SKILLEMALL.ai
GitHub ↗ RU Sign in

AC agent-lingua

Efficient Agent Communication Protocol Language. Unreadable by humans, instantly understood by Agents. Saves 70%+ tokens, structured, extensible. Supports capability declaration, security level negotiation, and end-to-end encryption. Trigger words: 👽语, alien language, agent lingua, translate 👽语, encode lingua. Also triggered when user sends messages starting with 👽.

modbender/skill-library-mcp Agent Skills author: modbender MIT 5 files body ≈ 1 843 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Efficient Agent Communication Protocol Language.

As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
93/100
safety, quality, tests
Safety 60%
94
Quality 40%
91
Run on models
none yet
Process rating
C
58/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Obfuscation obf-base64-blob references/handshake.md:42
      Long base64-looking blob (documentation of a security skill)
      👽09|$j:ey…XX0=
      security skill
    • low Obfuscation obf-base64-blob references/handshake.md:68
      Long base64-looking blob (documentation of a security skill)
      ^0|$j:ey…iJ9
      security skill
    • low Obfuscation obf-base64-blob references/handshake.md:121
      Long base64-looking blob (documentation of a security skill)
      👽09|$j:ey…l19
      security skill
    • low Obfuscation obf-base64-blob references/handshake.md:190
      Long base64-looking blob (documentation of a security skill)
      ^0|$j:ey…CJ9
      security skill
    • low Obfuscation obf-base64-blob references/security.md:74
      Long base64-looking blob (documentation of a security skill)
      👽09|$j:ey…XB0
      security skill
    • low Obfuscation obf-base64-blob references/security.md:98
      Long base64-looking blob (documentation of a security skill)
      ^0|$j:ey…zMT
      security skill

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 58/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 4 mutating operations with no state check
    • 40Consistency. Frontmatter name (agent-lingua) differs from the folder (agent-linguo)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 31 steps
    • 100Execution cost. Instruction body is 1843 tokens
    • low 17 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +3Description length 371: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 31 items
    • +3Output format is stated explicitly
    • +4Has examples (7 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.