SKILLEMALL.ai
GitHub ↗ RU Sign in

BB model-migrate-flagos

Migrate a model from the latest vLLM upstream repository into the vllm-plugin-FL project (pinned at vLLM v0.13.0). Use this skill whenever someone wants to add support for a new model to vllm-plugin-FL, port model code from upstream vLLM, or backport a newly released model. Trigger when the user says things like "migrate X model", "add X model support", "port X from upstream vLLM", "make X work with the FL plugin", or simply "/model-migrate-flagos model_name". The model_name argument uses snake_case (e.g. qwen3_5, kimi_k25, deepseek_v4). Do NOT use for models already supported by vLLM 0.13.0 core, or for multimodal-only components that don't need backporting.

ClawHub Agent Skills author: Flagos v1.1.0 MIT-0 16 files · 4 scripts body ≈ 1 798 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 72/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationSoftware developmentInfrastructuretype 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
B
83/100
safety, quality, tests
Safety 60%
71
Quality 40%
100
Run on models
none yet
Process rating
B
72/100
Nearly there
Result and completion w 14
0
Inputs and preconditions w 11
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 13

    ✓ No critical or high findings

    Medium and low: 13
    • medium Exfiltration exfil-read-secret-files README_zh.md:220
      Reads credential / secret files (quoted — discussed, not commanded)
      > 1. 配置免密 SSH 登录 GT 机器：`ssh-copy-id -i ~/.ssh/id_ed25519 <user>@<GT_HOST_IP>`
      quoted
    • medium Exfiltration exfil-read-secret-files README.md:223
      Reads credential / secret files (quoted — discussed, not commanded)
      > 1. Set up passwordless SSH to the GT machine: `ssh-copy-id -i ~/.ssh/id_ed25519 <user>@<GT_HOST_IP>`
      quoted
    • medium Exfiltration exfil-read-secret-files references/procedure.md:284
      Reads credential / secret files (quoted — discussed, not commanded)
      If this fails, guide the user to set up SSH key: `ssh-copy-id -i ~/.ssh/id_ed25519 <GT_USER>@<GT_HOST_IP>`
      quoted
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash(curl:*)
      allowed-tools: Bash(pytest:*) Bash(python3:*) Bash(git:*) Bash(vllm:*) Bash(cp:*) Bash(curl:*) Bash(bash:*) Bash(test:*) Bash(ls:*) Bash(pip:*) Bash(cd:*) Read Edit Write Glob Grep AskUserQuestion Tas
    • low Secrets in code secret-high-entropy-token references/compatibility-patches.md:100
      High-entropy token-like string (may be an id, hash or a credential)
      class Qwen…ion(Qwen…ion):
    • low Secrets in code secret-high-entropy-token references/compatibility-patches.md:104
      High-entropy token-like string (may be an id, hash or a credential)
      class Qwen…ion(Qwen…ion):
    • low Secrets in code secret-high-entropy-token references/compatibility-patches.md:108
      High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
      super(Qwen…ion, self).__init__(...)  # skip parent, call grandparent
      placeholder
    • low Dangerous commands cmd-background-process scripts/e2e_remote_serve.sh:66
      Starts a background / autostarted process (code comment)
      # Start server in background: nohup docker exec ... &
      comment
    • low Secrets in code secret-high-entropy-token scripts/e2e_test_prompts.json:69
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "url": "data:image/png;base64,iVBO…AlC+aJAA…0b3/pZNm…3Pi/fUQe…PQN+753Q…UXz
      fixturequoted
    • low Secrets in code secret-high-entropy-token scripts/e2e_test_prompts.json:90
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "url": "data:image/png;base64,iVBO…AlC+aJAA…wD1/cAiC…GYV
      fixturequoted
    • low Secrets in code secret-high-entropy-token scripts/e2e_test_prompts.json:111
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "url": "data:image/png;base64,iVBO…AlC+aJAA…HZ7/YfyC…AKC+/AKC8/AKA8…Cjv/sHxh…AAA
      fixturequoted
    • low Secrets in code secret-high-entropy-token scripts/e2e_test_prompts.json:132
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "url": "data:image/jpeg;base64,/9j/4AAQ…AAD/2wBD…NDL/2wBD…IyM
      fixturequoted
    • low Secrets in code secret-high-entropy-token scripts/e2e_test_prompts.json:153
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      "url": "data:image/jpeg;base64,/9j/4AAQ…AAD/2wBD…NDL/2wBD…IyM
      fixturequoted

    Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "user-invokable"

    Process rating: all ten parameters 72/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 30Running it twice. 2 mutating operations with no state check
    • 100Tools and files. Tools declared in frontmatter
    • 100Steps. 14 steps
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 2 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1798 tokens
    • 100Progress reporting. Reports progress

    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

    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +5Description quotes 5 example trigger phrases
    • +4Description says when NOT to use the skill
    • +3Description length 667: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 14 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 6 scripts are documented
    • +1License stated

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

    External checks

    ClawHub: suspicious
    This appears to be a real vLLM model-migration skill, but it grants broad GPU and remote-server control without enough safeguards.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026