AC livestream-and-realtime
The live + realtime-format skill -- plan, promote, run, and repurpose livestreams and realtime moments (IG Live, TikTok LIVE, YouTube Live, LinkedIn Live, X, live shopping). Use when someone wants to plan a livestream, go live, run a live Q&A/AMA, do live shopping, or repurpose a live recording. Live is the "human premium," but the value is the event around it: promo before, engagement during, repurposing after. Uses the STAGE framework. Reads brand-profile + the live's goal first. The agent plans the live (platform + run-of-show), writes + schedules the pre-live promo, advises the live playbook (the human broadcasts natively), and plans the repurposing (recording -> clips). WoopSocial schedules the promo and publishes the repurposed clips; it does NOT broadcast, moderate in realtime, or run live shopping. Never fabricates viewer numbers. Distinct from community-management (native live moderation), campaign-and-launch-planning, and captions-and-clipping (the clip craft it routes to).
The live + realtime-format skill -- plan, promote, run, and repurpose livestreams and realtime moments (IG Live, TikTok LIVE, YouTube Live, LinkedIn Live, X…
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 56/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1593 tokens
- high The skill tells the model to perform an irreversible action with no human approval
- 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
- +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 998: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 10 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.