gasserane/personal-skills

daily-brief

Produce a scannable morning briefing for Ane (Senior MEL/SRHR Specialist at IPPF).

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/gasserane/personal-skills --skill daily-brief

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Daily Brief

Produces a 60-second morning briefing. Outputs in a fixed structure so Ane can scan and act without re-parsing formatting every day.

When to use

Trigger when the user opens the day, mentions a morning briefing, or asks what today looks like. Do not use for end-of-day summaries — route to journal-reflection for that.

Required inputs

If no MCP is connected, ask the user for any of these that are missing before producing output. Ask in one batch, not iteratively.

  1. Today's calendar (times, attendees, purpose)
  2. Top 1-3 priorities carried from yesterday or the week plan
  3. Overdue or blocked items (what is stuck, since when)
  4. Decisions pending (what needs a call from Ane, by when, for whom)
  5. Energy state in one word (fresh / tired / scattered / focused)

If calendar MCP or email MCP is available, pull directly instead of asking.

Output format

Produce exactly these sections, in this order, each under the named heading:

Top priority today One sentence. The single most important thing. Lead with the verb.

Calendar Chronological list. For each: time, meeting, one-line prep note (who, goal, what Ane owns going in). Skip pure-FYI meetings.

Overdue / blocked Bulleted. For each: what it is, what is blocking it, the next action and owner. Flag any item stuck more than 7 days.

Decisions pending Bulleted. For each: the decision, by when, what Ane needs to decide, what information is missing.

Energy check One sentence matched to the state the user reported. If "scattered", propose the one thing to drop today. If "tired", propose the one meeting to protect and the one to reschedule. If "fresh", propose the hardest thing to front-load.

Data gaps List anything the user did not provide that meaningfully affects the brief. Use the format: ⚠️ Data gap: [what is missing] — [why it matters] — [recommended action]. Omit this section if there are no gaps.

Writing rules

Follow the house style from CLAUDE.md: active voice, sentences under 25 words, no em-dashes, no hedging, no performative softeners. Lead every line with the actor or the action. No abstract openings.

Limitations

Do not invent calendar items, decisions, or blockers. If the user did not provide a section's inputs and no MCP supplies them, leave the section empty and flag it as a data gap. Do not pad.

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
gasserane
コミュニティ

ann

Ann — Convener for MEL/SRHR work. Use when Ane brings any analytical, evaluation, SRHR, or structured-output task. Ann classifies task complexity, queries the MEL Wiki, retrieves knowledge, creates an implementation plan (verifies with user for complex tasks), coordinates with Vi for execution, runs a 5-point quality gate, and delivers. General-purpose — not tied to any specific project.

導入数
1
GitHub Stars
2
更新日
9月24日
gasserane
コミュニティ

capture-desktop

Capture a claude.ai Desktop session into the MEL file system. Use when Ane finishes a session in the Claude Desktop app and wants the work captured on the device — triggered by "/capture-desktop", "capture this desktop session", "I did this on Claude desktop", "save my desktop work", "import from claude.ai". Paste-driven; no cloud API exists. Stages a local transcript, classifies content into deliverables, decisions/rules, project-knowledge changes, and full log, then files each to its home. Aut

導入数
1
GitHub Stars
2
更新日
9月24日
gasserane
コミュニティ

grade-system

Apply substantive quality and reliability grading to Ane''s MEL/SRHR system (Ann/Vi/Li/Researcher team + wiki + harness + three-repo architecture): letter grades on 9 components and 10 dimensions plus OECD-DAC adapted criteria, three concrete risks, what an external evaluator would still want, and recommendations for moving the grade, with a mandatory self-grading bias note. Use when Ane types /grade-system, /grade, /quality-grade, /rate-system, or asks how good the system is. Honest grading, no

導入数
1
GitHub Stars
2
更新日
9月24日
gasserane
コミュニティ

grill-mel

A relentless one-question-at-a-time interview to stress-test a MEL/SRHR design before building it: a theory of change, evaluation design, indicator set, results framework, proposal angle, or learning question. Walks the MEL branches (assumptions tested vs untested, OECD-DAC criteria, output/outcome/impact, disaggregation, lens application, data gaps, audience tier), recommends an answer for each question, and flags any fact it cannot source. Use when Ane says "grill my ToC", "stress-test this ev

導入数
1
GitHub Stars
2
更新日
9月24日