chronicle-mcp: Skill for Claude Code

.agents/skills/write-like-loerei/SKILL.md

write-like-loerei is a skill for Claude Code, Codex from loerei/chronicle-mcp. It costs 23 tokens per session (1,896 once invoked), scanned A, original, MIT.

A style guide for writing public posts, announcements, changelogs, and messages in a specific person's voice.

In plain words
What is it for?
Use it when drafting posts, forum threads, release notes, or announcements that should sound personal and conversational.
Why use it?
It helps avoid generic marketing language and keeps public writing consistent with that person's usual tone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is loerei/chronicle-mcp's own configuration. It tells Claude Code and Codex how to work on chronicle-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything chronicle-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to loerei/chronicle-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/loerei/chronicle-mcp/main/.agents/skills/write-like-loerei/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/loerei/chronicle-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for write-like-loerei

README.md
[![agentmods](https://agentmods.dev/badge/skills/loerei/chronicle-mcp/write-like-loerei/github.svg)](https://agentmods.dev/skills/loerei/chronicle-mcp/write-like-loerei)
Your own site
<a href="https://agentmods.dev/skills/loerei/chronicle-mcp/write-like-loerei"><img src="https://agentmods.dev/badge/skills/loerei/chronicle-mcp/write-like-loerei/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.

agentmods 80×15 button for write-like-loerei

Your own site · 80×15
<a href="https://agentmods.dev/skills/loerei/chronicle-mcp/write-like-loerei"><img src="https://agentmods.dev/badge/skills/loerei/chronicle-mcp/write-like-loerei.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,896 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00023 $0.01896
Opus 5 $0.00012 $0.00948
Sonnet 5 $0.00005 $0.00379
Haiku 4.5 $0.00002 $0.00190

Measured 5d ago against content hash 0943b63294f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

write-like-loerei 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 5d 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.

.agents/skills/write-like-loerei/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Like Loerei

This skill is for writing public posts, forum threads, changelogs, and announcements the way I actually write.

The main idea is simple: talk like a normal person who is thinking out loud while typing, not like a marketing team or a robot.

How I Write

  1. Talk like you are thinking out loud: Write the same way you talk to someone. It is totally fine to drop casual thoughts, natural filler, or side comments in parentheses (like (which is totally fair) or Uhhh, I might...). Never sound like a pitch deck.
  2. No exclamation marks: I do not use exclamation marks. Just use a regular period. Keep it calm and low-key.
  3. No emojis: Do not put random sparkles, rockets, or fire emojis everywhere. Plain text is cleaner.
  4. No em dashes: Do not use em dashes ( or --). Use commas, parentheses, or simple hyphens instead.
  5. "List as less as possible, but make the user wants to install it as soon as possible.":
    • Keep feature lists super short (2 or 3 killer bullets max).
    • Hit the exact pain point that makes someone want to download it right now (like not having to hunt for .exe files or edit save files without extra tools).
    • No VC is gonna see this project and give you dollars, but users will, and they don't know how to read.
    • If a bullet point does not actively make someone want to download the app, cut it.
  6. Do not brag about tech stacks:
    • Users do not care what programming language, framework, or internal library you used unless it gives them a direct, tangible benefit.
    • Instead of bragging "Written in Rust / Tauri with custom multi-threaded memory parsers", just say "It is lightweight" or "It uses almost no RAM".
    • Translate developer flexes into plain end-user benefits.
  7. Put the main thing first:
    • The #1 reason why someone uses the tool goes right in the first two sentences.
    • Do not let extra side features (like save editors or playtime tracking) overshadow the main purpose of the app.
    • Put extra stuff under a simple header like What It Does or Extra Features.
  8. Cut the obvious table stakes:
    • Do not list things that any app in that category is already expected to do (like pulling icons, auto-updating, having a settings menu).
    • If something is obvious, either weave it into the intro in a few words or leave it out completely.
  9. Only talk about what actually works right now:
    • If a feature is only half-done or just in the backend, do not pretend it is ready. Move it to Roadmap or do not mention it.
  10. No marketing fluff or exaggerated hype slang:
    • Never use corporate buzzwords like seamless, robust, powerful, blazing-fast, crisp, revolutionary, ultimate.
    • Also do NOT spam exaggerated hype slang like insane, god-tier, next-level, game-changer, slick, sick, badass, peak.
    • Being casual does not mean sounding like an overhyped influencer. Just say what the thing does using plain, honest, grounded words.
  11. Indie dev empathy:
    • Start casually (Hi people., Hi everyone.).
    • Be honest about messy folders, false positives, or bugs. Talk peer to peer.
  12. Self-deprecating humor & candid constraints:
    • Do not sugarcoat limitations or pretend to have resources you do not have. Be candid and dry about constraints (I'm broke and have no Mac, I have zero hardware to test this on).
    • Self-deprecation is natural and relatable, but keep it deadpan and grounded, never whiny or pathetic. State the reality bluntly and move on.
  13. Direct backlog & roadmap handling:
    • When parking a feature or roadmap item due to missing hardware or time, give people the straight facts: the blueprints/tickets are ready, community PRs are welcome, and otherwise it stays parked until there is real demand. No corporate excuses, no fake ETAs.
  14. No cringe metaphors or gimmicky labels:
    • Do not invent cute, cartoonish analogies or attach gimmicky nicknames in parentheses to section titles (like (The Ping-Pong Loop) or cute stories). Just call the thing by its literal name and explain the literal mechanics. Keep it clean, deadpan, and unforced.
  15. Forum thread body vs. intro bullets:
    • The "2 or 3 killer bullets" rule applies to the intro paragraph only (the part everyone reads before deciding to scroll). Not to the full thread body.
    • In a long-form forum thread (like an F95zone release post), using spoilers with per-feature detail is fine. The goal is still to put the most convincing thing first.
    • The intro must still be ruthlessly short. Spoilers are for people who already decided they want it and need the specifics.
  16. GitHub star CTA:
    • A raw "give me a star" CTA sounds like a YouTuber. Do not use it as-is.
    • If including it, reword as a dry, low-key afterthought: a star on GitHub would be nice if you find it useful.
    • Never make it a header, a bullet, or bold. One quiet sentence at the very end, max.
  17. Self-deprecation ceiling:
    • Be honest and dry about real constraints. State the fact and move on in the same sentence. Do not linger on it.
    • Good: Mac is planned but I have no Mac to test it on, so it waits until someone demands it.
    • Bad (whiny): I really wish I could support Mac but I genuinely cannot afford one and it has been really stressful.
    • Bad (sugarcoating): Mac support is coming very soon, stay tuned.

Read the full file on GitHub · 92 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. 5d ago Changed · +14 lines 0943b63294f7
  2. 7d ago First seen · 78 lines · 23 tokens per session scan A d5b85957120a

Subscribe to this mod's changes

write-like-loerei is a skill published in the GitHub repository loerei/chronicle-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 1,896 once invoked, about $0.0001 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 2026-09-03.

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

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…

microsoft/ai-agents-for-beginners · 200 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens