Back to skills
SkillHub ClubWrite Technical DocsFull StackTech Writer

written-communication

Draft and edit high-signal written artifacts and produce a Written Communication Pack (brief, outline, draft email/memo/doc, canonical doc option, quality gate). Use for writing, written communication, memo, email, doc, async update, rewrite for clarity. Category: Communication.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars
36
Hot score
90
Updated
March 20, 2026
Overall rating
C2.1
Composite score
2.1
Best-practice grade
A88.4

Install command

npx @skill-hub/cli install liqiongyu-lenny-skills-plus-written-communication

Repository

liqiongyu/lenny_skills_plus

Skill path: skills/written-communication

Draft and edit high-signal written artifacts and produce a Written Communication Pack (brief, outline, draft email/memo/doc, canonical doc option, quality gate). Use for writing, written communication, memo, email, doc, async update, rewrite for clarity. Category: Communication.

Open repository

Best for

Primary workflow: Write Technical Docs.

Technical facets: Full Stack, Tech Writer.

Target audience: everyone.

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: liqiongyu.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

  • Install written-communication into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
  • Review https://github.com/liqiongyu/lenny_skills_plus before adding written-communication to shared team environments
  • Use written-communication for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.

Original source / Raw SKILL.md

---
name: "written-communication"
description: "Draft and edit high-signal written artifacts and produce a Written Communication Pack (brief, outline, draft email/memo/doc, canonical doc option, quality gate). Use for writing, written communication, memo, email, doc, async update, rewrite for clarity. Category: Communication."
---

# Written Communication

## Scope

**Covers**
- Turning messy notes into a clear **email, memo, doc, or async update**
- Making the **“how”** explicit (what happens next, by whom, by when)
- Editing for **clarity at scale** (scanability, definitions, single source of truth)
- Creating/maintaining a **canonical doc** for an ongoing project

**When to use**
- “Draft an email to stakeholders explaining a change and what I need from them.”
- “Turn these bullets into a 1-page memo with a recommendation and next steps.”
- “Rewrite this doc to be clearer, shorter, and more actionable.”
- “Create a canonical doc as the source of truth for this project.”

**When NOT to use**
- You need **marketing/brand copy** (landing pages, ads) more than internal/executive clarity.
- You need a full product spec/PRD from scratch (use `writing-prds` or `writing-specs-designs`).
- You’re writing **legal/HR/regulated** communications without expert review.
- The real issue is alignment via facilitation (you may need a meeting/offsite plan, not a rewrite).

## Inputs

**Minimum required**
- Artifact type + channel (email / memo / doc / status update; where it will live)
- Audience (roles/seniority) + what they care about
- Goal + ask (inform/align/decide; what you want the reader to do, by when)
- Key context (facts, constraints, timeline, links) + what must be avoided (sensitivities)
- Source material (notes, existing draft, Slack threads, etc.)

**Missing-info strategy**
- Ask up to 5 questions from [references/INTAKE.md](references/INTAKE.md) (3–5 at a time), then proceed.
- If critical info remains missing, make explicit assumptions and offer 2–3 options (structure/tone/ask).

## Outputs (deliverables)

Produce a **Written Communication Pack** in Markdown (in-chat; or as files if requested):

1) **Message brief** (audience, goal, ask, constraints)
2) **Outline** (TL;DR + key points + “how/next steps”)
3) **Draft artifact** (email/memo/doc/status update) in final-ready format
4) **Canonical doc skeleton** (optional; when the project needs a single source of truth)
5) **Risks / Open questions / Next steps** (always)

Templates: [references/TEMPLATES.md](references/TEMPLATES.md)  
Expanded guidance: [references/WORKFLOW.md](references/WORKFLOW.md)

## Workflow (8 steps)

### 1) Intake + choose the lightest artifact
- **Inputs:** user request + [references/INTAKE.md](references/INTAKE.md).
- **Actions:** Clarify the channel and pick the smallest artifact that works (email vs memo vs doc vs status update vs canonical doc).
- **Outputs:** Message brief (draft) + artifact selection.
- **Checks:** You can answer: “Who is this for, and what should they do after reading?”

### 2) Lock the reader outcome + ask (one sentence)
- **Inputs:** brief.
- **Actions:** Write one sentence: “After reading, the audience will ____.” Make the ask explicit (decision/options, approval, feedback, or FYI) and include a deadline if relevant.
- **Outputs:** Outcome/ask line + decision/feedback request.
- **Checks:** The ask is unambiguous and doesn’t require a meeting to interpret.

