SKILLEMALL.ai
GitHub ↗ RU Sign in

AC tencentcloud-oceanus-ops

Use for TencentCloud Oceanus (流计算 Oceanus) operations: SQL/JAR job CRUD, job config, run/stop jobs, dependency/resource management, job events/logs, workspace/folder ops. Trigger on keywords: job, 作业, workspace, 工作空间, 集群, 依赖, resource, 日志, log, or IDs matching space-*, cluster-*, cql-*. Also trigger when user asks to run oceanus_ops.py. Do NOT trigger for generic cloud tasks (CVM, COS, TKE, billing) or cluster lifecycle (create/scale/delete cluster).

ClawHub Agent Skills author: 腾讯开源 v1.0.1 MIT-0 31 files body ≈ 2 154 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

Use for TencentCloud Oceanus (流计算 Oceanus) operations: SQL/JAR job CRUD, job config, run/stop jobs, dependency/resource management, job events/logs…

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions

ProcedureSoftware developmentInfrastructureAI 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
91/100
safety, quality, tests
Safety 60%
90
Quality 40%
92
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
55
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.

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • medium Dangerous commands cmd-shell-rc references/credential-setup.md:36
      Writes to a shell startup file
      cat >> ~/.zshrc <<'EOF'
    • medium Dangerous commands cmd-shell-rc references/credential-setup.md:50
      Writes to a shell startup file
      cat >> ~/.bashrc <<'EOF'

    Files scanned: 31. 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 63/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 100Steps. 49 steps
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2154 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • +2Single-language instructions
    • +3Description length 454: enough signal without eating the budget
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 49 items
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (7 of 7)
    • +3All 14 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: suspicious
    The skill appears purpose-built for TencentCloud Oceanus operations, but it needs Review because it can make real cloud changes and has under-scoped credential and data-exposure paths.
    LLM: suspicious (high) · 24 Jul 2026