The README now says Watch runs in Claude Code (Desktop's Code tab, VS
Code, or a terminal) and does not work in Claude Chat or Cowork. Cowork's
cloud environment drops the Gemini key between tasks and most sites block
yt-dlp from it. The standalone Chat upload instructions are removed.
Setup lets the user choose how to add an API key: paste it in chat, or
have the agent open ~/.config/watch/.env in their editor.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude's skill upload rejects frontmatter keys outside the spec. SKILL.md now
uses only spec keys, with the version under metadata.version.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Without a reported language, selection fell back to alphabetical order,
so an English video with de + en manual tracks got a German transcript.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A 403 now carries an update-and-retry-once hint, the skill contract tells
the agent how to update yt-dlp through its owning package manager, and CI
installs the latest yt-dlp instead of a pinned baseline.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
FFmpeg 9 lists the option as "-fps_mode[:<stream_spec>]", so the
whitespace-anchored probe missed it and every local run lost its frames.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Add opt-in local transcription with managed installation, cache warm-up,
and a one-time backend choice while preserving native-caption priority.
Correct frame timing and coverage, caption provenance and download
ownership, configuration parsing, provider pairing, and partial reports.
Update cross-host instructions, packaging, and test-gated release CI.
Validate 198 isolated tests, real local English and Spanish inference,
network-denied warm-cache inference, live captions/media, and packaging.
Record platform and account-dependent acceptance limits separately.
An inline comment on the WATCH_DETAIL value line (e.g.
`WATCH_DETAIL=balanced # ...`) parsed as the literal "balanced # ..."
value, failed validation, and silently reverted to the default mode.
- setup.py: move the allowed-values list off the value line in the env
template so the wizard no longer models a trailing inline comment.
- config.py: strip a whitespace-preceded inline comment from unquoted
values so a stray comment can't silently break selection again
(preserves '#' inside quotes / API keys).
- SKILL.md: note to write the bare key with no trailing comment.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the 0.2.0 changelog entry (--detail dial, frame dedup, Whisper
auto-chunking, --timestamps/--no-whisper, self-contained skill restructure).
README: drop the "Why this exists" section, trim two speculative use cases,
and condense the frame-dedup and detail-modes sections to state the facts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Frame dedup and Whisper auto-chunking are user-facing feature additions, so
bump the minor version across the three in-sync version files (SKILL.md
frontmatter, .claude-plugin/plugin.json, .codex-plugin/plugin.json).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Frame extraction now runs a perceptual dedup pass (default on, --no-dedup
to disable) that drops near-identical frames before the budget cap, so the
budget goes to distinct content instead of held slides/static recordings.
The Frames report line notes how many near-duplicates were dropped.
Whisper transcription splits audio over the 25 MB upload cap into evenly
sized chunks, transcribes each, shifts segment timestamps back into source
time, and tolerates partial failures (only fails if every chunk fails) —
length alone no longer fails transcription.
token-burner is exempt from the long-video sparse-scan warning since it
keeps every scene-change frame. README/SKILL.md updated. Adds test_dedup.py and test_whisper.py.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Move the skill into skills/watch/ so SKILL.md and its scripts/ runtime are
siblings inside one folder. `npx skills add` (Codex/Cursor/Copilot/agents) now
copies a working skill as a unit; previously it grabbed the root SKILL.md alone
and left scripts/ behind, so the skill was dead on arrival on every non-Claude
host. Mirrors the layout last30days-skill adopted for the same reason.
- skills/watch/{SKILL.md,scripts/}: self-contained skill folder
- SKILL.md: resolve a harness-agnostic $SKILL_DIR (the dir it was Read from)
instead of the Claude-Code-only ${CLAUDE_SKILL_DIR}; guard + 19 call sites
- drop commands/watch.md: /watch derives from frontmatter (name + user-invocable)
- .codex-plugin/plugin.json: full manifest with "skills": "./skills/" + interface
- add .agents/plugins/marketplace.json, AGENTS.md, CLAUDE.md, .skillignore
- build-skill.sh: archive the skills/watch subtree (one SKILL.md, no zip -d)
- fix paths in tests, hooks hint, .gitattributes, release.yml
- relocate dev-sync.sh to repo root and fix REPO_ROOT
- README: content-ideas structure, npx skills install, star history
Verified: 37/37 tests pass; npx skills add bundles the full scripts/ runtime;
manifests valid; versions synced at 0.1.3.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- #2: harden subprocess argv against option injection
- #4: read/write config files as UTF-8 on Windows
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Path.read_text()/write_text() default to the platform encoding (cp1252
on Windows), which mangles or crashes on UTF-8 files. yt-dlp's
video.info.json is UTF-8 and routinely contains non-ASCII bytes, so on
Windows the parse raised UnicodeDecodeError, was swallowed by a bare
except, and the /watch report came back missing Title/Uploader.
- download.py: read video.info.json as UTF-8; log parse failures to
stderr instead of swallowing them silently.
- whisper.py, setup.py: same UTF-8 fix on .env reads and writes for
symmetry across platforms.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- download.py: insert `--` before URL in yt-dlp argv so a `-`-prefixed
string can never be parsed as a flag (e.g. --exec, --config-location).
Tighten is_url to reject `-`-prefixed sources and require non-empty
netloc.
- frames.py, whisper.py: resolve video/audio paths to absolute via
Path.resolve() before passing to ffmpeg/ffprobe (which don't honor
`--` as end-of-options), so a relative path starting with `-` can
never be misinterpreted as a flag.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- watch.py: drop the ⚠️ emoji from the long-video warning; cp1252
consoles on Windows couldn't encode it and the script crashed.
- setup.py: add a Windows branch that prints winget / pip install
commands, matching what the README already promised.
- SKILL.md: note that Windows users must invoke the scripts with
`python`, not `python3` (which is the Microsoft Store stub).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Claude Code plugins expose slash commands from commands/*.md; the root
SKILL.md alone isn't discovered. Thin shim delegates to the existing
skill contract. Strip commands/ from the claude.ai .skill bundle since
that surface uses SKILL.md directly. Bumped to 0.1.1.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Give Claude the ability to watch any video — yt-dlp download, ffmpeg
frame extraction with auto-scaled fps, native-caption transcript with
Whisper (Groq/OpenAI) fallback.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
