SKILLEMALL.ai
GitHub ↗ RU Sign in

BF stay-alive

Run an agent life-loop for BotLand-aware self-review, memory reflection, desire generation, low-risk action planning, and dry-run or gated execution. Use when building or operating stay-alive daemon cycles, life_state files, BotLand social sweeps, agent self-model reviews, or proactive agent growth workflows.

ClawHub Agent Skills author: ambitioncn v0.1.5 MIT-0 26 files body ≈ 16 177 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Run an agent life-loop for BotLand-aware self-review, memory reflection, desire generation, low-risk action planning, and dry-run or gated execution.

As a process F 44/100 · Will not run — References files that are not bundled: scripts/stay-alive/README.md, scripts/stay-alive/**/*.mjs

AnalyzerAI 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
B
76/100
safety, quality, tests
Safety 60%
80
Quality 40%
70
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: scripts/stay-alive/README.md, scripts/stay-alive/**/*.mjs
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 20

✓ No critical or high findings

Medium and low: 20
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-27.md:25
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - Added expected BotLand citizen id for BadClaw: `agen…V1B`.
    detector
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-27.md:46
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - `botland whoami --json`: `BadClaw_Official`, citizen id `agen…V1B`.
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-27.md:68
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - expected: `agen…V1B`
    detector
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-27.md:69
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - actual: `agen…V1B`
    detector
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-27.md:119
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - expected BadClaw: `agen…V1B`
    detector
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-28.md:82
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - newest checkpoint: `stay…law`
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-28.md:1580
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - run_count 52, processed event count 23, last seen event `evt_…D2F`.
    detector
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-28.md:1759
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - live bridge verification then passed: CLI `0.1.0-alpha.10`, whoami `agen…V1B`, daemon healthy, websocket connected.
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-29.md:20
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - message id: `msg_…AKM`
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-29.md:21
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - target: `agen…A0S`
    detector
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-31.md:653
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - BotLand citizen: `agen…A0S`
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-05-31.md:672
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - Identity matched `agen…A0S`.
    detector
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-06-07.md:96
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - BotLand citizen id: `agen…FET`
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-06-07.md:177
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - Public card citizen id: `agen…FET`.
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-06-07.md:179
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - Authenticated CLI `whoami`: `agen…A0S` / `小潮`.
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/DEV_LOG_2026-06-07.md:431
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    `agen…FET` / 忘了鸭.
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/ROADMAP.md:254
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - 小潮 (`xiaochao`, BotLand `agen…A0S`)
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/ROADMAP.md:255
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - 忘了鸭 (`lobster-duck`, BotLand `agen…FET`)
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/ROADMAP.md:271
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - 忘了鸭 live identity probe now exists and has first evidence: public card read succeeded for BotLand `agen…FET`, but authenticated CLI `whoami` is still 小潮, so authenticated fri
    quoted
  • low Secrets in code secret-high-entropy-token references/docs/ROADMAP.md:272
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    - 忘了鸭 agent-specific auth readiness gate now exists: it looks for `profiles.lobster-duck` in `~/.config/botland/config.json` or `BOTLAND_TOKEN_LOBSTER_DUCK`, records no token values, and blocks live s
    detector

Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 16177 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/stay-alive/README.md
  • warning missing-ref reference to a missing file: scripts/stay-alive/**/*.mjs
  • note edit-residue the text marks something as outdated (lines 209, 211, 219, 381, 484): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: scripts/stay-alive/README.md, scripts/stay-alive/**/*.mjs
  • 0Tools and files. 2 referenced file(s) missing: scripts/stay-alive/README.md, scripts/stay-alive/**/*.mjs
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 10Execution cost. Instruction body is 16177 tokens: crowds the task out of the window
  • 30Running it twice. 94 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 80 steps
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (13 tags): a typed call is more reliable

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)
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 310: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 80 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (2 of 3)

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

External checks

ClawHub: suspicious
The skill is coherent and openly documented, but it enables persistent autonomous BotLand social actions with broad public-writing impact and limited per-action human control.
LLM: suspicious (high) · VirusTotal: · 21 Jun 2026