BC maxclaw-helper
Usage guidance and runtime diagnostics for MaxClaw / OpenClaw. Activate when: (1) User asks how to use a feature — e.g. 'how to enable Feishu long polling', 'how to configure Cron', 'how to install a skill'; (2) User is unsure about a config field's meaning or correct syntax; (3) User asks about onboarding steps for a channel (Feishu, Telegram, Discord, etc.); (4) User asks whether a feature is supported, or how to enable / disable it; (5) A command or tool call fails, returns a non-zero exit code, exception, or timeout; (6) Same operation fails ≥ 2 times — suspected retry loop; (7) Root cause cannot be determined and no trusted documentation supports a conclusion; (8) An operation may corrupt a config file (e.g. openclaw.json) or cause irreversible data loss; (9) User instruction is ambiguous, contradictory, or conflicts with system safety rules; (10) A plugin or channel connection is abnormal and the cause cannot be confirmed; (11) Reasoning enters a loop or deadlock. Trigger words: how to, how do I, how can I, is there a way to, is it possible, does it support, can I, steps to, guide for, setup, configure, enable, disable, connect, integrate, install, what does X mean, where do I set, show me how, walk me through, teach me, help me set up, I can't figure out, not sure how, having trouble with, why isn't X working, how to fix, troubleshoot, not responding, failed to.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: ClawHub
How to improve
- Shorten the description to 1024 characters.
- 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 · 0
✓ No critical or high findings
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1391 chars, limit 1024
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 27 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1429 tokens
- 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)
- +3Description length 1391: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 27 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.