Agent Skillsmohitagw15856/pm-claude-skills › body-double-session

body-double-session

GitHub

协助ADHD或执行功能障碍者启动并坚持任务,通过生成会话计划、伙伴邀请话术及单人替代方案,利用他人陪伴提升专注力。

exports/openclaw/body-double-session/SKILL.md mohitagw15856/pm-claude-skills

Trigger Scenarios

无法开始任务 请求身体双重陪伴 ADHD执行功能障碍

Install

npx skills add mohitagw15856/pm-claude-skills --skill body-double-session -g -y
More Options

Non-standard path

npx skills add https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/body-double-session -g -y

Use without installing

npx skills use mohitagw15856/pm-claude-skills@body-double-session

指定 Agent (Claude Code)

npx skills add mohitagw15856/pm-claude-skills --skill body-double-session -a claude-code -g -y

安装 repo 全部 skill

npx skills add mohitagw15856/pm-claude-skills --all -g -y

预览 repo 内 skill

npx skills add mohitagw15856/pm-claude-skills --list

SKILL.md

Frontmatter
{
    "name": "body-double-session",
    "homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/body-double-session.html",
    "metadata": {
        "openclaw": {
            "emoji": "🧠"
        }
    },
    "description": "Set up and run a body-doubling session — using another person's presence (in the room, on a call, or a chat check-in) to start and stay on the task your ADHD brain keeps bouncing off. Use when someone says 'I can't start this task', 'body double with me', 'I only work when someone's around', or has ADHD\/executive-dysfunction and a task that won't begin. Produces a session plan, the exact ask to send a body-double partner, and a solo fallback for when no one's available."
}

Body Double Session Skill

Body doubling — working alongside another person's presence — is one of the few ADHD strategies that reliably converts "I physically cannot start this" into "it's half done." It isn't accountability or supervision; the other person does nothing but exist nearby, and somehow the task that was impossible alone becomes possible. This skill sets one up properly: pick the right task, structure the session so the doubling actually helps (there's a way to do it wrong), write the slightly-awkward ask to a partner, and — because the partner isn't always available — build the solo approximations that borrow the same mechanism.

What This Skill Produces

  • A session plan: the task cut to a startable first step, session length, the start ritual, and how breaks work so momentum survives them
  • The partner ask, ready to send: what body doubling is, what you need them to do (almost nothing), format (in person / video / audio / async check-in), and duration — de-awkwarded
  • A format pick: which kind of doubling fits this task and this person (silent video coworking vs a start-and-check-in text vs someone physically there)
  • A solo fallback: the ways to fake the presence when no one's free (a coworking stream, a "just started, will report back" text, a scheduled call at the finish line)

Required Inputs

Ask for (if not already provided):

  • The task that won't start, and honestly why it's sticky (boring? ambiguous? scary? too big? all four?)
  • Who might body double (a friend, partner, an online coworking room, a coworker) and how comfortable the user is asking
  • What's worked before, if anything, and what killed past attempts (a chatty double who became a distraction is common)
  • Time available and the environment they'll do it in

Framework

  1. Cut the task to a startable atom. Body doubling starts things; it can't start a blob. Reduce the task to a first action small enough that beginning it is almost involuntary ("open the document and title it," not "write the report"). The double is the ignition; the atom is the fuel line.
  2. Pick the format by task and person. Deep silent work → silent video/in-person coworking. A dread task → someone who'll start with you then just be there. A day of scattered admin → async check-ins ("starting now" / "done, next"). The wrong format (a talker for deep work) turns a double into a distraction — match deliberately.
  3. Write the ask so it's easy to say yes to. The partner's job is tiny and the ask should say so: "I focus way better when someone's just there — can we hop on a muted video call for 45 min while we each do our own thing? You don't have to do anything." Low cost to them, easy yes. Reciprocity ("I'll double you back") makes it sustainable.
  4. Ritualize start and protect breaks. A tiny start ritual (cameras on, "starting in 3… go") flips the switch; a rule for breaks (they end, doubling resumes) keeps a pause from becoming the end. Name the finish so there's a landing.
  5. Fake the presence when you must. No partner? Approximations that borrow the mechanism: a live coworking stream/room, texting a friend "starting X, tell you when it's done," booking a call for right after the task (a soft deadline with a face attached), or working in a café. Weaker than the real thing, better than alone.

