AC podcast-and-audiograms
The audio-to-social pipeline skill -- turn a podcast episode into short, branded, captioned clips and audiograms that drive people back to the full episode. Use when someone wants to repurpose a podcast, make podcast clips, create audiograms, or promote an episode on social. Uses the WAVES framework. Reads brand-profile + the episode first. Select clips by listener-retention data + timestamped transcript, not just an AI virality score, plus a strategic CTA back to the episode. The agent plans the clip strategy, briefs the clip/audiogram creation, plans the cadence, and writes hooks/CTAs; a clip or audiogram tool produces the clips; the creator finalizes; WoopSocial publishes on a schedule and does NOT record/edit/transcribe the podcast, generate clips, or host it. Captions are non-optional (85% sound-off). Never fabricates virality or clips someone's copyrighted podcast. Distinct from captions-and-clipping, content-recycling, and youtube-long-form.
The audio-to-social pipeline skill -- turn a podcast episode into short, branded, captioned clips and audiograms that drive people back to the full episode.
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. 9 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 1616 tokens
- 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 962: 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.