CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 organized with concrete, mostly executable examples and a useful constraints section, but it is held back by broken reference links, unreferenced bundle scripts, missing validation in the batch workflow, and redundant performance claims repeated across three sections.

Suggestions

Fix the '参考资源' section to reference files that actually exist in the bundle — e.g. scripts/encode.py, scripts/decode.py, scripts/quick_demo.py — instead of broken paths like examples/two_agent_demo.py and ../DESIGN.md.

Add validation to the batch-transfer workflow: verify decoded similarity (e.g. skills.similar(v, skills.decode(e)) > 0.95) per message with a full-encode or JSON fallback, as already sketched in the error-handling section.

Remove the duplicated performance numbers (stated in the feature list, the performance table, and the FAQ) and drop the version-history section to tighten token usage.

DimensionReasoningScore

Conciseness

The body is mostly code, tables, and lists, but the same performance numbers (7-10x, <1ms, 0.9999 fidelity) are stated three times (feature list, performance table, FAQ '性能如何'), and the version-history section is time-sensitive padding that belongs outside the skill body. Not 4 because the redundancy is more than minor; not 2 because most sections are lean and instructional.

3 / 5

Actionability

Most code examples are concrete and executable (AgentSkills, send/receive, collaborate, batch encoding with numpy), with installation and integration steps included. Not 5 because of gaps like the undefined 'get_semantic_vector() # 你的语义向量' placeholder and undeclared 'vector1, vector2' in the basic example; not 3 because the examples are real code, not pseudocode.

4 / 5

Workflow Clarity

Usage is organized into basic-communication, send, collaborate, and batch scenarios, and an error-handling snippet shows a similarity check (sim < 0.95 warning) with JSON fallback. However, the batch-transfer workflow — a core advertised use case — encodes and sends 100 messages with no per-message validation or recovery loop, and the main workflows themselves lack checkpoints. The batch-without-validation cap applies, holding this at 3.

3 / 5

Progressive Disclosure

All four '参考资源' links point to files that do not exist in the bundle ('examples/two_agent_demo.py', '../DESIGN.md', '../neuralang/core/OPTIMIZATION_SUMMARY.md', '../skills-package/tests/test_all.py' — several also escaping the skill directory), while the actual bundle scripts (scripts/encode.py, scripts/decode.py, scripts/quick_demo.py) are never referenced anywhere in the body, making them undiscoverable. Not 3 because the references are broken rather than merely unclear; not 1 because the body itself has clear section structure.

2 / 5

Total

12

/

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.

A strong description that clearly states both capability and explicit 'Use when' triggers, with natural trigger terms and a distinct niche. Its main weaknesses are limited enumeration of concrete actions and some missing trigger synonyms.

DimensionReasoningScore

Specificity

The description names its domain ('Agent-to-Agent communication protocol') and 1-2 concrete actions ('vector encoding to reduce token consumption by 7-10x'), but does not list several specific capabilities (encode/decode/send/receive/collaborate are absent). Not 4 because coverage of concrete actions is not 'several'; not 2 because the actions given are concrete and quantified, not generic.

3 / 5

Completeness

It explicitly answers both what ('Efficient Agent-to-Agent communication protocol using vector encoding to reduce token consumption by 7-10x') and when ('Use when Agent collaboration, batch message transfer, or token saving is needed') with concrete trigger phrases, mirroring the anchor-5 example structure.

5 / 5

Trigger Term Quality

'Agent collaboration', 'batch message transfer', and 'token saving' are natural phrases a user would plausibly say when needing this skill. Not 5 because common synonyms and variations ('multi-agent', 'agent messaging', 'token cost/reduction') are missing; not 3 because the present terms go beyond merely 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The niche of vector-encoded inter-agent communication is fairly distinct, though 'Agent collaboration' and 'token saving' are broad triggers that could overlap with general orchestration or cost-optimization skills. Not 5 due to that overlap risk; not 3 because the vector-encoding niche is more specific than typical overlapping skills.

4 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 3 suspicious

Warning

Total

15

/

16

Passed

Repository

Fractal-Holographic-Lab/neuralang

Path

SKILL.md

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.