Borrowing it
Nothing to install: this file belongs to andrzejchm/fdb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrzejchm/fdb/main/.agents/skills/writing-client-facing-content/SKILL.mdgit clone --depth 1 https://github.com/andrzejchm/fdbWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/andrzejchm/fdb/writing-client-facing-content)<a href="https://agentmods.dev/skills/andrzejchm/fdb/writing-client-facing-content"><img src="https://agentmods.dev/badge/skills/andrzejchm/fdb/writing-client-facing-content/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/andrzejchm/fdb/writing-client-facing-content"><img src="https://agentmods.dev/badge/skills/andrzejchm/fdb/writing-client-facing-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01138 |
| Opus 5.5 | $0.00022 | $0.00455 |
| Sonnet 5.5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
writing-client-facing-content 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 24d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply these wording, terminology, and omission rules to any message a non-technical client will read, whatever the channel.
For a page on a public docs site rather than a short message, use this project's docs-site page skill if it has one: different medium, different rules. Without such a skill, apply this one.
Assume the client only uses the product. They do not know what a PR, commit, branch, ticket status, or endpoint is.
Contents
- Glossary Gate
- MUST
- MUST NOT
- Template Overrides
- Process
- Example
Glossary Gate
Read the project's client glossary in full before drafting. Locate it via the project's root AGENTS.md routing table; docs/GLOSSARY.md is the conventional path.
MUST NOT draft a client-facing message without it. Terminology and language come from the glossary, never from the agent's own translation of a UI label.
If the project has no glossary, stop and tell the user this skill needs one before it can run. A usable glossary declares:
- Client language — the language the product UI and all client messages are written in.
- Product terms — the exact wording of each domain concept as it appears in the app UI, in the client language.
- Jargon table — internal engineering term mapped to plain client wording, or marked "omit".
Offer to draft the glossary from the app's UI strings, then resume.
MUST
- Write in the client language declared by the glossary. Do not mix in English product terms the UI does not use.
- Use the glossary's exact product terms, matching the app UI.
- Keep it short: one or two sentences per point.
- State the outcome first: done, not yet, or needs a decision from the client.
- Describe changes in terms of what the client sees or does in the app, not how it was built.
- Give enough context that the message stands alone without the client re-reading their original report.
- Say plainly when something is not fixed or not done. Never imply progress that hasn't happened.
- Cut greetings, thanks, unsupported hedging, em dashes, and sign-offs from the draft before showing it, unless the calling workflow's fixed template explicitly requires one (see Template Overrides). Load
humanizing-ai-textand apply it in full: em dashes are zero-tolerance by default, no sycophantic openings, no chatbot sign-offs.
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.
- 24d ago First seen · 89 lines · 55 tokens per session scan A c846886b263d
writing-client-facing-content is a skill published in the GitHub repository andrzejchm/fdb (46 stars, last pushed 12d ago), licensed MIT. It adds 55 tokens to every session and 1,138 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.