Output Format

## The session
Task, cut to its startable atom: …
Format (and why it fits): … · Length: … · Start ritual: … · Break rule: …

## The ask (send this)
[The low-cost, easy-yes message to your body double + a reciprocity line]

## If no one's available (solo fallbacks)
[Coworking room · start/finish check-in text · call-at-the-finish-line · café]

## The landing
[What "done for this session" is, so momentum has an endpoint]

Quality Checks

  • The task is cut to an atom small enough that starting is nearly involuntary
  • The format is matched to the task type, not defaulted — talkers aren't assigned to deep work
  • The partner ask is genuinely low-cost and easy to decline-or-accept, with reciprocity offered
  • A solo fallback exists — the skill still works when no human is available
  • There's a defined finish, so a session has a landing instead of trailing off

Anti-Patterns

  • Do not turn the double into a supervisor or accountability enforcer — presence is the mechanism, judgment kills it
  • Do not assign a chatty format to focus work; social doubling and deep-work doubling are different tools
  • Do not shame the user for needing this — body doubling is a legitimate, well-attested strategy, not a crutch to apologize for
  • Do not skip the atom step and double a vague blob — it'll fail and feel like the user's fault when it was the setup's
  • Do not treat inability-to-start as laziness anywhere in tone; executive dysfunction is real and the whole point

Related

[[deep-work-blocking]] for the solo-structure layer; [[task-triage-matrix]] to pick which atom first; [[masking-budget]] and [[meltdown-map]] for the ND context around it.

Version History

  • a462f61 Current 2026-08-12 13:22

Same Skill Collection

exports/openclaw/360-feedback-template/SKILL.md
exports/openclaw/401k-plan-decoder/SKILL.md
exports/openclaw/ab-test-planner/SKILL.md
exports/openclaw/ab-test-readout/SKILL.md
exports/openclaw/accessibility-audit/SKILL.md
exports/openclaw/account-plan/SKILL.md
exports/openclaw/acquirer-red-team/SKILL.md
exports/openclaw/ad-copy/SKILL.md
exports/openclaw/aeo-optimizer/SKILL.md
exports/openclaw/agenda-or-cancel/SKILL.md
exports/openclaw/agent-design-review/SKILL.md
exports/openclaw/agent-hiring-panel/SKILL.md
exports/openclaw/agent-observability-spec/SKILL.md
exports/openclaw/agent-severance/SKILL.md
exports/openclaw/agent-spec/SKILL.md
exports/openclaw/agm-in-a-box/SKILL.md
exports/openclaw/ai-ethics-review/SKILL.md
exports/openclaw/ai-eval-plan/SKILL.md
exports/openclaw/ai-feature-prd/SKILL.md
exports/openclaw/ai-product-canvas/SKILL.md
exports/openclaw/air-quality/SKILL.md
exports/openclaw/altitude-shifter/SKILL.md
exports/openclaw/ambiguity-resolver/SKILL.md
exports/openclaw/analyst-relations-brief/SKILL.md
exports/openclaw/announcement-card/SKILL.md
exports/openclaw/api-docs-writer/SKILL.md
exports/openclaw/api-test-plan/SKILL.md
exports/openclaw/api-versioning-strategy/SKILL.md
exports/openclaw/apology-letter/SKILL.md
exports/openclaw/architecture-decision-record/SKILL.md
exports/openclaw/architecture-diagram/SKILL.md
exports/openclaw/archive-strategy/SKILL.md
exports/openclaw/assumption-bounty/SKILL.md
exports/openclaw/assumption-mapper/SKILL.md
exports/openclaw/async-update-format/SKILL.md
exports/openclaw/auto-repair-estimate-decoder/SKILL.md
exports/openclaw/autopilot-charter/SKILL.md
exports/openclaw/awkward-message-helper/SKILL.md
exports/openclaw/behavior-intervention-plan/SKILL.md
exports/openclaw/benefits-decoder/SKILL.md
exports/openclaw/bennett-time-audit/SKILL.md
exports/openclaw/bid-tender-review/SKILL.md
exports/openclaw/board-deck-narrative/SKILL.md
exports/openclaw/board-game-designer/SKILL.md
exports/openclaw/board-game-night-planner/SKILL.md
exports/openclaw/board-minutes/SKILL.md
exports/openclaw/board-pre-read/SKILL.md
exports/openclaw/bom-cost-review/SKILL.md
exports/openclaw/bookkeeping-categorization/SKILL.md

Metadata

Files
0
Version
a462f61
Hash
041e031b
Indexed
2026-08-12 13:22

Home - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-12 20:01
浙ICP备14020137号-1 $Map of visitor$