AD openclaw-feishu-multi-bot
Configure multiple Feishu/Lark bot identities within a single OpenClaw instance — each Agent gets its own Feishu App, name, avatar, and message routing. Use when: (1) Setting up multi-bot Feishu integration where each Agent appears as a separate bot, (2) Configuring message routing between Feishu apps and OpenClaw agents, (3) Debugging Feishu bot routing issues (bot not responding, wrong agent receiving messages, gateway startup failures), (4) Designing a multi-Agent architecture with per-role Feishu entry points, (5) Setting up per-project Feishu group isolation. Also trigger for: '飞书多机器人', '一个龙虾多个飞书', '飞书路由', 'Feishu accounts', 'Lark bot routing', or any question about making multiple Agents appear as separate bots in Feishu/Lark. Based on production experience running 10+ Agents with independent Feishu bots (2026-04).
As a process D 41/100 · Unfinished process — weak spots: steps, result and completion, when it triggers
How to improve
- 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: 9. 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 41/100
- 0Steps. Prose only: no discrete steps
- 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. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 881 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 832: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.