CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body offers strong, well-sequenced workflows with explicit verification checkpoints and real referenced bundle files, but it is over-long with duplicated paper-lane guidance and inline detail that should be externalized. Actionability is good but undermined by placeholder commands and abstract directives mixed in.

Suggestions

Merge the 'Paper Radar Pattern' and 'Multi-Source Paper Exploration Mesh' sections — they repeat the same arXiv/OpenReview/venue/bioRxiv lane lists — and move the lane catalog into a reference file to cut duplicated tokens.

Replace the '<private-skill-installer>' placeholder and abstract SenSight install prose with a concrete, copy-paste-ready command or an explicit 'ask the user' instruction so the guidance is fully executable.

Move the SenSight actions table and the authenticated-social-link DOM-extraction recipe into references/ files, keeping only a one-line pointer plus the most-used action in SKILL.md, to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is ~420 lines with heavy repetition (Paper Radar Pattern and Multi-Source Paper Exploration Mesh re-state the same arXiv/OpenReview/venue lanes) and explanatory prose like 'Why this matters'; mostly efficient but padded and could be tightened.

2 / 3

Actionability

Concrete executable commands exist (the multi_source_paper_explore.py invocation, SenSight actions table, arXiv HTML route, ego-browser DOM extraction) but are mixed with placeholders like '<private-skill-installer>' and abstract directives, leaving guidance incomplete in places.

2 / 3

Workflow Clarity

Intake, Active Research, and Self-Verification workflows are clearly numbered and sequenced, with an explicit self-verification checklist and validation checkpoints (e.g., SenSight auth-block handling, Unread marking) that catch errors early.

3 / 3

Progressive Disclosure

Real one-level-deep bundle files are referenced and confirmed present (references/paper-reading-protocol.md, scripts/multi_source_paper_explore.py), but large sections that could be externalized (Paper Radar Pattern, Multi-Source Mesh, SenSight actions) remain inline rather than split out.

2 / 3

Total

9

/

12

Passed

Description

100%

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 concrete, trigger-rich, and answers both 'what' and 'when' with an explicit Use-when clause and a negative-scope boundary that limits conflict risk. It is written in imperative third-person voice with no first/second person.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'research, find learning materials, process 素材: links, 请你读 / 精读 a material, build a material radar' and 'SenSight-like broad information retrieval' — rather than vague language, matching the top anchor.

3 / 3

Completeness

Clearly answers both what (research/material discovery/triage) and when via an explicit 'Use when the user asks...' clause, plus a conflict-avoidance clause; not merely implied.

3 / 3

Trigger Term Quality

Natural trigger terms a user would actually say are well covered: 'research', '素材:', '请你读', '精读', '整理笔记', 'material radar', and SenSight-style retrieval.

3 / 3

Distinctiveness Conflict Risk

A clear niche (career learning + Agent infra tracking) with an explicit 'Do not use... for user-directed 整理笔记 into a named note' boundary that prevents triggering for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 11 missing

Warning

Total

15

/

16

Passed

Repository
huangruiteng/CS-Notes
Reviewed

Table of Contents

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.