recovering-from-errors
Recovering from Errors guides you through diagnosing Watch Skill failures using the built-in doctor command, which identifies issues with ffmpeg, yt-dlp, video acquisition, provider authentication, and local models. Apply the stated fixes, retry your original operation, and report any persistent structured errors without looping or changing security policies.
Recovering from Errors helps diagnose and fix Watch Skill command failures using structured error codes and targeted remediation.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-12
Recovering from Errors helps diagnose and fix Watch Skill command failures using structured error codes and targeted remediation. Recovering from Errors guides you through diagnosing Watch Skill failures using the built-in doctor command, which identifies issues with ffmpeg, yt-dlp, video acquisition, provider authentication, and local models. Apply the stated fixes, retry your original operation, and report any persistent structured errors without looping or changing security policies.
Use it when
- Recovering from Errors addresses ffmpeg dependency issues through the doctor command.
- Recovering from Errors includes yt-dlp troubleshooting as a core repair pathway.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
oxbshw/watch-skill/recovering-from-errors · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
Watch skill command failed—how to fix it?
Recovering from Errors helps you diagnose and repair Watch Skill failures. Start by running the built-in doctor command, which identifies issues with ffmpeg, yt-dlp, video acquisition, provider authentication, and local models. The doctor will return structured error codes that pinpoint the root cause. Apply the stated fixes, then retry your original operation. If the error persists, report the structured error code without looping or changing security policies.
How do I troubleshoot ffmpeg missing error recovery?
Recovering from Errors addresses ffmpeg dependency issues through the doctor command. When ffmpeg is missing, the doctor detects this and provides repair instructions. Install ffmpeg using your system's package manager (apt, brew, or equivalent), verify the installation, then retry your watch command. The doctor command will confirm ffmpeg is properly detected before you proceed with video operations.
What should I do if yt-dlp is not found?
Recovering from Errors includes yt-dlp troubleshooting as a core repair pathway. Run the doctor command to confirm yt-dlp is missing, then install it via pip or your package manager. After installation, verify the tool is accessible from your command line, then retry your video download or watch operation. The doctor will validate that yt-dlp is properly configured before you continue.
How do I resolve provider authentication and API key errors?
Recovering from Errors guides you through provider authentication issues. The doctor command detects when API keys are missing, expired, or misconfigured. Check your provider credentials, ensure they are correctly set in your environment or configuration file, and verify the API key has not been revoked. Retry your operation after updating credentials. If errors persist, report the structured error code for further investigation.
Why can't it watch this video and how do I fix it?
Recovering from Errors helps diagnose video acquisition failures. Run the doctor command to identify whether the issue stems from ffmpeg, yt-dlp, provider authentication, corrupt caches, or local model problems. Clear any stale locks or corrupt caches if flagged, repair missing dependencies, and verify provider credentials. Retry your watch operation once fixes are applied. Report any persistent structured errors without changing security policies.
What does the watch skill doctor command do?
Recovering from Errors describes the doctor command as your primary diagnostic tool. It scans for broken ffmpeg and yt-dlp dependencies, validates provider authentication and API key configuration, detects corrupt caches and stale locks, and checks local vision model and memory health. The doctor returns structured error codes that guide you to specific fixes. Run it whenever a watch command fails to identify the exact issue and next steps.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Recovering from errors
Failures use stable error codes and include an actionable fix. Preserve that evidence;
do not replace it with a generic explanation.
Diagnose first
watch-skill doctor --json
Read the failing checks and apply only their stated fixes. doctor can repair managed
ffmpeg and yt-dlp binaries, stale locks, corrupt caches, missing frame directories, and
known local-model health failures. Re-run it once after remediation.
Retry the original operation once
After doctor is green, repeat the command that failed. If it returns another structured error, report its code, message, and fix. Do not loop indefinitely, silently switch cloud providers, enable cloud STT, or reprocess an already indexed video.
Common routes:
-
(truncated - see the full file via the links below)
File tree — 1 file
adapters/claude-skill/skills/recovering-from-errors/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Diagnose and fix a failed watch skill command using structured error codes”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Watch Skill processes any video—URLs, local files, streams, recordings—by extracting frames, running OCR, and transcribing audio into a unified searchable index. Query the index directly instead of re-watching, and batch-process playlists or folders in one pass.
When a video answer goes wrong, report the correction and Watch Skill records it as a lesson stored locally. The system classifies the mistake, injects it into similar future questions, and can re-ask the original question to verify the fix worked. Check what's been learned or review token savings anytime.
Watch Skill processes videos locally by extracting scene-aware frames, running OCR on text within them, and transcribing audio via offline Whisper or captions. It builds a searchable index so follow-up questions are answered without re-processing the video. No API keys required for core features; vision and STT are optional and configurable.
Turn your video analysis into a self-contained HTML file that anyone can open without needing Watch Skill or internet access. The page bundles frames, transcript, OCR text, and all your cached Q&A with timestamped evidence in one shareable document—ideal for bug tickets, code reviews, or handing off findings to teammates.
Video Memory maintains a searchable index of every video watched on your machine, preserving frames, transcripts, and extracted answers in persistent storage. Search across all indexed videos by keyword or semantic meaning, drill into specific moments, or synthesize answers from insights spanning multiple videos. Batch-import playlists or folders to build your video library quickly.
Pull structured data from videos you've already watched: titled chapters with timestamps for long content, pinpointed bug reports with error frames and OCR text, or opening-hook analysis scored across attention, pacing, visuals, and on-screen text. All answers come straight from the persistent index with no extra model calls.
More skills asking-with-evidence (MIT)