neuralang-communication

高效 Agent 间通信协议，使用向量编码减少 7-10x Token 消耗。当需要 Agent 协作、批量消息传输或节省 Token 时使用 (Efficient Agent-to-Agent communication protocol using vector encoding to reduce token consumption by 7-10x. Use when Agent collaboration, batch message transfer, or token saving is needed)

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

57%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 well-structured and actionable with multiple executable examples and a real scripts bundle, but it suffers from repeated metrics, a batch workflow without validation, and references that do not match the actual bundle files. Tightening redundancy and aligning references to the real scripts would lift the weaker dimensions.

Suggestions

Consolidate the latency/performance claims into the single performance table and remove their repetition in the feature list and FAQ to improve conciseness.

Add an explicit validation checkpoint to the batch-transmission example (e.g. verify decoded similarity per message before proceeding) to satisfy the batch-operation workflow requirement.

Replace the dead external references with links to the actual bundle scripts (scripts/quick_demo.py, scripts/encode.py, scripts/decode.py) so navigation matches the real file structure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with relevant code and tables, but repeats latency/figure claims across the feature list, performance table, and FAQ, and the FAQ restates install and performance details that could be tightened.	3 / 5
Actionability	Provides several concrete, mostly executable code examples (basic encode/decode, send/receive, collaborate, batch) backed by real scripts in scripts/, with only minor gaps such as the placeholder get_semantic_vector() and a local pip install -e rather than a published package.	4 / 5
Workflow Clarity	Usage examples are numbered and an encode→decode→similarity-check→JSON-fallback feedback loop is shown, but the batch-transmission workflow lacks explicit validation; per the batch-operation cap, this keeps workflow clarity at 3 rather than 4.	3 / 5
Progressive Disclosure	Section structure is clear with a dedicated references list, but the referenced paths (../DESIGN.md, examples/two_agent_demo.py) are not present in the bundle while the actual provided scripts (scripts/encode.py, decode.py, quick_demo.py) are never referenced from the body.	3 / 5
	Total	13 / 20 Passed

Description

78%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 cleanly answers both what the skill does and when to use it, with concrete quantified benefits and natural bilingual triggers. Its main weakness is specificity, since it conveys essentially one core action rather than a suite of capabilities.

Suggestions

Expand the 'what' to list 2-3 concrete capabilities (e.g. encode/decode vectors, send/receive messages, batch transfer) instead of stating only the vector-encoding mechanism.

Add synonym trigger terms (e.g. 'multi-agent', 'agent messaging', 'context compression') to broaden natural keyword coverage toward the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('Agent-to-Agent communication protocol') and one concrete mechanism ('vector encoding to reduce token consumption by 7-10x'), but does not list multiple distinct actions, matching the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	Explicitly answers both 'what' (efficient protocol using vector encoding, 7-10x reduction) and 'when' ('Use when Agent collaboration, batch message transfer, or token saving is needed') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural triggers ('Agent collaboration, batch message transfer, or token saving') in both Chinese and English, giving good keyword coverage; falls short of 5 only because it lacks synonyms and file-extension-style variants.	4 / 5
Distinctiveness Conflict Risk	The vector-encoding-for-agent-comms niche is mostly distinct, but triggers like 'Agent collaboration' and 'token saving' carry minor overlap risk with general agent-orchestration skills, so it sits at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing, 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: Fractal-Holographic-Lab/neuralang
Path: SKILL.md
Commit: 1101631

Reviewed: ~21 hours ago

Table of Contents

Discovery Implementation Validation

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.