#811 by GitHub stars

taoufik123-collab/claude-watch

Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analys

Claude Code Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

7711231e4c47 → 7711231e4c47

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7711231e4c47

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 7711231e4c47e5d4e06bcf5326c4abf5b70ab4a9

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/taoufik123-collab/claude-watch.git .hotskills/taoufik123-collab-claude-watch && git -C .hotskills/taoufik123-collab-claude-watch checkout --detach 7711231e4c47e5d4e06bcf5326c4abf5b70ab4a9
# Copy each selected skill directory from .hotskills/taoufik123-collab-claude-watch into .claude/skills/<skill-name>/

1.1kGitHub stars

43stars in 7 days

1skill in this repository

0commits in 30 days

Heat

6.8

Star growth, last 7 daysAhead of 95% of tracked repositories
Star growth, last 24 hoursAhead of 91% of tracked repositories
Rank movement, last 7 daysAhead of 83% of tracked repositories
Commits, last 30 daysAhead of 0% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

watch /

How it works

watch

When your agent uses it

Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.

What it loads into context

Frontmatter

183 tokens

Always available to the agent

SKILL.md

6,025 tokens

When the skill is activated

Reference documents

5,181 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

What v2 does differently
Configuration — finding the user's Obsidian vault
Step 0 — Setup preflight (runs every `/watch` invocation, silent on success)
When to use
Recommended limits
How to invoke
Transcription
Failure modes and handling
Token efficiency
Security & Permissions

Scripts executed separately

hooks/scripts/check-setup.sh
scripts/build-skill.sh
scripts/download.py
scripts/frames.py
scripts/hook.py
scripts/pacing.py
scripts/report.py
scripts/setup.py
scripts/tests/__init__.py
scripts/tests/test_frames_scene.py
scripts/tests/test_pacing.py
scripts/tests/test_report.py
scripts/transcribe.py
scripts/watch.py
scripts/whisper.py

Files

.claude-plugin/marketplace.jsonasset761 bytes
.claude-plugin/plugin.jsonasset696 bytes
.codex-plugin/plugin.jsonasset332 bytes
.gitattributesasset1,069 bytes
.github/workflows/release.ymlasset589 bytes
.gitignoreasset215 bytes
AUTHORS.mddoc630 bytes
CHANGELOG.mddoc4,356 bytes
LICENSEasset1,072 bytes
README.mddoc14,549 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
SKILL.mdcore23,397 bytes
commands/watch.mddoc699 bytes
hooks/hooks.jsonasset279 bytes
hooks/scripts/check-setup.shruns1,996 bytes
scripts/build-skill.shruns1,745 bytes
scripts/download.pyruns4,078 bytes
scripts/frames.pyruns13,773 bytes
scripts/hook.pyruns3,037 bytes
scripts/pacing.pyruns3,311 bytes
scripts/report.pyruns6,599 bytes
scripts/setup.pyruns10,552 bytes
scripts/tests/__init__.pyruns0 bytes
scripts/tests/test_frames_scene.pyruns2,616 bytes
scripts/tests/test_pacing.pyruns2,128 bytes
scripts/tests/test_report.pyruns2,679 bytes
scripts/transcribe.pyruns2,897 bytes
scripts/watch.pyruns12,144 bytes
scripts/whisper.pyruns13,165 bytes

Read SKILL.md


# /watch — Claude watches a video

You don't have a video input; this skill gives you one. A Python script downloads the video, extracts frames as JPEGs (one per detected shot via scene-change), gets a timestamped transcript (native captions first, then Whisper API as fallback), runs editorial pacing metrics, and microscopes the first 10 seconds at higher density. You then `Read` each frame path to see the images, combine them with the transcript to answer the user, fill the structured `report.md`, and offer to ingest the analysis into Taoufik's Second Brain.

## What v2 does differently

- **Scene-change frame sampling** — one frame per detected shot instead of uniform ticks. Cuts the frame budget on long videos while capturing every transition.
- **Editorial pacing metrics** — cuts/min, mean shot length, motion (when available). Lets you reason about pacing the way an editor does.
- **Hook microscope** — first 10s auto-runs at 2 fps + word-level Whisper. The single most leveraged 10 seconds of any video deserves dense treatment.
- **Structured `report.md`** — every watch emits an ingest-shaped report at `<workdir>/report.md` with TL;DR, key moments, hook breakdown, editorial profile, quotable moments, entities, concepts, and transcript. Narrative sections are emitted as `<!-- pending Claude fill: ... -->` markers — you fill them in before offering ingest.
- **Step 4.5 — Ingest gate** — after answering the user, you ask once: "Want to ingest this into your Obsidian vault?" If yes, and a vault is detected, you read `$VAULT_DIR/CLAUDE.md` (if it exists) and run that vault's Ingest op against the report.

None of the above add new dependencies — pure ffmpeg + stdlib + the existing Whisper backend.

View the complete source on GitHub

Skills included

watch

Repository facts

License: MIT
Created: May 25, 2026
Last pushed: Jul 24, 2026
Forks: 221
Open issues: 4
Project activity: Slowing

Rank over the last 12 weeks

Now #811 · best #680 · down 39 in 30 days

#813 on Nov 2
#814 on Nov 3
#810 on Nov 4
#809 on Nov 5
#806 on Nov 6
#811 since Nov 7

82 earlier periods

#770 on Aug 2
#781 on Aug 8
#828 on Aug 12
#835 on Aug 13
#818 on Aug 14
#793 on Aug 15
#814 on Aug 16
#817 on Aug 17
#837 on Aug 18
#831 on Aug 19
#822 on Aug 20
#827 on Aug 21
#778 on Aug 22
#836 on Aug 23
#845 on Aug 24
#855 on Aug 25
#841 on Aug 26
#842 on Aug 27
#823 on Aug 28
#739 on Aug 29
#733 on Aug 30
#759 on Aug 31
#767 on Sep 1
#746 on Sep 2
#743 on Sep 3
#715 on Sep 4
#699 on Sep 5
#728 on Sep 6
#735 on Sep 7
#758 on Sep 8
#742 on Sep 9
#747 on Sep 10
#725 on Sep 11
#721 on Sep 12
#719 on Sep 13
#744 on Sep 14
#740 on Sep 15
#741 on Sep 16
#745 on Sep 17
#728 on Sep 18
#697 on Sep 19
#711 on Sep 20
#730 on Sep 21
#747 on Sep 22
#735 on Sep 23
#701 on Sep 24
#686 on Sep 25
#683 on Sep 26
#709 on Sep 27
#721 on Sep 28
#756 on Sep 29
#736 on Sep 30
#692 on Oct 1
#700 on Oct 2
#680 on Oct 3
#711 on Oct 4
#716 on Oct 5
#727 on Oct 6
#733 on Oct 7
#772 on Oct 8
#742 on Oct 9
#725 on Oct 10
#718 on Oct 11
#728 on Oct 12
#726 on Oct 13
#735 on Oct 14
#727 on Oct 15
#733 on Oct 16
#708 on Oct 17
#702 on Oct 18
#736 on Oct 19
#738 on Oct 20
#745 on Oct 21
#724 on Oct 22
#727 on Oct 23
#693 on Oct 24
#812 on Oct 25
#806 on Oct 28
#808 on Oct 29
#810 on Oct 30
#812 on Oct 31
#810 on Nov 1

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 19 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

2 broad permissionsin 2 files: SKILL.md:1 commands/watch.md:1
4 dangerous shell commandsin 2 files: SKILL.md:190 scripts/setup.py:183
58 network referencesin 10 files: README.md:9 scripts/setup.py:39 scripts/tests/test_report.py:23 and 7 more
No hidden or obfuscated text
No instruction overrides
15 executable scriptsin 15 files: hooks/scripts/check-setup.sh:1 scripts/build-skill.sh:1 scripts/download.py:1 and 12 more
63 references to secretsin 7 files: scripts/whisper.py:35 scripts/setup.py:14 hooks/scripts/check-setup.sh:7 and 4 more
No requests to vote in Hot

Show all 142 signals by file

`.claude-plugin/marketplace.json`

Network accessline 16

"source": "./",       "category": "productivity",       "homepage": "https://github.com/taoufik123-collab/claude-watch"

Network accessline 17

"category": "productivity",       "homepage": "https://github.com/taoufik123-collab/claude-watch"     }

Network accessline 18

"homepage": "https://github.com/taoufik123-collab/claude-watch"

