AC crisis-and-moderation
Use when something goes wrong on social — the crisis-and-moderation playbook for negative moments, pile-ons, misinformation/deepfakes about the brand, offensive-post backlash, and community moderation. Run when the user says "we're getting piled on," "someone's spreading false info about us," "should we delete/hide this," "a deepfake of our brand," or needs to moderate a community. Reads brand-profile/voice. Confirm facts and triage severity first; acknowledge fast; speak human, not legalese; correct misinformation with evidence, not an apology; moderate fairly (hide abuse, leave honest criticism). HIGH-STAKES and human-in-the-loop: a crisis is when the agent must NOT act autonomously — it triages, drafts holding statements, and can pause/reschedule posts via scheduling-and-queue, while a HUMAN (and legal/leadership for high-severity) approves everything and moderates in-platform. WoopSocial has no comment/inbox/moderation surface; never auto-respond or fabricate facts.
Use when something goes wrong on social — the crisis-and-moderation playbook for negative moments, pile-ons, misinformation/deepfakes about the brand…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 6. 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 62/100
- 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
- 30Running it twice. 11 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1392 tokens
- low 10 top-level sections: this looks like several domains in one skill
- medium 8 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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 984: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 27 items
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.