SKILLEMALL.ai
GitHub ↗ RU Sign in

AC pokecron

Power-user scheduler that creates persisted OS-native timers (systemd/launchd/Task Scheduler) which later run user-configured argv command hooks (`--pre-cmd`, `--post-cmd`, `--on-pong-command`, `--if-unconfirmed-command`) and agent prompts under your user account, without a daemon. Also ships an opt-in `--apply` migration helper that rewrites the OpenClaw config (with a timestamped backup) to disable native heartbeat polling, and an opt-in vector-tone mode that POSTs intent text to `OLLAMA_URL` (loopback-only unless `POKE_ALLOW_REMOTE_OLLAMA=1`). Reply-aware with escalation and quiet hours. Use for time-based requests — "remind me", "wake me", "every morning", "keep poking until I reply". *Linux only for now; mac coming VERY soon. Windows eventually.*

ClawHub Agent Skills author: Æliott v1.0.4 MIT-0 42 files · 3 scripts body ≈ 545 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Power-user scheduler that creates persisted OS-native timers (systemd/launchd/Task Scheduler) which later run user-configured argv command hooks (--pre-cmd…

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

GeneratorAI 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
92/100
safety, quality, tests
Safety 60%
98
Quality 40%
82
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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 · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Dangerous commands cmd-background-process sub-skills/stages.md:77
      Starts a background / autostarted process (security demo / example; quoted — discussed, not commanded)
      self-daemonize (e.g. `setsid` + write a PID file) and exit its parent
      demoquoted
    • low Dangerous commands cmd-background-process sub-skills/stages.md:114
      Starts a background / autostarted process (quoted — discussed, not commanded)
      - On `--start`: self-daemonize (`setsid bash -c '…' &`, or re-exec with
      quoted

    Files scanned: 42. 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 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 1 mutating operations with no state check
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 10 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 545 tokens

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • -32 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 4 example trigger phrases
    • +3Description length 761: enough signal without eating the budget
    • +4Structure: 5 headings
    • +3Step-by-step instructions: 10 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: suspicious
    This is a disclosed power-user reminder scheduler, but one stored-context feature can leak commitments into later agent prompts more broadly than documented.
    LLM: suspicious (high) · VirusTotal: · 28 May 2026