### 3) Convert “what/why” into “how” (actionable next steps)
- **Inputs:** source material + outcome/ask.
- **Actions:** Identify the 3–7 concrete steps, responsibilities, and dependencies. If proposing a change, include what changes, what stays the same, and what happens next.
- **Outputs:** “How / Next steps” bullets (owner + date where possible).
- **Checks:** A reader could execute without asking “so what do you want me to do?”

### 4) Structure for skim (clarity at scale)
- **Inputs:** brief + next steps.
- **Actions:** Create a TL;DR, then headings in the order readers scan: Ask → Context → Details → Next steps. Use bullets, short paragraphs, and explicit labels.
- **Outputs:** Outline with headings.
- **Checks:** A skim-reader can capture the point in < 60 seconds.

### 5) Draft the artifact (write to be forwarded)
- **Inputs:** outline + templates.
- **Actions:** Draft in plain language; avoid jargon; put key numbers and decisions in writing. If this is ongoing work, link to (or create) the canonical doc.
- **Outputs:** Draft email/memo/doc/status update.
- **Checks:** The draft is safe to forward; it stands alone without verbal context.

### 6) “Letter to yourself” clarity pass (then rewrite for the audience)
- **Inputs:** draft.
- **Actions:** If the content is fuzzy, write a quick internal version (“what am I actually saying?”), then rewrite in the audience’s language and incentives.
- **Outputs:** Clarified rewrite with cleaner logic.
- **Checks:** The message has a single through-line; no contradictions or buried ledes.

### 7) Canonical doc check (single source of truth)
- **Inputs:** draft + project context.
- **Actions:** If readers will keep asking “where is the latest?”, create/update a canonical doc (links, owners, last updated, decisions, next update cadence).
- **Outputs:** Canonical doc skeleton or link section.
- **Checks:** There is one obvious place to find the current state and decisions.

### 8) Quality gate + finalize
- **Inputs:** full pack.
- **Actions:** Run [references/CHECKLISTS.md](references/CHECKLISTS.md) and score with [references/RUBRIC.md](references/RUBRIC.md). Add Risks/Open questions/Next steps.
- **Outputs:** Final Written Communication Pack.
- **Checks:** Clarity, actionability, and ownership meet the bar (≥ 3 on each rubric dimension).

## Quality gate (required)
- Use [references/CHECKLISTS.md](references/CHECKLISTS.md) and [references/RUBRIC.md](references/RUBRIC.md).
- Always include: **Risks**, **Open questions**, **Next steps**.

## Examples

**Example 1 (stakeholder email):** “Draft an email to exec stakeholders: the launch is slipping 2 weeks; we need approval to cut scope and a decision by Friday.”  
Expected: TL;DR + explicit ask/options + what changes + next steps with owners.

**Example 2 (project memo + canonical doc):** “Turn these notes into a 1-page memo that aligns the team on the new onboarding approach, and create a canonical doc outline for ongoing updates.”  
Expected: memo with recommendation + tradeoffs + next steps, plus a source-of-truth doc skeleton.

**Boundary example:** “Write a legal/HR disciplinary notice.”  
Response: decline to fabricate legal/HR guidance; request expert review; offer to help with neutral structure, tone, and clarity if the user provides approved language.


---

## Referenced Files

> The following files are referenced in this skill and included for context.

### references/INTAKE.md

```markdown
# Intake (Question Bank)

Ask **up to 5 questions at a time**, then proceed. If answers remain missing, state assumptions explicitly and offer 2–3 options.

## Minimum set (use first)
1) What are we writing (email/memo/doc/status update) and where will it live (Slack, email, Notion, Google Doc)?
2) Who is the audience (roles/seniority) and what do they care about (time, risk, cost, quality, morale)?
3) What is the goal and the **ask** (inform/align/decide)? What should the reader do, by when?
4) What are the key facts that must be included (timeline, decision, constraints, numbers, links)? What must be avoided (sensitivities, legal/HR constraints, confidential info)?
5) Constraints: length, tone (direct vs warm), formatting, deadline, and any “must-include” sections.

## Helpful follow-ups (pick what’s relevant)

### If it’s a decision request
- What decision options are on the table (A/B/C) and what’s your recommendation?
- What tradeoffs matter (speed vs quality, cost vs scope, risk vs upside)?
- What happens if we don’t decide by the deadline?

### If it’s a status update
- What changed since last update (progress, metrics, decisions)?
- What’s blocked and what are you doing about it?
- What are the explicit asks (who, what, by when)?
- When is the next update, and where is the canonical doc?

### If it’s a rewrite/edit request
- What must be preserved (facts, tone, intent)? What should change (shorter, more direct, more persuasive)?
- Target reading time / length (e.g., “< 2 minutes”, “< 300 words”)?
- Any example you want to match (a prior email, style guide)?

### If it’s an ongoing project
- Do we have a **single source of truth** doc? If not, where should it live and who owns updates?
- What links must be included (PRD/spec, tracker, decision log, dashboard)?


