AB comeback-buddy
帮用户分析对话场景并生成巧妙的回怼话术。Use when the user provides chat screenshots, conversation transcripts, or describes a situation where they felt spoken down to, bullied in conversation, or wished they had a better comeback. Inputs include chat context (text or screenshots). Outputs: 1) Situation analysis (who's right, power dynamics, emotional undercurrents), 2) Ready-to-use comeback lines (multiple options with different tones), 3) Generalizable techniques for similar future encounters. Triggers on phrases like "帮我回怼", "怎么怼回去", "帮我分析这段对话", "这句话怎么回", "被人说了不知道怎么回", "吵架没发挥好", "怼怼". Works across scenarios: couples, friends, colleagues, bosses, family, customer disputes. Covers mild comebacks through nuclear options (leave-the-job level).
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice
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: 4. 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 65/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 549 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 731: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 35 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.