CtrlK
BlogDocsLog inGet started
Tessl Logo

aris-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. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.

68

Quality

82%

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

The canonical home for this skill is comm-lit-review in wanshuiyin/Auto-claude-code-research-in-sleep

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 well-structured, highly actionable literature-review skill with clear sequencing, but it pays a conciseness cost from repeated restatement of the source-priority logic, lacks explicit validation checkpoints in its workflow, and keeps lengthy venue-tier material inline with no progressive-disclosure references.

Suggestions

Consolidate the source-ordering policy into one authoritative section and have 'External Search Policy', 'Venue Priority' usage rules, and 'Key Rules' reference it instead of restating the ladder each time.

Add an explicit validation/dedup checkpoint between Step 1 (external search) and Step 2 (fact extraction) — e.g., verify each candidate is reachable and de-duplicate against already-captured sources before extracting facts.

Move the Tier A/B/C venue lists and the output-table column spec into a bundled reference file (e.g., references/venues.md) and link to it one level deep, keeping SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient and directive (no explaining of basic concepts), but the source-ordering logic is restated across 'Retrieval Order', 'External Search Policy', 'Venue Priority' usage rules, and 'Key Rules' — redundancy that could be tightened, matching the 'mostly efficient but could be tightened' anchor rather than the lean level-3 example.

2 / 3

Actionability

Highly actionable instruction-only guidance: a concrete database ladder with URLs (ieeexplore.ieee.org, sciencedirect.com, dl.acm.org), tiered venue lists, a fixed output-table column set, a Source-origin enum, and explicit synthesis groupings — copy-paste ready despite the absence of code, which is appropriate for a lit-review skill.

3 / 3

Workflow Clarity

Steps are clearly sequenced (0a/0b/0c/1/2 → Synthesis → Output) with explicit skip conditions, but there are no explicit validation checkpoints or feedback loops (e.g., a dedup/verify-availability gate between steps), matching the 'steps listed but checkpoints missing or implicit' anchor rather than the level-3 'explicit validation steps; feedback loops' anchor.

2 / 3

Progressive Disclosure

Sections are well-organized with clear headers, but the ~290-line body is monolithic: the full Tier A/B/C venue lists and the output-table spec are inline, and there are no bundle files or one-level-deep references to move that detail into (references/scripts/assets are empty), matching the 'content that should be separate is inline' anchor.

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.

A strong description: third-person, concise yet specific, with explicit 'Use when' triggers, a rich set of natural trigger terms, and a clear niche. It fully satisfies the what/when/completeness bar.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'literature review', 'Search Zotero, Obsidian, and local paper folders first', 'search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (knowledge-base-first literature review with a named source ladder) and when ('Use when the task is about ... and the user wants papers, related work, a survey, or a landscape summary'), matching the 'clearly answers both what AND when' anchor.

3 / 3

Trigger Term Quality

Dense coverage of natural user terms ('communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming' plus 'papers, related work, a survey, or a landscape summary'), matching the 'good coverage of natural terms' anchor.

3 / 3

Distinctiveness Conflict Risk

A clear communications-domain niche with a distinctive KB-first source ladder and layer-specific triggers (PHY/MAC, NTN, congestion control), making it unlikely to fire 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

allowed_tools_field

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

Warning

Total

15

/

16

Passed

Repository
OpenLAIR/dr-claw
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.