```

### references/TEMPLATES.md

```markdown
# Templates (Copy/Paste)

Use these templates to produce the Written Communication Pack deliverables.

## 1) Message brief (context snapshot)
- Artifact type + channel:
- Audience (roles/seniority):
- Goal (inform/align/decide):
- Ask (what should they do, by when):
- Why now (1 sentence):
- Key facts (dates, numbers, constraints):
- Sensitivities / what to avoid:
- Links (canonical doc, tracker, docs):
- Tone + length constraints:

## 2) Outline (default structure)
**TL;DR (2–4 bullets)**
- …

**What’s happening / Context (optional, short)**
- …

**What’s changing (and what’s not)**
- Changing:
- Not changing:

**How this works / Next steps (actionable)**
1) <Owner>: <action> — <due date>
2) <Owner>: <action> — <due date>

**What I need from you (explicit ask)**
- …

**Risks / open questions**
- …

## 3) Email template (stakeholder update + ask)
**Subject:** <clear outcome + topic> (e.g., “Decision needed by Fri: Launch scope change”)

Hi <name/team>,

**TL;DR**
- …

**What’s changing**
- …

**What I need from you (by <DATE>)**
- Decision: <A/B/C> (recommended: <X>)
- OR Feedback: <what kind> (how to respond)

**Next steps**
1) <Owner>: <action> — <date>
2) <Owner>: <action> — <date>

**Links**
- Canonical doc: <link>
- Tracker: <link>

Thanks,  
<name>

## 4) 1-page memo template (recommendation + tradeoffs)
**Title:**  
**Author:**  
**Date:**  
**Audience:**  
**Status:** Draft / Review / Approved

### TL;DR (recommendation)
- Recommendation:
- Decision needed:
- Deadline:

### Context (only what’s necessary)
- …

### Options (A/B/C) + tradeoffs
- Option A:
- Option B:
- Option C:

### Proposed plan (“how”)
1) …
2) …

### Risks / open questions / next steps
**Risks**
- …

**Open questions**
- …

**Next steps**
1) …

## 5) Status update template (weekly async)
**Status:** Green / Yellow / Red  
**This week (wins/progress)**
- …

**Metrics (if applicable)**
- …

**Risks / blockers**
- …

**Asks (who/what/by when)**
- …

**Next week plan**
- …

**Links**
- Canonical doc:
- Tracker:

## 6) Canonical doc template (single source of truth)
**Project:**  
**Owner:**  
**Last updated:**  
**Purpose (1–2 sentences):**

### TL;DR
- Current state:
- Next milestone:
- Top risk:

### Key links
- Tracker:
- Specs/docs:
- Decision log:
- Dashboard:

### Decisions (latest first)
| Date | Decision | Owner | Notes/links |
|---|---|---|---|
|  |  |  |  |

### Next steps (owned)
| Owner | Action | Due | Status |
|---|---|---:|---|
|  |  |  |  |

### Update cadence
- Next update: <date>
- Cadence: weekly / biweekly


