Settle Sweep
Answers "what can I settle", "what's open", "which threads can I close" with one line per open T3 Code thread, settle it, it needs him, or still running, read from T3's own database. Use for any quick pass over his open threads; the full page of every thread is thread-explainer.
Install
npx skills add thatmike1/claude-skills --skill settle-sweepgit clone --depth 1 https://github.com/thatmike1/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/settle-sweep ~/.claude/skills/settle-sweepPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# settle sweep Mike leaves threads open after they are done, and the sidebar fills with ones he could close. The sweep tells him which, in a reply he can act on without opening any of them. ## Run `node ~/.claude/skills/settle-sweep/scripts/sweep.mjs` prints every open thread, newest first: title, status, how long it has been quiet, its link, his last real message and the agent's last words. Settled, snoozed, archived and subagent threads are left out, and so is the thread you run in. ## Judge One line per thread, led by its link exactly as printed, so the line is clickable: - `settle: why` — finished, or its next step already lives in a bead or on his hub. - `needs you: the decision` — the last reply asks him something, or he wrote last and nothing answered. - `running: what comes back` — a run, delegated agent or job it started is still going. His latest real message beats the agent's tail when they disagree. Date-bound wording (tonight, tomorrow) is checked against today; a step whose day has passed is stale. When 400 characters of last words are not enough to judge, read that one thread with `t3_thread_read` (low `limit`, `maxCharsPerItem` around 1500) rather than guessing. The script stays the first pass: one call covers every thread, where T3's tools would need a list plus a read per thread. ## Settling You cannot settle threads yourself: T3's database has one writer, and Mike clicks. Lead the reply with the count he can settle, then the lines, settles first.
Details
- Skill name
settle-sweep- Repository
- thatmike1/claude-skills
- Path
settle-sweep/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Settle Sweep skill do?
Answers "what can I settle", "what's open", "which threads can I close" with one line per open T3 Code thread, settle it, it needs him, or still running, read from T3's own database. Use for any quick pass over his open threads; the full page of every thread is thread-explainer.
How do I install the Settle Sweep skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add thatmike1/claude-skills --skill settle-sweep. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Settle Sweep popular?
It lives in thatmike1/claude-skills, which has 10 GitHub stars and 1 forks.
Related skills
Afk Prompt
10thatmike1/claude-skills
Write a copy-paste prompt that hands one or more tasks (usually beads issues) to a fresh Claude instance to run autonomously while the user is away — no questions, no waiting for input. Includes picking which tasks are safe to run unattended. Use when the user says they're going AFK (shower, lunch, errand, overnight), asks "which tasks can just run without me", or wants an autonomous/batch prompt. For attended sessions the user will steer, use the live-prompt skill instead.
AI CV Scanner
10thatmike1/claude-skills
Mine Claude Code conversation history to answer questions about your AI experience. Scans session indexes, spawns parallel subagents to deep-dive relevant conversations, and drafts evidence-based answers. Use when user mentions CV, AI experience, questionnaire, scan my conversations, or needs to document their AI usage.
Arena
10thatmike1/claude-skills
Give several T3 child candidates the same prompt, rank them against a rubric written before they run, pick a base and graft the best of the rest into it. Run with /arena when one attempt at a non-trivial artifact would lock in the wrong shape.
Thread Explainer
10thatmike1/claude-skills
A page of every open T3 Code thread, sorted into lanes by what each one wants from Mike, read straight from T3's own database. Use when he asks for the thread explainer, what his open threads want from him, or to catch up on all of them at once.
Hex
8hex-inc/hex-skills
Router for all Hex operations from CoCo. Use for ANY request involving Hex: create Hex project, build Hex app, deploy Hex app, publish Hex app, run Hex notebook, Hex Threads, migrate Tableau to Hex, migrate Looker to Hex, Hex data connection, Hex setup, install Hex CLI, Hex authentication, Hex cell, Hex agent, Hex context, Hex guide, Hex eval, business analytics question in Hex, notebook authoring in Hex, build dashboard in Hex, create visualization in Hex, Hex context engineering, endorse tables in Hex, Hex warehouse descriptions, Hex semantic model, Hex agent gave the wrong answer, improve H
Connect Cdc Mongodb
9redpanda-data/skills
Streams change data capture from MongoDB into Redpanda or Kafka using Redpanda Connect's mongodb_cdc input, built on MongoDB Change Streams over a replica set or sharded cluster. Use when configuring mongodb_cdc, setting up Change Streams, enabling an initial or incremental snapshot alongside live streaming, backfilling a collection on demand through a signal collection, choosing between update_lookup and pre_and_post_images document modes, or checkpointing with resume tokens in a cache resource. Also covers Redpanda Enterprise destination features like Iceberg Topics, Tiered Storage, and serv
Browse the most popular Claude skills, all databases skills, or write your own with the skills generator.