`.claude-plugin/plugin.json`

Network accessline 6

"name": "taoufik"   },   "homepage": "https://github.com/taoufik123-collab/claude-watch",

Network accessline 7

},   "homepage": "https://github.com/taoufik123-collab/claude-watch",   "repository": "https://github.com/taoufik123-collab/claude-watch",

Network accessline 8

"homepage": "https://github.com/taoufik123-collab/claude-watch",

Network accessline 9

"repository": "https://github.com/taoufik123-collab/claude-watch",

`.codex-plugin/plugin.json`

Network accessline 3

"version": "0.2.0",   "description": "Let Claude (or Codex) watch a video — scene-change frames + transcript + structured report, with a 0-10s hook microscope and optional Obsidian auto-save.",   "repository": "https://github.com/taoufik123

Network accessline 4

"description": "Let Claude (or Codex) watch a video — scene-change frames + transcript + structured report, with a 0-10s hook microscope and optional Obsidian auto-save.",   "repository": "https://github.com/taoufik123-collab/claude-watch",

Network accessline 5

"repository": "https://github.com/taoufik123-collab/claude-watch",

`AUTHORS.md`

Network accessline 5

**Bradley Bonanno** — [bradautomates/claude-video](https://github.com/bradautomates/claude-video)

Network accessline 13

**Taoufik** — [taoufik123-collab](https://github.com/taoufik123-collab)

`CHANGELOG.md`

Network accessline 7

Based on [bradautomates/claude-video](https://github.com/bradautomates/claude-video) v0.1.3 by Bradley Bonanno (MIT). Its pipeline (yt-dlp + ffmpeg + Whisper) is preserved; everything below is additive.

`README.md`

Network accessline 9

[![This Claude Skill Watches Videos So You Don't Have To](https://img.youtube.com/vi/iYG5tiFfK3E/maxresdefault.jpg)](https://www.youtube.com/watch?v=iYG5tiFfK3E&t=43s)

Network accessline 17

claude.ai (web): [download `watch.skill`](https://github.com/taoufik123-collab/claude-watch/releases/latest) and drop it into Settings → Capabilities → Skills.

Network accessline 21

git clone https://github.com/taoufik123-collab/claude-watch.git ~/.codex/skills/watch

Network accessline 42

/watch https://youtu.be/iYG5tiFfK3E how does this creator hook the viewer in the first 45 seconds?

Network accessline 55

**Analyze someone else's content.** `/watch https://youtu.be/<viral-video> what hook did they open with?` Claude looks at the first frames, reads the opening transcript, breaks down the structure. Same for ad creative, competitor launches,

Network accessline 59

**Summarize a video.** `/watch https://youtu.be/<long-thing> summarize this` does the obvious thing — pulls the structure, the key moments, what was actually said and shown. Faster than watching at 2x.

Network accessline 88

|---------|---------| | **Claude Code** | `/plugin marketplace add taoufik123-collab/claude-watch` then `/plugin install watch@claude-watch` | | **claude.ai** (web) | [Download `watch.skill`](https://github.com/taoufik123-collab/claude-watc

Network accessline 89

| **Claude Code** | `/plugin marketplace add taoufik123-collab/claude-watch` then `/plugin install watch@claude-watch` | | **claude.ai** (web) | [Download `watch.skill`](https://github.com/taoufik123-collab/claude-watch/releases/latest) → S

Network accessline 90

| **claude.ai** (web) | [Download `watch.skill`](https://github.com/taoufik123-collab/claude-watch/releases/latest) → Settings → Capabilities → Skills → `+` |

Network accessline 91

| **Codex** | `git clone https://github.com/taoufik123-collab/claude-watch.git ~/.codex/skills/watch` |

Network accessline 92

| **Manual / dev** | `git clone https://github.com/taoufik123-collab/claude-watch.git ~/.claude/skills/watch` |

Network accessline 106

1. [Download `watch.skill`](https://github.com/taoufik123-collab/claude-watch/releases/latest) from the latest release.