```

### references/WORKFLOW.md

```markdown
# Workflow (Expanded)

This file expands the steps from `../SKILL.md` with extra guidance and heuristics.

## Step 1 — Choose the lightest artifact
Default rule: pick the smallest artifact that still achieves the outcome.

Common picks:
- **Email/Slack message:** fast update + clear ask.
- **Memo (1–2 pages):** recommendation + tradeoffs + decision.
- **Doc (longer):** shared context that will be referenced repeatedly.
- **Canonical doc:** ongoing project hub (links + decisions + current state).

Failure mode: writing a long doc when the reader only needed a crisp ask + next steps.

## Step 2 — Lock outcome + ask
Write the “after reading…” sentence and keep it visible while drafting.

Ask patterns:
- **Decision:** “Approve option B by Friday.”
- **Feedback:** “Reply with concerns by EOD Wednesday.”
- **Action:** “Please do X by DATE; I’ll do Y.”
- **FYI:** “No action needed; next update DATE.”

Failure mode: implied asks (readers don’t know what you want).

## Step 3 — Make the “how” concrete (don’t over-explain the premise)
Source insight: readers usually already accept the “what/why”. They need the “how”.

Include:
- What changes vs what stays the same
- Owners (names/roles) and dates
- Dependencies and risks

Failure mode: paragraphs of context with no actionable next steps.

## Step 4 — Structure for skim (clarity at scale)
Defaults that work for most audiences:
- **TL;DR first**
- Headings that match reader questions: “What’s happening?”, “What I need from you”, “Next steps”
- Bullets > paragraphs (especially for steps/asks)

Heuristic: if the reader only reads the TL;DR and headings, they should still act correctly.

## Step 5 — Draft to be forwarded
Write like your message might be forwarded to:
- A new exec who has zero context
- A partner team who is skeptical

Practical rules:
- Avoid “this/that/it” without nouns (“this change” vs “this”)
- Define acronyms on first use
- Put key numbers in writing (dates, scope cuts, thresholds)

## Step 6 — “Letter to yourself” clarity pass
Source insight: writing is a thinking tool. If you’re confused, the reader will be too.

Technique:
1) Write a blunt internal version (“What am I actually trying to say?”).
2) Extract the through-line (problem → decision → next steps).
3) Rewrite for the audience’s incentives and vocabulary.

Failure mode: polishing unclear thinking instead of clarifying it.

## Step 7 — Canonical doc (single source of truth)
Source insight: projects need one canonical place to learn the current state.

Canonical doc should make it easy to answer:
- What’s the latest?
- What decisions have been made?
- What’s next, and who owns it?

Include “last updated” and an update cadence to reduce anxiety and follow-ups.

## Step 8 — Quality gate
Before sending:
- Run [CHECKLISTS.md](CHECKLISTS.md)
- Score [RUBRIC.md](RUBRIC.md)
- Add **Risks / Open questions / Next steps**

Failure mode: sending a draft that creates more meetings and confusion than it prevents.


```

### references/CHECKLISTS.md

```markdown
# Checklists

Use these before you send or publish written communication.

## Universal checklist (any artifact)
- Audience is clear; the first screen answers “why am I reading this?”
- The ask is explicit (decision/action/feedback/FYI) and includes a deadline if needed
- The “how” is concrete: steps, owners, and dependencies are specified
- TL;DR exists and matches the body (no surprises)
- Scanability: headings, bullets, short paragraphs; no wall-of-text sections
- Terms, acronyms, and dates are unambiguous; key numbers are written down
- Single source of truth is linked (or created) for ongoing work
- Tone is direct and respectful; avoids blame; assumes good intent
- Safety: no secrets, credentials, or unnecessary sensitive/PII details

## Decision request checklist (email/memo)
- Options are stated (A/B/C) with your recommendation and rationale
- Tradeoffs are explicit (what you’re giving up, what you’re protecting)
- The cost of delay is stated (what happens if no decision)
- “If you disagree” path is clear (how to respond, by when)

## Status update checklist
- Status (G/Y/R) is justified with one sentence
- Asks are in a separate section with owner + date
- Blockers include what you’re doing about them (not just “blocked”)
- Next update date/cadence is stated

## Canonical doc checklist
- Owner and last updated are present
- Key links are complete and current
- Decisions are logged and easy to find
- Next steps have owners and dates


```

### references/RUBRIC.md

```markdown
# Rubric (Score 1–5)

Score the Written Communication Pack. Aim for **≥ 3** on every dimension before sending. If any dimension is **≤ 2**, revise.

## 1) Outcome + ask clarity
1 = unclear why the reader should care; ask is implied  
3 = ask is explicit with a clear deadline/response path  
5 = outcome is crisp; decision/action path is effortless for the reader

## 2) “How” specificity (actionability)
1 = mostly context; no concrete steps  
3 = next steps exist with owners and reasonable dates  
5 = highly actionable plan with dependencies, sequencing, and clear ownership

## 3) Structure + scanability (clarity at scale)
1 = hard to skim; walls of text; buried lede  
3 = TL;DR + headings + bullets; easy to follow  
5 = optimized for skim + deep read; information hierarchy is excellent

## 4) Correctness + completeness (given inputs)
1 = missing key facts; likely to confuse or mislead  
3 = includes necessary context, constraints, and links  
5 = accurate, complete, and anticipates key reader questions

## 5) Tone + trust
1 = defensive, blaming, or mismatched to audience  
3 = direct and respectful; appropriate confidence level  
5 = builds trust; acknowledges uncertainty; invites constructive response

## 6) Source of truth + follow-through
1 = no place to find “latest”; follow-ups inevitable  
3 = canonical doc/link and next update cadence exist when needed  
5 = reduces future meetings: decisions, owners, and cadence are crystal clear


```

written-communication | SkillHub