AB podcast-to-script
Turn a podcast episode link into a timestamped transcript AND a production-ready Chinese two-host script package (outline.md, script.md, notes.md) that faithfully translates/restores the original episode and passes the bundled format checker — self-contained, no external pipeline dependency. Use when the user pastes a podcast URL (open.spotify.com/episode/..., podcasts.apple.com/..., an RSS feed URL, or a direct audio link) and asks for 字幕/转录/transcript/文字稿/逐字稿, wants 把播客转成文字 or 转成播客脚本, translate an episode into a 双人对谈中文脚本 (翻译还原原播客), or batch-process episodes. Staged & resumable: preflight → fetch → outline → draft → notes, each stage gated by a script. No Spotify/Apple API key: metadata via oEmbed/iTunes, official <podcast:transcript> when available, otherwise public RSS audio + faster-whisper. SKIP: YouTube/video captions, music tracks, Spotify-exclusive shows with no public RSS feed (script reports this).
Turn a podcast episode link into a timestamped transcript AND a production-ready Chinese two-host script package (outline.md, script.md, notes.md) that…
As a process B 66/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
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: 7. 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 66/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1540 tokens
- low The response is described with custom markup (8 tags): a typed call is more reliable
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 921: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 9 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.