Network accessline 115

git clone https://github.com/taoufik123-collab/claude-watch.git ~/.codex/skills/watch

Network accessline 121

git clone https://github.com/taoufik123-collab/claude-watch.git ~/.claude/skills/watch

Access to secretsline 131
```
[Credential-related source omitted]
```

Network accessline 140

|------------|---------------|------| | Download + native captions | `yt-dlp` + `ffmpeg` | Free | | Whisper fallback (preferred) | [Groq API key](https://console.groq.com/keys) — `whisper-large-v3` | Cheap, fast |

Network accessline 141

| Download + native captions | `yt-dlp` + `ffmpeg` | Free | | Whisper fallback (preferred) | [Groq API key](https://console.groq.com/keys) — `whisper-large-v3` | Cheap, fast | | Whisper fallback (alt) | [OpenAI API key](https://platform.ope

Network accessline 142

| Whisper fallback (preferred) | [Groq API key](https://console.groq.com/keys) — `whisper-large-v3` | Cheap, fast |

Network accessline 143

| Whisper fallback (alt) | [OpenAI API key](https://platform.openai.com/api-keys) — `whisper-1` | Standard pricing |

Network accessline 149

/watch https://youtu.be/iYG5tiFfK3E how does this creator hook the viewer in the first 45 seconds?

Network accessline 150

/watch https://www.tiktok.com/@user/video/123 summarize this

Network accessline 152

/watch https://vimeo.com/123 what tools does she mention?

Network accessline 157

/watch https://youtu.be/abc --start 2:15 --end 2:45

Network accessline 210

I'm Taoufik. I build AI agents and tools like `/watch`, and I make videos about how I build them: **[@TaoufikAI on YouTube](https://www.youtube.com/@TaoufikAI)**. If this skill saved you time, the channel is where the next ones show up firs

Network accessline 220

Built on `yt-dlp`, `ffmpeg`, and Claude's multimodal `Read` tool. Whisper transcription via [Groq](https://groq.com) or [OpenAI](https://openai.com).

Network accessline 224

[github.com/taoufik123-collab/claude-watch](https://github.com/taoufik123-collab/claude-watch) · [Credits](#credits) · [LICENSE](LICENSE)

`SKILL.md`

Broad permissionsline 1
```
Bash, Read, AskUserQuestion
```

Network accessline 4

argument-hint: "<video-url-or-path> [why you're watching it]" allowed-tools: Bash, Read, AskUserQuestion homepage: https://github.com/taoufik123-collab/claude-watch

Network accessline 5

allowed-tools: Bash, Read, AskUserQuestion homepage: https://github.com/taoufik123-collab/claude-watch repository: https://github.com/taoufik123-collab/claude-watch

Network accessline 6

homepage: https://github.com/taoufik123-collab/claude-watch

Network accessline 7

repository: https://github.com/taoufik123-collab/claude-watch

Access to secretsline 78
```
[Credential-related source omitted]
```
Access to secretsline 80
```
[Credential-related source omitted]
```

Network accessline 103

**Step 1 — parse the user input.** Separate the video source from any question the user asked. The question (or the user's prior stated interest) IS the intent — pass it to the script via `--intent`. Example: `/watch https://youtu.be/abc wh

Dangerous shell operationline 190

**Cleanup implication for Step 4.5:** if the user picks "No, drop it" at 4.5 AND a vault was staged at 4.4, ALSO `rm -rf "$VAULT_DIR/raw/watched/<slug>"` since we pre-staged. Do NOT drop the vault copy if they picked Yes or Stage.

Dangerous shell operationline 216

**C. No, drop it:** proceed to Step 5 (cleanup) — and per the cleanup-implication note in Step 4.4, `rm -rf "$VAULT_DIR/raw/watched/<slug>"` to undo the pre-staging.

Dangerous shell operationline 220

**Step 5 — clean up.** The script prints a working directory at the end. If you ingested (Step 4.5 path A), the hero frames + report.md are already copied to Second Brain — you can `rm -rf` the original workdir. If you staged (path B), same

Access to secretsline 257
```
[Credential-related source omitted]
```
Access to secretsline 258
```
[Credential-related source omitted]
```

