writing

A writing method for creating audience-focused material such as explanatory documents, presentations, emails and announcements. It guides the message, structure and communication choices while leaving factual content to the relevant subject expert.

In plain words
What is it for?
Use it to plan and write briefs, manifestos, pitch decks, one-pagers, essays, speeches, video scripts, emails and announcements.
Why use it?
It helps turn accurate information into writing that is clear and suited to its intended audience without changing the underlying facts.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jircdev/crew-plugin/writing
Any agent
npx skills add jircdev/crew-plugin --skill writing
Clone the repo
git clone --depth 1 https://github.com/jircdev/crew-plugin

Made for: Claude Code, Codex.

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,286 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00114 $0.01286
Opus 5 $0.00057 $0.00643
Sonnet 5 $0.00023 $0.00257
Haiku 4.5 $0.00011 $0.00129

Measured yesterday against content hash ad7dc28ae477, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/writing/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing — the communication craft

Formerly the communications-strategist role; now a horizontal craft any role loads when it writes. The domain truth belongs to the owning role (the technical decision to system-architect, viability to commercial-strategist, the requirement to functional-analyst, the product truth to product-strategist); this skill governs how that truth lands.

Method

  1. Internalize objective and audience. What should they think, feel, or do afterward — and who exactly are they? A piece without a declared objective and audience is not ready to be written.
  2. Pull the WHAT from its owner. Read the project docs or consult the owning role; never invent or alter domain facts to make the narrative flow.
  3. Fix the idea-force: the single thing the audience must remember.
  4. Choose the impact principle that fits — golden circle (why → how → what), storytelling, framing, proof points, exponential framing — because the objective calls for it, never as decoration. State why.
  5. Design the arc: hook → development → climax → close, beat by beat; for each beat, the message, the visual support required (specify, don't design), the emotional intent.
  6. Write in the structure proper to the format. The format follows the objective, not a fixed template.
  7. Close with the call to action or the idea that stays.
  8. If spoken, add delivery notes: pacing, pauses, emphasis, where energy rises and falls.
  9. Hand off visual support as a per-beat specification to ux-architect (owner of the visual system); they design the slides or assets.

Craft rules

  • Segmentation: the same idea-force adapts to different audiences and formats without losing coherence — one project can yield a team induction and an external webinar the same week; they are different pieces.
  • Register and tone adapt to channel and audience; jargon the audience cannot decode gets glossed or cut.
  • Message before context: the why never arrives after the how. Burying the message under background is the most common failure.
  • Length sized to the decision, not to the template.
  • Senior judgment, not transcription: reorganizing the source material without adding communicational judgment is the anti-pattern this craft exists to prevent.

Read the full file on GitHub · 63 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 63 lines · 114 tokens per session scan A ad7dc28ae477

Subscribe to this mod's changes

writing is a skill published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 114 tokens to every session and 1,286 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens