CtrlK
BlogDocsLog inGet started
Tessl Logo

comm-lit-review

Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.

64

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A highly actionable, well-structured instruction skill held back by repetition of the source/venue ladders and by keeping reference-worthy material inline instead of pointing to the existing bundle files. Adding a verification checkpoint and offloading venue/source-policy detail to the references would lift the weaker dimensions.

Suggestions

Add an explicit verification step to the workflow (e.g., 'Before producing the table, confirm each paper's relevance and that de-duplication against Zotero/local hits is complete') to satisfy the batch-operation feedback-loop expectation.

Replace the inline 'Venue Priority' tier lists and 'Source Selection'/'External Search Policy' detail with one-line pointers to venue-tiering.md and source-policy.md, signaling the existing reference files from the body.

De-duplicate the repeated zotero→obsidian→local→ieee→sciencedirect→acm→web ladder so it appears once, removing the conciseness drag from restating it in Retrieval Order, External Search Policy, and Step 1.

DimensionReasoningScore

Conciseness

It avoids explaining concepts Claude already knows, but the source ladder (zotero, obsidian, local, ieee, sciencedirect, acm, web) and venue tiers are restated across 'Retrieval Order', 'External Search Policy', and 'Step 1', so it could be tightened.

2 / 3

Actionability

Concrete, specific instruction guidance throughout: enumerated source values, named venue tiers, a fixed paper-fact extraction list, an explicit output table with columns, and a defined synthesis/output ordering.

3 / 3

Workflow Clarity

Steps 0a/0b/0c/1/2 are clearly sequenced, but this batch literature scan has no explicit validation or verification checkpoint before final output; per the rubric, batch operations missing feedback loops cap at 2 rather than 3.

2 / 3

Progressive Disclosure

The body is well-sectioned and reference files exist (venue-tiering.md, source-policy.md, output-template.md, domain-taxonomy.md), but venue tiers and source policy are fully inline and the body never signals the reference files, so content that should be separate is inline and references are not clearly signaled.

2 / 3

Total

9

/

12

Passed

Description

90%

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 well-constructed description with an explicit Use-when trigger and rich natural keyword coverage; its only weakness is that it enumerates domains more than distinct concrete actions. Voice is appropriately third-person with no over-claims.

DimensionReasoningScore

Specificity

It names the domain and two concrete actions ('literature review', 'knowledge-base-first retrieval'), but the bulk is a domain enumeration rather than a list of multiple specific concrete actions, matching anchor 2 rather than 3.

2 / 3

Completeness

It clearly states what it does ('Communications-domain literature review with Claude-style knowledge-base-first retrieval') and gives an explicit 'Use when the task is about... and the user wants papers, related work, a survey, or a landscape summary' trigger, answering both what and when.

3 / 3

Trigger Term Quality

Strong coverage of natural terms a user would say: 'wireless', 'networking', 'satellite/NTN', 'Wi-Fi', 'cellular', 'congestion control', 'beamforming', and 'papers, related work, a survey, or a landscape summary'.

3 / 3

Distinctiveness Conflict Risk

A clear, narrow niche (communications-domain literature review) with distinct trigger terms, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
wanshuiyin/Auto-claude-code-research-in-sleep
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.