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.
62
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skills-codex/comm-lit-review/SKILL.mdQuality
Discovery
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.
This is an excellent skill description that clearly defines its niche (communications-domain literature review), provides comprehensive trigger terms spanning both broad and specific sub-domains, and explicitly states both what it does and when to use it. The retrieval order specification adds operational clarity and further distinguishes it from generic search or research skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: literature review, knowledge-base-first retrieval, searching Zotero/Obsidian/local folders, searching IEEE Xplore/ScienceDirect/ACM Digital Library, and specifies the retrieval order. Also names specific sub-domains like beamforming, channel estimation, MAC/PHY, etc. | 3 / 3 |
Completeness | Clearly answers both 'what' (communications-domain literature review with knowledge-base-first retrieval across specific sources) and 'when' (explicit 'Use when' clause listing specific topic triggers and user intent triggers like 'wants papers, related work, a survey, or a landscape summary'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'papers', 'related work', 'survey', 'landscape summary', plus domain-specific keywords like 'wireless', 'networking', 'satellite/NTN', 'Wi-Fi', 'cellular', 'congestion control', 'routing', 'beamforming', 'channel estimation'. These are terms users would naturally use when requesting a literature review in communications. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: narrowly scoped to communications-domain literature review with a specific retrieval hierarchy (Zotero → Obsidian → local folders → IEEE Xplore → ScienceDirect → ACM DL → web). The combination of domain specificity and tool-chain specificity makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent workflow clarity with well-defined retrieval ordering, graceful degradation, and clear escalation logic. However, it is significantly too verbose — venue lists, repeated source-ordering rules, and over-specified policies inflate the token cost substantially. It would benefit from concrete examples (e.g., a filled-out literature table row, example search queries) and splitting reference material like venue tiers into separate files.
Suggestions
Condense venue tiers into a compact table or move them to a separate VENUES.md reference file to reduce the main skill's token footprint by ~40%.
Add a concrete example showing one completed literature table row and a sample synthesis paragraph to make the output format truly actionable.
Remove redundant restatements of source ordering and graceful degradation rules — these appear in 'Retrieval Order', 'External Search Policy', 'Workflow Step 1', and 'Key Rules' sections.
Add an example of how to actually invoke Zotero MCP or search IEEE Xplore (e.g., example tool calls or search query patterns) to move from procedural description to executable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It over-specifies venue lists, tier definitions, and source policies that Claude already understands or could infer. The venue priority section alone is a wall of text that could be condensed to a compact table. Many rules are restated multiple times (e.g., graceful degradation, source ordering appears in multiple sections). | 1 / 3 |
Actionability | The skill provides clear structured steps and a specific output table format, which is good. However, there is no executable code, no concrete search query examples, no example of a completed literature table row, and no demonstration of how to actually interact with Zotero MCP, Obsidian MCP, or search IEEE Xplore. The guidance is detailed but procedural rather than executable. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0a through 2, then Synthesis, then Output) with explicit skip conditions, graceful degradation rules, and clear escalation logic (when to widen tiers, when to move to next database). The retrieval order is unambiguous with explicit handling of missing sources. | 3 / 3 |
Progressive Disclosure | The content is entirely monolithic — everything is in a single file with no references to supporting documents. The venue tier lists, synthesis rules, and output format could be split into separate reference files. However, the internal section structure is reasonable with clear headers, so it's not a complete wall of text. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Commit
a425a71
- 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.