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.

60

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex/comm-lit-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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-structured, sequenced research workflow with clear degradation rules, but it is hampered by redundancy across sections and by an inverted progressive-disclosure structure: detailed venue/source material is inlined in SKILL.md while matching reference files sit unused. Adding concrete search/MCP call examples would improve actionability.

Suggestions

Link the existing references/ files (venue-tiering.md, source-policy.md, domain-taxonomy.md, output-template.md) from the relevant body sections and move the inlined venue-tier and source-policy lists out of SKILL.md to eliminate duplication and orphaned bundles.

Add one or two executable examples per retrieval step — e.g. a representative WebSearch query string and a sample Zotero/Obsidian MCP call — so the search actions are concrete rather than implied.

De-duplicate the database/venue ordering that currently recurs across Retrieval Order, External Search Policy, Venue Priority, and Step 1; state the canonical ordering once and reference it.

DimensionReasoningScore

Conciseness

The body is mostly instructional and avoids explaining concepts Claude already knows, but the database/venue ordering is restated across Retrieval Order, External Search Policy, Venue Priority, and Step 1, creating noticeable redundancy that could be tightened.

3 / 5

Actionability

Guidance is specific in places (named venues, the exact paper-level fields to capture, the output table columns), but the actual retrieval steps lack executable commands or examples (no WebSearch query templates, no Zotero/Obsidian MCP call examples), leaving the execution details implicit.

3 / 5

Workflow Clarity

A clearly sequenced multi-step workflow (Step 0a/0b/0c, Step 1, Step 2, Synthesis, Output) with explicit graceful-degradation checkpoints ("If an unrequested source is unavailable, do not fail"; stop-and-report when an explicitly requested source is missing); minor gaps only.

4 / 5

Progressive Disclosure

Bundle files exist in references/ (venue-tiering.md, source-policy.md, domain-taxonomy.md, output-template.md) but the body never references or links to them, and the venue-tier and source-policy material is instead inlined and duplicated in SKILL.md — the classic "content that belongs in separate files is inlined" pattern with orphaned references.

2 / 5

Total

12

/

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: it explicitly states what the skill does and when to use it, with a rich set of natural communications-domain trigger terms. Its only weakness is that the core capability is described somewhat abstractly rather than as a list of discrete concrete actions.

DimensionReasoningScore

Specificity

Names a concrete domain and concrete outputs ("papers, related work, a survey, or a landscape summary") plus a defined method ("knowledge-base-first retrieval"), but the core action is still fairly abstract rather than a list of several discrete operations.

4 / 5

Completeness

Explicitly answers both what ("Communications-domain literature review with Claude-style knowledge-base-first retrieval") and when ("Use when the task is about ... and the user wants papers, related work, a survey, or a landscape summary") with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and acronyms (communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming) alongside the user-intent phrases papers/related work/survey/landscape summary.

5 / 5

Distinctiveness Conflict Risk

Clear niche (communications-domain literature review) with domain-specific triggers that minimize conflict, but the broad literature-review framing leaves minor overlap risk with a general literature skill for edge topics.

4 / 5

Total

18

/

20

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.