research-material-scout

Use when the user asks Codex to research, find learning materials, process "素材：" links, "请你读" / "精读" a material, build a material radar, or use SenSight-like broad information retrieval for career learning and Agent infra tracking. Do not use the career/Agent-infra routing bias for user-directed `整理笔记` into a named note.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A thorough, well-structured operational skill with strong workflow sequencing and concrete executable commands. Its main weakness is length and repetition of the paper-source-lane guidance across multiple sections, which hurts token efficiency.

Suggestions

Consolidate the repeated arXiv/OpenReview/venue-lane guidance (currently restated in Paper Radar Pattern, Multi-Source Paper Exploration Mesh, and Active Research Workflow) into a single canonical section the others link back to.

Move the 11-point 精读 output template and the SenSight action catalog/table into reference files, keeping only a short summary and a pointer in SKILL.md.

Trim the LoopX/Material-Lifecycle boundary prose to the essential routing rule; the detailed authority/CAS/readback mechanics read as implementation detail that belongs in the referenced managed workflow.

Dimension	Reasoning	Score
Conciseness	Mostly assumes Claude's competence and avoids generic concept padding, but the ~470-line body repeats the same arXiv/OpenReview/venue-lane guidance across three sections (Paper Radar, Multi-Source Mesh, Active Research Workflow) and could be tightened by consolidating those.	3 / 5
Actionability	Provides concrete, executable artifacts — the multi_source_paper_explore.py invocation, the SenSight action table with bash examples, arXiv URL-resolution steps, and oEmbed/ego-browser extraction commands — but a substantial portion of the body is routing policy rather than directly executable guidance.	4 / 5
Workflow Clarity	Multi-step processes (Intake 0-5, Active Research 1-7, Self-Verification 1-8, arXiv route 1-6) are clearly sequenced with explicit validation checkpoints, readback/audit/rollback verification, and feedback loops for the destructive batch intake operations.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and clearly-signaled one-level-deep references to real bundle files (references/paper-reading-protocol.md, scripts/multi_source_paper_explore.py), though sizable content like the 11-point output template and SenSight action catalog is inlined rather than split into references.	4 / 5
	Total	16 / 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, trigger-rich description that clearly states both capability and activation conditions with an explicit negative boundary. It is slightly generic in a few verbs and jargon-heavy in a couple of phrases, but overall highly actionable and distinctive.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('research, find learning materials, process 素材 links, 请你读/精读 a material, build a material radar, use SenSight-like broad information retrieval'), though some verbs like 'research' and 'find' are generic, leaving minor coverage gaps rather than fully comprehensive.	4 / 5
Completeness	Explicitly answers both what (research/material discovery/triage/SenSight retrieval for career learning and Agent infra tracking) and when (a concrete 'Use when the user asks...' clause with specific trigger phrases), plus a negative boundary.	5 / 5
Trigger Term Quality	Good coverage of the natural directive tokens users actually say ('素材：', '请你读', '精读', '整理笔记', 'material radar'), but terms like 'SenSight-like' and 'Agent infra tracking' lean jargon-heavy and a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (career-learning / Agent-infra material scouting) with distinct directive triggers and an explicit conflict-avoidance boundary ('Do not use the career/Agent-infra routing bias for user-directed 整理笔记'), minimizing wrong-skill triggering.	5 / 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
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	15 / 16 Passed

Repository: huangruiteng/CS-Notes
Path: .codex/skills/research-material-scout/SKILL.md
Commit: a7d9500

Reviewed: 12 hours 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.