibling skills rather than being fully self-contained.	4 / 5
Workflow Clarity	Phases 0-5 are explicitly sequenced with validation gates (triage check, Planning Gate checklist, REVISE-only-if-documented rule) and feedback loops for error recovery.	5 / 5
Progressive Disclosure	A clear overview delegates stage detail to one-level-deep, well-signaled sibling-skill and shared-protocol references; no inlined bulk content or nested references.	5 / 5
	Total	19 / 20 Passed

Description

87%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.

A strong, specific description with explicit what-and-when guidance and natural multilingual trigger terms. It is clearly distinguishable from the component skills it composes. Minor gains are possible only in enumerating a few additional trigger phrasings.

Dimension	Reasoning	Score
Specificity	Names the domain (chaining research-refine and experiment-plan) and several concrete actions/outputs (final proposal, experiment roadmap, pipeline summary), but does not exhaustively enumerate every capability the pipeline performs.	4 / 5
Completeness	Explicitly answers both what (chains the two workflows to produce a proposal plus experiment roadmap) and when (a concrete 'Use when...' clause listing multiple trigger phrases).	5 / 5
Trigger Term Quality	Includes natural user phrases ('build a pipeline', 'do it end-to-end', '串起来', 'one-shot') with synonyms, giving strong keyword coverage; a few plausible trigger phrasings are still absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear integrated-pipeline niche with distinct triggers and is explicitly framed as distinct from the single-stage sibling skills, minimizing wrong-skill activation.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/research-refine-pipeline/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.