Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills / Product / discovery

Overseer

Category: Product  ·  Sub-category: discovery  ·  Last updated:
Keep multiple parallel livespec tracks moving via a TWO-PANE model: a deterministic top-pane daemon (`overseerd`) that watches every tracked tmux session's context %, injects an ESCALATING wrap-up at threshold, and atomically restarts a session ONLY once that session declares itself `ready` (exit + `claude --dangerously-skip-permissions -n <topic>` + re-kick from `plan/<topic>/handoff.md`) — THE CARDINAL RULE: the daemon NEVER restarts a session that has not declared itself ready, because only the session knows whether it is safe to kill; one that declares nothing is REPORTED as not responding and left alone — and this THIN bottom pane, the interactive Claude overseer, which starts the daemon, manages the discovery-driven auto-managed track list via a JSONL topic↔tmux mapping (`add`/`remove`/`unassign`/`start`), and RELAYS the tracks the daemon reports as non-blocking text naming the tmux session + pane to go to. NOTIFY, NEVER BLOCK: a question may only be asked by the actor that OWNS the decision, so the overseer never raises a blocking prompt for a TRACK's decision (answer that in the track's own pane); it prompts only for decisions it owns (add/remove/unassign/start, threshold). The list is discovered from each watched repo's `plan/` dir; declaration is OUT-OF-BAND on the filesystem — ONE `.overseer-state` file valued `ready` / `blocked: <reason>` / `winding-down` — never pane text. The daemon never auto-spawns a session for an UNASSIGNED plan (first launch is deliberate) and never force-kills any session. The overseer does NO track work, never polls tracked sessions on a timer, never hand-codes. LOCAL-ONLY to this repo and usable only from it — a PERMANENT, human-supervised ALTERNATE to autonomous mode (not a stopgap): not part of the plugin, spec, template, or fleet, and not synced.
Security AStatic scan found no risk patternsHow grading works ›

From the source SKILL.md

You are the bottom pane of the overseer: the interactive Claude session that starts and supervises a deterministic daemon. You keep several other tracks moving in parallel, each in its own tmux session, but you do no track work yourself and you never poll the tracked sessions on a timer — that context-burning inline-worker pattern is exactly the historical failure this design defeats. The mechanical watching runs in the top-pane daemon (a dumb, token-free Python process that cannot blow up a context); you manage the track list, start the daemon, and relay what it surfaces.

What this skill does

Overseer is a community-contributed Claude Code skill in the discovery sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/overseer/ and loads when your prompt matches the skill's trigger.

Who uses this skill

The Overseer Claude Code skill is built for product managers, product designers, and cross-functional teams planning, shipping, and measuring product features. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 152,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/overseer
curl -L https://claudskills.com/skills/overseer/SKILL.md \
  -o ~/.claude/skills/overseer/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/overseer/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/overseer/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\overseer\SKILL.md on Windows. See the full install guide for step-by-step instructions.

Telegram

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Frequently asked questions

How do I install the Overseer Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/overseer/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.
What does the Overseer skill do?
Keep multiple parallel livespec tracks moving via a TWO-PANE model: a deterministic top-pane daemon (`overseerd`) that watches every tracked tmux session's context %, injects an ESCALATING wrap-up at threshold, and atomically restarts a session ONLY once that session declares itself `ready` (exit + `claude --dangerously-skip-permissions -n <topic>` + re-kick from `plan/<topic>/handoff.md`) — THE CARDINAL RULE: the daemon NEVER restarts a session that has not declared itself ready, because only the session knows whether it is safe to kill; one that declares nothing is REPORTED as not responding and left alone — and this THIN bottom pane, the interactive Claude overseer, which starts the daemon, manages the discovery-driven auto-managed track list via a JSONL topic↔tmux mapping (`add`/`remove`/`unassign`/`start`), and RELAYS the tracks the daemon reports as non-blocking text naming the tmux session + pane to go to. NOTIFY, NEVER BLOCK: a question may only be asked by the actor that OWNS the decision, so the overseer never raises a blocking prompt for a TRACK's decision (answer that in the track's own pane); it prompts only for decisions it owns (add/remove/unassign/start, threshold). The list is discovered from each watched repo's `plan/` dir; declaration is OUT-OF-BAND on the filesystem — ONE `.overseer-state` file valued `ready` / `blocked: <reason>` / `winding-down` — never pane text. The daemon never auto-spawns a session for an UNASSIGNED plan (first launch is deliberate) and never force-kills any session. The overseer does NO track work, never polls tracked sessions on a timer, never hand-codes. LOCAL-ONLY to this repo and usable only from it — a PERMANENT, human-supervised ALTERNATE to autonomous mode (not a stopgap): not part of the plugin, spec, template, or fleet, and not synced.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Overseer skill?
Use Overseer when your Claude Code task falls under the Product category — specifically in the discovery area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Overseer" or describe the task and let Claude pick). Browse related skills at /category/product/.
What is a Claude Code skill and how does the Overseer skill fit in?
A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Overseer is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Product category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA
thewoolleyman. (2026). Overseer [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/overseer/
BibTeX
@misc{overseer-2026,
  author    = {thewoolleyman},
  title     = {Overseer [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/overseer/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge
[![ClaudSkills](https://claudskills.com/badge/overseer.svg)](https://claudskills.com/skills/overseer/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/overseer.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/overseer.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Overseer"></iframe>

Security scan

Grade A · scanned 2026-07-16 — free static scan against the OWASP Agentic Skills Top 10.

No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›

Show this grade on your repo (click to copy):

[![Security: A](https://img.shields.io/badge/Security-A-2e7d32)](https://claudskills.com/skills/overseer/#security)

Free. No spam. Unsubscribe in one click.

More Product skills

Browse all Product skills in the ClaudSkills registry, or explore these other picks from the same category:

Browse all Product skills → Top 100 skills
Part of ClaudSkills — the open registry for Claude Skills & Claude Code Skills.  ·  What's New  ·  Install guide  ·  About  ·  llms.txt

Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore