Live Prompt
Write a copy-paste prompt that hands a task (usually a beads issue) to a fresh Claude instance the user will actively work with, in either collaborative (discuss-approach-first) or off-the-leash (implement-end-to-end) mode. Use when the user says "give me a prompt", "prompt for <task-id>", or wants to start a fresh instance on a task. For unattended runs (user going AFK), use the afk-prompt skill instead.
Install
npx skills add thatmike1/claude-skills --skill live-promptgit clone --depth 1 https://github.com/thatmike1/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/deprecated/live-prompt ~/.claude/skills/live-promptPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Live Prompt
Write a short prompt the user pastes into a fresh Claude Code instance to start it on a task. The fresh instance has zero context — but the beads task usually has plenty, so the prompt's job is to point, not to re-explain.
## Pick the mode
Two modes. When the task state makes the mode obvious — the bead or memory carries a locked approach (off the leash), or the approach is visibly open (collaborative) — pick it and say which you picked. Ask one short question ("collaborative or off the leash?") only when it's genuinely ambiguous.
**Collaborative (leash on)** — approach/architecture is still open. The instance reads the task, then discusses before writing any code. Lighter than /grill-me: short back-and-forth, one topic at a time, no relentless interrogation. End the prompt with the handover signal: once the approach is settled, the user lets it implement.
**Off the leash** — decisions are locked. The instance claims, implements, runs gates, commits, reports. Only use when the task description genuinely contains the locked-in approach.
## Structure (both modes)
1. **Task pointer first**: name the beads issue, tell the instance to invoke the beads skill, read the task, and claim it (`bd update <id> --claim`). If decisions live in the description, say "the decisions are in the description — don't relitigate them."Details
- Skill name
live-prompt- Repository
- thatmike1/claude-skills
- Path
deprecated/live-prompt/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Live Prompt skill do?
Write a copy-paste prompt that hands a task (usually a beads issue) to a fresh Claude instance the user will actively work with, in either collaborative (discuss-approach-first) or off-the-leash (implement-end-to-end) mode. Use when the user says "give me a prompt", "prompt for <task-id>", or wants to start a fresh instance on a task. For unattended runs (user going AFK), use the afk-prompt skill instead.
How do I install the Live Prompt skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add thatmike1/claude-skills --skill live-prompt. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Live Prompt 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.
Orchestrate
10thatmike1/claude-skills
Team-lead orchestrator: whichever frontier-class Claude model leads your session plans, routes, and verifies while cheaper Claude or Codex workers execute. Use for: orchestrate, delegate, conductor mode, save tokens, multi-agent.
Insights Report
9lingengyuan/my-skills
Generate a usage insights report from local Claude Code, Codex, pi, and omp session transcripts. Use when the user asks for an insights report, session analysis, usage review, "how do I work with agents", or runs /insights-report.
Peek
10thatmike1/claude-skills
Read another agent session's transcript straight from its log on disk, with zero footprint on the observed session, and list which sessions are running right now. Covers Claude Code, Codex and the Antigravity CLI (agy/Gemini), and the T3 Code threads wrapped around any of them. Use before sending a message to another session, when observing or coaching a session that must stay untouched, when asked which T3 threads are still open or unsettled, or when asked to peek at, read, or follow what another session is doing.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.