AF reconcile-timeline
Re-anchor a long-form video timeline to the MEASURED voiceover. After TTS runs, the timeline segment start/end times are still the PREDICTED (155 wpm) values while the audio plays at the TTS engine's actual pace. On a multi-minute video this compounds across segments and desyncs image from audio. This skill walks each timeline segment's vo_line against the measured word timings (written into subtitles[] by elevenlabs-tts) and rewrites each segment's start_time/end_time to the real audio boundaries, then updates audio_duration to the measured total. No API call. Re-runnable. Run AFTER elevenlabs-tts and BEFORE the final video render, long-form only. Use when processing a long-form (schema_version 3.0-long) job where the voiceover has already been generated and measured word timings exist in input.json.
Re-anchor a long-form video timeline to the MEASURED voiceover.
As a process F 54/100 · Will not run — References files that are not bundled: ../elevenlabs-tts/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../elevenlabs-tts/SKILL.md
Process rating: all ten parameters 54/100
- 0Tools and files. 1 referenced file(s) missing: ../elevenlabs-tts/SKILL.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 11 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 628 tokens
- 100Running it twice. No mutating operations
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 812: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 6 headings
- +3Step-by-step instructions: 11 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.