本文へ移動
cccskills
無料GitHub で公開

communication

Draft professional emails, feedback (SBI/BID), difficult conversations, meeting notes, and escalation templates. Covers tone matrix, cross-cultural communication, Slack/Teams async patterns, and structured notes from raw transcripts.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md10.3 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Communication

Professional writing that gets results. Based on Harvard Business Review, Radical Candor (Kim Scott), Crucial Conversations (Patterson et al.), Amazon Working Backwards, and Google Project Aristotle.

Sub-Commands

CommandDescription
draftDraft an email, message, or document from context
polishPolish tone, cut filler, strengthen ask
feedbackDraft feedback using SBI/BID model
notesStructure meeting notes from raw transcript or notes
escalateDraft escalation with clear facts, impact, and request
replyReply to a message with appropriate tone

Workflow

Step 1 — Identify audience & context

  • Who is the recipient? What is your relationship?
  • What is their communication style (direct/indirect, formal/casual)?
  • What is the power dynamic (peer, manager, report, client, exec)?
  • What has happened before this communication?

Step 2 — Choose tone from matrix

ContextToneSalutationClosing
Internal peerCasual-direct"Hi [Name]""Thanks"
Internal managerProfessional"Hi [Name]""Thanks"
Cross-teamProfessional"Hi [Name]""Best"
Client (established)Cordial"Hi [Name]""Best regards"
Client (new)Formal-cordial"Dear [Name]""Best regards"
Executive / VP+Formal"Dear [Title] [Last]""Sincerely"
EscalationFirm, respectful"Hi [Name]""Regards"
ComplaintCalm, professional"Hi [Name]""Best regards"

Step 3 — Select channel

ScenarioChannel
Simple question, needs quick answerDM (Slack/Teams)
Team-wide decision or updatePublic channel
Sensitive feedbackIn-person or video call
Complex explanationLoom or shared doc
Formal request or escalationEmail
Needs paper trailEmail
External clientEmail

Step 4 — Draft using structure

Email structure:

  1. Subject: [Verb] + [Topic]. Max 50 chars. Prefix: [Request/Update/Follow-up/Escalation]
  2. Context: reference previous communication in one sentence
  3. Purpose: the ask or update in the FIRST paragraph
  4. Detail: supporting info, bulleted if > 3 items
  5. Next step: who does what by when
  6. Closing: matched to relationship

Step 5 — Review checklist

  • Subject ≤ 50 chars, prefixed with [Request/Update/Follow-up/Escalation]
  • One explicit ask per message, with deadline
  • Length ≤ 150 words internal, ≤ 200 client
  • Tone matches recipient in matrix
  • Zero filler: no "hope this finds you well", "just checking in", "I wanted to reach out"
  • No passive-aggression: no "as per my last email", "per our conversation"
  • Blame externalized: "The deployment failed" not "You failed"

Step 6 — Send at appropriate time

  • During recipient's working hours (respect timezone)
  • Avoid Friday afternoon (unless urgent)
  • Avoid right before lunch or end of day

Step 7 — Follow up

  • If no response in 48h, send ONE follow-up
  • Format: same subject, first line = "Gentle ping on this — do you need anything from me to move forward?"

Filler Phrases to Delete (exact replacements)

DeleteReplace with
"I hope this email finds you well"Nothing. Start with the purpose.
"I just wanted to reach out"State the purpose directly.
"Per my last email"Restate the ask directly.
"Just checking in""Following up on [specific thing] — do you have an ETA?"
"Quick question"Ask the question directly in the subject.
"Sorry to bother you""When you have a moment, [ask]"
"To be honest"Everything you write should be honest. Drop the phrase.
"I think" / "I feel""I recommend" / "The data shows" — be direct.

Feedback (SBI Model)

  • Situation: when and where
  • Behavior: what exactly was said/done (observable, not interpreted)
  • Impact: what effect it had

Rules:

  • Always in private for redirecting feedback
  • As close to the event as possible
  • Focus on actions, not personality
  • End with a question: "Does that resonate?"
  • Ask permission first: "Can I share some feedback?"
  • One topic per session
  • Never: "you always", "you never", comparison to others

Meeting Notes Format

Every meeting produces exactly four things:

## [Topic] — [Date]

## Summary
One paragraph. A non-attendee should understand what happened.

## Decisions
- [DECIDED] We will use X instead of Y because Z

## Action Items
| Owner | Task | Due |
|-------|------|-----|
| @name | Specific task description | 2026-05-15 |

## Open Questions
- [QUESTION] ... → @owner to decide by Friday

## Risks
- Risk description → mitigation

Rules:

  • Notes sent within 2 hours of meeting end
  • Every action has a named owner + ISO date deadline
  • No verbatim discussion. Strip to 4 sections.