`commands/watch.md`

Broad permissionsline 1
```
Bash
```

`hooks/scripts/check-setup.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Access to secretsline 7
```
[Credential-related source omitted]
```
Access to secretsline 10
```
[Credential-related source omitted]
```
Access to secretsline 11
```
[Credential-related source omitted]
```
Access to secretsline 13
```
[Credential-related source omitted]
```
Access to secretsline 14
```
[Credential-related source omitted]
```
Access to secretsline 25
```
[Credential-related source omitted]
```
Access to secretsline 33
```
[Credential-related source omitted]
```
Access to secretsline 42
```
[Credential-related source omitted]
```
Access to secretsline 43
```
[Credential-related source omitted]
```
Access to secretsline 55
```
[Credential-related source omitted]
```

`scripts/build-skill.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`scripts/download.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/frames.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/hook.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 22
```
[Credential-related source omitted]
```
Access to secretsline 33
```
[Credential-related source omitted]
```
Access to secretsline 51
```
[Credential-related source omitted]
```
Access to secretsline 52
```
[Credential-related source omitted]
```
Access to secretsline 54
```
[Credential-related source omitted]
```
Access to secretsline 68
```
[Credential-related source omitted]
```

`scripts/pacing.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/report.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/setup.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 14
```
[Credential-related source omitted]
```
Access to secretsline 32
```
[Credential-related source omitted]
```

Network accessline 39

# and is faster in practice. OpenAI is the compatible fallback. # # Get a Groq key:  https://console.groq.com/keys

Network accessline 40

# # Get a Groq key:  https://console.groq.com/keys # Get an OpenAI key:  https://platform.openai.com/api-keys

Network accessline 41

# Get a Groq key:  https://console.groq.com/keys

Network accessline 42

# Get an OpenAI key:  https://platform.openai.com/api-keys

Access to secretsline 47
```
[Credential-related source omitted]
```
Access to secretsline 48
```
[Credential-related source omitted]
```
Access to secretsline 75
```
[Credential-related source omitted]
```
Access to secretsline 99
```
[Credential-related source omitted]
```
Access to secretsline 101
```
[Credential-related source omitted]
```
Access to secretsline 112
```
[Credential-related source omitted]
```

Network accessline 163

if _which("brew") is None:         return False, (             "Homebrew is not installed. Install it from https://brew.sh, then re-run setup. "

Network accessline 164

return False, (             "Homebrew is not installed. Install it from https://brew.sh, then re-run setup. "             "Or install manually: `brew install " + " ".join(_brew_pkg(missing)) + "`"

Network accessline 165

"Homebrew is not installed. Install it from https://brew.sh, then re-run setup. "

Dangerous shell operationline 183

hints.append("apt: `sudo apt install ffmpeg` or dnf: `sudo dnf install ffmpeg`")

Access to secretsline 218
```
[Credential-related source omitted]
```
Access to secretsline 240
```
[Credential-related source omitted]
```
Access to secretsline 241
```
[Credential-related source omitted]
```
Access to secretsline 249
```
[Credential-related source omitted]
```
Access to secretsline 308
```
[Credential-related source omitted]
```
Access to secretsline 309
```
[Credential-related source omitted]
```

`scripts/tests/init.py`

Executable scriptline 1
```
Executable file
```

`scripts/tests/test_frames_scene.py`

Executable scriptline 1
```
Executable file
```

`scripts/tests/test_pacing.py`

Executable scriptline 1
```
Executable file
```

`scripts/tests/test_report.py`

Executable scriptline 1
```
Executable file
```

Network accessline 23

out = write_report(             out_path=self.tmp / "report.md",             source="https://youtu.be/test",

Network accessline 24

out_path=self.tmp / "report.md",             source="https://youtu.be/test",             title="Test Video",

Network accessline 25
```
source="https://youtu.be/test",
```

Network accessline 53

text = out.read_text(encoding="utf-8")         self.assertTrue(text.startswith("---\n"))         self.assertIn("source: https://youtu.be/test", text)

Network accessline 54

self.assertTrue(text.startswith("---\n"))         self.assertIn("source: https://youtu.be/test", text)         self.assertIn("intent: studying hook patterns", text)

Network accessline 55

self.assertIn("source: https://youtu.be/test", text)

`scripts/transcribe.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`scripts/watch.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 27
```
[Credential-related source omitted]
```
Access to secretsline 164
```
[Credential-related source omitted]
```
Access to secretsline 167
```
[Credential-related source omitted]
```
Access to secretsline 187
```
[Credential-related source omitted]
```
Access to secretsline 188
```
[Credential-related source omitted]
```
Access to secretsline 194
```
[Credential-related source omitted]
```

