research-pipeline

Full end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.

Quality

82%

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

Quality

Content

73%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.

The body is a well-sequenced, highly actionable orchestration guide with strong validation gates and feedback loops. Its main weakness is conciseness — the confusing Stage 5/6 renumbering note and some redundant prose add tokens without clarity — alongside minor progressive-disclosure gaps where inline content could be externalized.

Suggestions

Remove or simplify the "Stage 5 / Stage 6" renumbering explanation (lines 225-227); pick one consistent stage numbering to eliminate confusing padding.

Tighten constant descriptions to one line each and drop restated rationale already covered elsewhere (e.g., the repeated --no-review justification in the Render HTML section).

Move the inline helper-resolution bash block (lines 50-63) into resumable-runs.md, keeping only a short pointer plus the warn-and-skip rule inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance, but contains unnecessary or confusing padding — notably the "Stage 5 / Stage 6" renumbering explanation and some redundant constant prose — that could be tightened.	3 / 5
Actionability	Concrete, copy-paste-ready slash commands with explicit arguments and named output files throughout, but relies on placeholders ($ARGUMENTS, $CHOSEN_IDEA_TITLE) and template-style gate presentations that leave minor gaps.	4 / 5
Workflow Clarity	Stages are clearly sequenced with explicit validation checkpoints (Gate 1 human checkpoint, Gate 2 venue/figure checks, sanity-check-first deployment) and feedback loops (auto-review loop up to 4 rounds with stop conditions), satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Good structure as an overview delegating to sub-skills and one-level-deep shared-references (external-cadence.md, resumable-runs.md, output-*.md) via clearly signaled links; minor gaps where a long inline helper-resolution bash block could live in a reference.	4 / 5
	Total	16 / 20 Passed

Description

91%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.

The description is strong: third-person voice, explicit what-and-when with concrete natural trigger phrases (including bilingual synonyms), and a clearly scoped niche. Minor gaps in action granularity and some overlap with chained sub-skills keep specificity and distinctiveness just below ceiling.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete pipeline stages — "idea discovery, experiments, and review all the way to a polished paper PDF" — but the actions are stage-level rather than granular, leaving minor coverage gaps (e.g., novelty check, ablations).	4 / 5
Completeness	Explicitly answers both what ("Full end-to-end research pipeline: from a broad research direction... to a polished paper PDF") and when ("Use when user says...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage with synonyms and bilingual variants — "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", "complete autonomous research lifecycle" — phrases a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (the complete autonomous research lifecycle) with distinct full-pipeline triggers, but minor overlap risk with its component skills (/idea-discovery, /experiment-bridge, /auto-review-loop) it chains.	4 / 5
	Total	18 / 20 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
relative_links	Relative link issues: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/skills-codex/research-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.