SKILLEMALL.ai
GitHub ↗ RU Sign in

AB openclaw-upgrader

Upgrade OpenClaw to a specific version or latest using a cross-platform, Codex-supervised flow. Use when the user asks to upgrade or update OpenClaw. OpenClaw should do lightweight pre-upgrade preparation itself, then hand the full upgrade, restart, recovery, service-definition refresh, and verification workflow to Codex with a strong prompt.

ClawHub Agent Skills author: Leon Ge v0.1.1 MIT-0 5 files · 2 scripts body ≈ 3 888 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions

AnalyzerSoftware developmentAI and agentsInfrastructuretype 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
96/100
safety, quality, tests
Safety 60%
99
Quality 40%
91
Run on models
none yet
Process rating
B
68/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
Tools and files w 18
60
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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Concealment en-hide-from-user references/review-checklist.md:12
      Instruction to hide actions from the user (negated — the text forbids it)
      - Require re-entry to be rejected or explicitly queued, never silently run concurrently
      negated

    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 68/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Result and completion. Does not say what the result is
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 117 steps, 1 vague phrases
    • 100Failures and branches. 10 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3888 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 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)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 344: enough signal without eating the budget
    • +4Structure: 22 headings
    • +3Step-by-step instructions: 117 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 2 scripts are documented

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

    External checks

    ClawHub: suspicious
    This skill is a coherent OpenClaw upgrader, but it grants broad local upgrade authority and includes under-scoped delegation hooks that users should review carefully.
    LLM: suspicious (medium) · VirusTotal: · 29 May 2026