菜单
Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when someone wants to decide whether a meeting is worth calling, price a meeting in dollars, build a timeboxed agenda with desired outcomes, or turn messy meeting notes into owned action items — or says "should this be a meeting", "/cs:meeting-prep", or "/cs:meeting-actions". Runs a cost gate (ASYNC / NOT-READY / MEET), builds a decision-first agenda, and extracts an owner + due-date checklist that flags every orphan.
Use when someone wants to plan a deep work day, time-block their calendar or task list, budget or cut shallow work, protect focus hours, track deep-work sessions and streaks, run an end-of-day shutdown ritual, or says "/deep-work" or "/time-block". Classifies tasks deep vs shallow, builds an energy-first time-blocked schedule that refuses deep demand past the 4-hour ceiling, batches shallow work into at most two windows, and logs focus sessions against a weekly target.
Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says "/cs:weekly-review". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.
Convert a rambling description of a desired outcome into one polished, autonomous /goal prompt ready to paste into a fresh session. Use when the user says "/fable-goal", "turn this into a goal prompt", "write me a fable prompt", "write the prompt that builds X", or rambles about something they want made and asks for the prompt that makes it happen. The output is a single copy-paste prompt, never the build itself. Do NOT use when the user wants the thing built right now in this session — only when they want the PROMPT that will make it happen in a fresh session.
Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle, memory/skill consolidation, or says things like 'make my agent better the more I use it', 'review my past sessions', 'learn my preferences', 'consolidate what you learned', 'run the sleep cycle', or wants to schedule offline self-optimization. Drives the skillopt_sleep engine: harvest past sessions -> mine recurring tasks -> replay offline -> consolidate validated CLAUDE.md and SKILL.md behind a held-out gate.
| name | resume |
| description | Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment. |
| command | /ar:resume |
Resume a paused or context-limited experiment. Reads all history and continues where you left off.
/ar:resume # List experiments, let user pick
/ar:resume engineering/api-speed # Resume specific experiment
If no experiment specified:
python {skill_path}/scripts/setup_experiment.py --list
Show status for each (active/paused/done based on results.tsv age). Let user pick.
# Checkout the experiment branch
git checkout autoresearch/{domain}/{name}
# Read config
cat .autoresearch/{domain}/{name}/config.cfg
# Read strategy
cat .autoresearch/{domain}/{name}/program.md
# Read full results history
cat .autoresearch/{domain}/{name}/results.tsv
# Read recent git log for the branch
git log --oneline -20
Summarize for the user:
Resuming: engineering/api-speed
Target: src/api/search.py
Metric: p50_ms (lower is better)
Experiments: 23 total — 8 kept, 12 discarded, 3 crashed
Best: 185ms (-42% from baseline of 320ms)
Last experiment: "added response caching" → KEEP (185ms)
Recent patterns:
- Caching changes: 3 kept, 1 discarded (consistently helpful)
- Algorithm changes: 2 discarded, 1 crashed (high risk, low reward so far)
- I/O optimization: 2 kept (promising direction)
How would you like to continue?
1. Single iteration (/ar:run) — I'll make one change and evaluate
2. Start a loop (/ar:loop) — Autonomous with scheduled interval
3. Just show me the results — I'll review and decide
If the user picks loop, hand off to /ar:loop with the experiment pre-selected.
If single, hand off to /ar:run.