Overcast init

Install and configure overcast for this harness: install the CLI, verify the system ffmpeg, and configure reusable provider profiles. Use once per machine/profile before driving the `overcast` skill.From its SKILL.md

Install

npx -y skills add kdr/overcast --skill overcast-init

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

4 things to look at

skips confirmationTells the agent to proceed without asking first, 2 times: "overcast provider setup apply --preset cloudglue --profile default --yes --json" and 1 more.
reads credentialsReads from 4 credential sources: `CLOUDGLUE_API_KEY` and 3 more.
12 stars12 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 8 commands, including `pi install npm:@kdrrr/overcast` and 7 more.

SKILL.md

3.6 KB, 971 tokens by cl100k_base, as published. Nobody here has run it

overcast-init

One-time setup for overcast.

Install the CLI — pi install npm:@kdrrr/overcast (inside pi) or npm i -g @kdrrr/overcast for the standalone binary.
Install bundled skills for this agent — for Codex, Cursor, and other non-Claude harnesses, copy the shipped skills into the agent's skills directory explicitly:
```
overcast skills install --dest ~/.codex/skills
```
Bare overcast skills install remains the Claude Code default (~/.claude/skills), and --harness claude-code is the explicit Claude target.
Install/update tinycloud — the default perception backend. Get the latest (npm i -g @cloudglue/[email protected] then tinycloud install --latest, or tinycloud update). overcast needs tinycloud ≥ 0.3.12 — its watch envelope inlines the verbatim watch/listen transcripts (watch.speech.v1); the face + index verbs need ≥ 0.3.4, and the image see/extract verbs behind the opt-in see:tinycloud provider need ≥ 0.3.7. Override the invocation with OVERCAST_TINYCLOUD_CMD if it isn't on PATH.
Verify — overcast doctor --json (pi pinned, ffmpeg/ffprobe runnable, Cloudglue key, tinycloud CLI + version, optional uv/visual-db readiness).
Cloudglue key — the default watch/listen/face/index providers reach Cloudglue via the tinycloud CLI; configure it (tinycloud setup cloudglue) or export CLOUDGLUE_API_KEY.
Provider profile setup — choose reusable providers once per profile, not once per case. Always preview before applying:
```
overcast provider setup show --profile default --json
overcast provider setup plan --preset cloudglue --profile default --json
overcast provider setup apply --preset cloudglue --profile default --yes --json
overcast doctor --profile default --json
```
Optional presets/choices:
- cloudglue for tinycloud watch/listen/face plus built-in ffmpeg enhance.
- fal for see/enhance with FAL_KEY.
- hf for see/enhance with HF_TOKEN.
- elevenlabs for listen/enhance with ELEVENLABS_API_KEY.
- owl-local for OWLv2 open-vocabulary object detection.
- see:tinycloud (choice, --verb see --choice tinycloud) for Cloudglue file-level image analysis via tinycloud see/extract (needs tinycloud ≥ 0.3.7; --detect facts are boxless — no crop).
- deepface-local for local face detect/match through DeepFace.

Optional visual DB setup — prepare visual DB Python once per checkout/machine. DeepFace can be selected as a profile provider for the face verb, while image/face DBs are still case-owned local indexes:

scripts/visual-db-uv.sh --face
overcast doctor --json
overcast provider setup apply --verb face --choice deepface-local --profile default --yes --json
overcast index create logos --type image-ransac --local --json
overcast index create localfaces --type deepface-local --local --json

Case setup later — use the main overcast skill per investigation to run case setup, select targets/sources/indexes, and optionally set case-level automation such as --auto-sense, --auto-index-new, and --findings (defaults to suggest — score/text triggers auto-suggest leads; review is the legacy text-only mode, off disables).

Then use the overcast skill to drive the verbs.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most project setup skills give in 971 tokens

Counted across 1,553 of the 3,091 authors here whose files we hold, read 2026-09-06

Write the configuration filein 36 of 1553
Create the directory structurein 35 of 1553, across 33 files
Verify the setuphere, and in 31 of 1553, across 28 files
Run the setup scriptin 30 of 1553, across 29 files
Pre-determine the required sample sizein 29 of 1553, across 12 files
Check if the configuration already existsin 29 of 1553
Document every testin 26 of 1553, across 10 files
Start with a hypothesisin 26 of 1553, across 11 files
Ask one question at a timein 22 of 1553
Test a single variable per testin 21 of 1553, across 9 files
Read product marketing context before asking questionsin 19 of 1553, across 8 files
Do not peek and stop earlyin 18 of 1553, across 7 files

Said here and by no other author read

Install bundled skills for this agent
Install tinycloud
Configure the Cloudglue key
Setup provider profiles
Preview before applying provider setup
Setup optional visual DB

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.