Cross-Cultural Communication

CultureDirectnessFormalityTimeFeedback
USDirectInformalStrict deadlinesDirect + positive
JapanIndirectFormalPunctualIndirect, private
GermanyDirectFormalStrictDirect, factual
BrazilIndirectRelationship-firstFlexibleIndirect, relationship
IndiaContext-dependentFormal with seniorsFlexibleIndirect, hierarchical

Async Communication Protocols

  1. Default to async: assume response within 24h (not instant)
  2. No "hi" messages: include context + question in first message
  3. Status updates: visible in project tool, not via DM
  4. Meeting notes: posted within 1h. Action items with owners + deadlines.
  5. Decision log: key decisions documented with rationale + date + decider.

Meeting Facilitation

  • Agenda sent 24h before. Start with purpose + desired outcome.
  • Timebox: 15min (standup), 30min (decision), 60min max (workshop)
  • Parking lot: off-topic items written down for later
  • Round-robin: every voice heard before discussion

Error Handling

CauseFix
Recipient didn't respond in 48 hoursSend one follow-up with same subject. First line: "Gentle ping on this — do you need anything from me to move forward?"
Email draft is too long (>200 words client, >150 internal)Cut to essentials. Move details to bullet points. Complex topics → Loom video or shared doc.
Tone feels passive-aggressive on re-readReplace "per my last email" with direct restatement. Remove "as I mentioned." Check for blame language.
Cross-cultural miscommunication riskCheck culture table. Japanese: add polite preamble, drop subject pronouns. German: complete information, use Sie. French: context before ask.
Emotional reaction while draftingSave draft. Wait 1 hour minimum. Revise before sending. Remove all loaded language.
Vague action items after meetingEvery action item must have: named owner + ISO date deadline + specific verb. No "we should think about."
Feedback received negativelyCheck SBI structure: Situation (when/where) + Behavior (observable) + Impact (effect). End with "Does that resonate?" Never "you always/never."
Escalation email ignored by leadershipStructure: clear facts first, business impact second, specific request third. Keep under 150 words. No blame. Include deadline.

Anti-Patterns

Anti-PatternWhy It FailsFix
No clear askReader doesn't know what to doState CTA explicitly in first paragraph
Reply-all for 1:1 mattersNoise for others, exposes private contextDM or email only relevant person
Wall of textNobody reads itMax 2 paragraphs. Bullets for > 3 items. Loom for complex.
Sending when emotionalRegret within the hourDraft, wait 1h, revise, send
CC'ing manager unnecessarilyPolitical escalationOnly CC when they need to know
False urgency ("URGENT" / "ASAP")Boy who cried wolfReserve for actual outages. Use specific deadline otherwise.
Over-apologizingUndermines confidenceApologize once sincerely, pivot to solution
Vague follow-ups ("Checking in")No context, no action"Following up on X — ETA for Y?"

Constraints

  • Max 150 words internal, 200 for client emails
  • No passive-aggressive language
  • No assigning blame to a person
  • Signature: Name, Title, Company, Phone. No quotes. No ASCII art.

Checklist

  • Audience identified (executive, peer, client, direct report)
  • Purpose clear: inform, persuade, align, or escalate
  • Tone matched to relationship and context
  • Key action item or ask stated explicitly near the top
  • Proofread for ambiguity and unnecessary jargon

Sources

  • Radical Candor — Kim Scott
  • Crucial Conversations — Patterson, Grenny, McMillan, Switzler
  • Harvard Business Review — Communication guides
  • Center for Creative Leadership — SBI model
  • Amazon Working Backwards methodology
  • Google Project Aristotle — Psychological safety
  • Thanks for the Feedback — Stone & Heen

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Apply professional, premium UI/UX design standards when building or styling web interfaces. Use this skill when the user asks to create a website, landing page, web app, dashboard, UI component, or any visual interface — or when they ask to make something look better, more professional, or more beautiful. Covers visual hierarchy, typography, color systems, layout, spacing, motion, dark mode, responsive design, and conversion patterns. Activate even when the user doesn't say "design" — if they're building a web frontend, these standards apply.

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

api-forge

無料

Design REST/GraphQL APIs with OpenAPI 3.1, error handling, pagination, rate limiting, webhooks, and idempotency. Use when user asks to design an API, create endpoints, define REST/GraphQL schema, or generate OpenAPI spec. Do NOT use for database schema design, frontend API integration, or non-HTTP protocols (gRPC, WebSocket, MQTT).

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Implement authentication and authorization with OWASP Top 10 standards, OAuth 2.0 + OIDC, WebAuthn/Passkeys, session management, and RBAC/ABAC. Use when user asks to implement login, signup, authentication, authorization, JWT, OAuth, SSO, passkeys, MFA, or role-based access. Do NOT use for API key management (use api-forge), encryption at rest, or network-level security (firewalls, WAF).

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

Generate brand guidelines, design systems with design tokens (W3C format), creative direction (SCAMPER, Design Thinking, TRIZ), and design briefs with scope and success criteria.

日本語の概要は準備中です。原文の説明を表示しています。

EliasOulkadi/shokunin1142026年10月5日 更新

EliasOulkadi のスキルをすべて見る

このスキルの問題を報告する