`scripts/whisper.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 28

GROQ_ENDPOINT = "https://api.groq.com/openai/v1/audio/transcriptions"

Network accessline 31

OPENAI_ENDPOINT = "https://api.openai.com/v1/audio/transcriptions"

Access to secretsline 35
```
[Credential-related source omitted]
```
Access to secretsline 36
```
[Credential-related source omitted]
```
Access to secretsline 41
```
[Credential-related source omitted]
```
Access to secretsline 64
```
[Credential-related source omitted]
```
Access to secretsline 65
```
[Credential-related source omitted]
```
Access to secretsline 68
```
[Credential-related source omitted]
```
Access to secretsline 152
```
[Credential-related source omitted]
```
Access to secretsline 167
```
[Credential-related source omitted]
```
Access to secretsline 279
```
[Credential-related source omitted]
```
Access to secretsline 285
```
[Credential-related source omitted]
```
Access to secretsline 286
```
[Credential-related source omitted]
```
Access to secretsline 288
```
[Credential-related source omitted]
```
Access to secretsline 290
```
[Credential-related source omitted]
```
Access to secretsline 293
```
[Credential-related source omitted]
```
Access to secretsline 304
```
[Credential-related source omitted]
```
Access to secretsline 306
```
[Credential-related source omitted]
```
Access to secretsline 321
```
[Credential-related source omitted]
```
Access to secretsline 329
```
[Credential-related source omitted]
```
Access to secretsline 330
```
[Credential-related source omitted]
```
Access to secretsline 332
```
[Credential-related source omitted]
```
Access to secretsline 333
```
[Credential-related source omitted]
```
Access to secretsline 344
```
[Credential-related source omitted]
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 9 facts

Network access in code of documentationREADME.md:21Low confidence
Network access in code of documentationREADME.md:42Low confidence
Network access in code of documentationREADME.md:115Low confidence
Network access in code of documentationREADME.md:121Low confidence
Network access in code of documentationREADME.md:149Low confidence
Network access in code of documentationREADME.md:150Low confidence
Network access in code of documentationREADME.md:152Low confidence
Network access in code of documentationREADME.md:157Low confidence
Broad permissions in the frontmatter of the SKILL.mdSKILL.md:5High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest .claude-plugin/marketplace.json	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![taoufik123-collab/claude-watch on hotskills](https://hotskills.dev/badge/taoufik123-collab-claude-watch.svg)](https://hotskills.dev/skill/taoufik123-collab-claude-watch/)

taoufik123-collab/claude-watch

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

watch

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

.claude-plugin/marketplace.json

.claude-plugin/plugin.json

.codex-plugin/plugin.json

AUTHORS.md

CHANGELOG.md

README.md

SKILL.md

commands/watch.md

hooks/scripts/check-setup.sh

scripts/build-skill.sh

scripts/download.py

scripts/frames.py

scripts/hook.py

scripts/pacing.py

scripts/report.py

scripts/setup.py

scripts/tests/__init__.py

scripts/tests/test_frames_scene.py

scripts/tests/test_pacing.py

scripts/tests/test_report.py

scripts/transcribe.py

scripts/watch.py

scripts/whisper.py

How the signals fit together

Works with

You might also use

mattpocock/skills

obra/superpowers

NousResearch/hermes-agent

multica-ai/andrej-karpathy-skills

anthropics/skills

DietrichGebert/ponytail

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`.claude-plugin/marketplace.json`

`.claude-plugin/plugin.json`

`.codex-plugin/plugin.json`

`AUTHORS.md`

`CHANGELOG.md`

`README.md`

`SKILL.md`

`commands/watch.md`

`hooks/scripts/check-setup.sh`

`scripts/build-skill.sh`

`scripts/download.py`

`scripts/frames.py`

`scripts/hook.py`

`scripts/pacing.py`

`scripts/report.py`

`scripts/setup.py`

`scripts/tests/init.py`

`scripts/tests/test_frames_scene.py`

`scripts/tests/test_pacing.py`

`scripts/tests/test_report.py`

`scripts/transcribe.py`

`scripts/watch.py`

`scripts/whisper.py`