跳到正文
cccskills
免费在 GitHub 公开

calendar-defrag

Defragment a work calendar through a tool-using agent — find the meeting debt, propose the consolidation, and (approval-gated) execute the moves. Use when asked to defrag my calendar, get me focus time, audit my meetings, or fix my week. Produces the calendar audit (cost per meeting, fragmentation map), a defrag proposal with focus blocks, and an approval-gated execution plan.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(2)

  • SKILL.md4.8 KB
  • references/worked-example.md3.0 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Calendar Defrag Skill

Calendars fragment the way disks did: nothing big fits anywhere, and every week costs more than it returns. This skill audits the week like a capacity planner (what each meeting costs, what the fragments waste), proposes the defrag, and — only with approval — executes the moves through an agent with calendar access.

What This Skill Produces

  • The audit — every recurring meeting priced (hours × attendees), fragmentation map of the week, the largest contiguous focus block currently possible
  • The defrag proposal — meetings to shorten / merge / make async / decline-with-note, moves that consolidate fragments into 2h+ focus blocks
  • The execution plan — exact calendar operations, shown before any are made

Required Inputs

Ask for these if not provided:

  • Calendar scope — which week(s), work hours, timezone
  • The user's real priorities — defrag serves deep work on something; name it
  • Untouchables — meetings that are politically or contractually fixed
  • Meeting-owner etiquette — may the agent propose times to others, or only move solo/owned events?

Framework

  1. Price everything: duration × attendees = cost; recurring cost × 26 = the six-month bill. Print it — the bill changes minds that advice can't.
  2. The fragment rule: a gap under 45 minutes is lost time; count the week's fragment waste in hours.
  3. The defrag moves, in preference order: delete (with a note) → make async (doc + comments) → halve the duration → merge with an adjacent ritual → move to the edge of the day.
  4. Focus blocks are placed first — 2h+ blocks at the user's stated peak hours; meetings pack around them, not vice versa.
  5. Respect other people's calendars: moves affecting others become proposals (draft messages), never unilateral moves.

Output Format

Calendar Defrag: week of [date]

The bill: [n] meeting-hours (× attendees = [n] person-hours) · fragments waste [n]h · largest focus block today: [n]min

MeetingCostVerdictMove
After defrag: [n] focus blocks ([hours]), [n]h returned per week.

Quality Checks

  • Every recurring meeting carries its six-month price
  • Every removal has a draft note to the organizer — silent declines burn trust
  • Focus blocks land on stated peak hours, not leftovers
  • Moves touching other people are proposals with drafts, not actions

Anti-Patterns

  • Do not judge meetings by name — a "sync" can be load-bearing; price and ask what it decides
  • Do not create focus blocks and leave them unlabeled — an empty slot gets colonized in a day
  • Do not defrag someone into back-to-back meetings to serve the user — fragmentation exported is not fragmentation solved
  • Do not touch the untouchables list, even when they're obviously the problem — name it, don't move it

Execution

For agents with calendar access (Google/Microsoft APIs or UI). Without tools, the audit + proposal is the deliverable. Rules per SKILLSPEC.md §5.

Preconditions

  • The defrag proposal has been produced and explicitly approved by a human, line-item vetoes honored.
  • Calendar access authenticated; the week(s) in scope named; the untouchables list confirmed.
  • The execution plan (exact create/move/shorten/decline operations) displayed and confirmed.

Allowed actions

  • Create the approved focus blocks (named, with decline-meetings visibility set as approved).
  • Move or shorten only events the user owns, per the approved plan.
  • Decline events on the approved list, attaching the approved note.
  • Save (never send) the drafted proposals for meetings owned by others.
  • Nothing else: no deleting events outright, no touching other calendars, no auto-accepting, no changes outside the approved week(s).

Verification

  • Re-read the week: focus blocks exist at approved times; moved events at new times; declined events show the note; nothing outside the plan changed.
  • Report the before/after fragment-waste numbers.

Rollback

  • Every move is recorded (event, old time, new time) — undo restores old times and removes created blocks.
  • Stop and ask a human if: an event was modified by someone else after approval, a move conflicts with a new event, or any API action fails.

Example Trigger Phrases

  • "Defrag my calendar."
  • "Get me focus time."
  • "Audit my meetings."
  • "Fix my week."

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360 feedback for a colleague, design a feedback survey, or produce a feedback report. Produces either a complete survey instrument with rating scales and open-ended questions, or a structured narrative feedback report with themes, strengths, and development areas.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14822026年10月23日 更新

Decode a 401k or workplace retirement plan — the real cost of its funds, the match's fine print, vesting math, and the plan features worth using or avoiding. Use when someone asks 'is my 401k any good', 'decode my 401k plan', 'which funds should I look at', or 'what fees am I paying'. Produces a fee decode in dollars-over-time, match and vesting math, a fund-lineup triage by cost, and the questions for HR or the plan administrator.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14822026年10月23日 更新

Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use when asked to set up an experiment, design an A/B test, calculate sample size, or interpret test results. Produces a complete test plan with hypothesis, variant definitions, sample size, duration estimate, guardrail metrics, and a results interpretation guide.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14822026年10月23日 更新

Analyse a finished A/B test and write the readout — the result, whether it's statistically and practically significant, what it means, and the ship/no-ship call. Use when asked to analyse experiment results, write an A/B test readout, interpret test data, or decide whether to ship a variant. Produces a clear verdict with the lift and confidence, segment cuts, the risks (peeking, novelty, sample), and a recommendation. Distinct from planning a test — this reads results.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14822026年10月23日 更新

Build or tailor an academic CV for faculty, postdoc, research or fellowship applications: publications, grants, teaching, supervision and service in the order the field expects, with consistent citations. Use when asked to write my academic CV, update my CV for a lectureship, tenure-track or postdoc application, format my publications list, or adapt my academic CV for an industry research role. Produces the full academic CV, a field-appropriate section order, a clean publications list in one citation style, and a two-page summary version when asked.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14822026年10月23日 更新

Generate a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan. Produces a prioritised checklist with pass/fail assessments and specific fixes.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14822026年10月23日 更新

查看 mohitagw15856 的全部技能

报告此技能的问题