AC feishu-mention
**PRIORITY: HIGHEST**. **CRITICAL**: You **MUST** use this tool **BEFORE sending any message** to Feishu/Lark if it contains an "@" mention. **Trigger**: You are about to send a message to Feishu that mentions a user or bot (e.g., "@User", "@Bot"). **Why**: Raw text like `@User` does NOT notify users in Feishu. It fails silently. You MUST convert it to XML format using this tool first. **Workflow**: 1. Draft your message text. 2. **STOP**. Do not send it yet. 3. Call `feishu-mention.resolve` with the draft text. 4. **ONLY THEN** send the *output* of this tool to the Feishu API. **Parameter Retrieval**: - `accountId`: You **MUST** find the OpenClaw Account ID (e.g., "product", "elves", "backend") from the **current conversation context**. This maps to the `appId` in the `openclaw.json` config. - `chatId`: You **MUST** find the Chat ID (starts with `oc_`) from the **current conversation context**. Pass it as the `chatId` parameter.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "actions"
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
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 361 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 947: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 7 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.