Borrowing it
Nothing to install: this file belongs to chama-x/GroundRules. 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/chama-x/GroundRules/master/.agents/skills/apple-writing-philosophy/SKILL.mdgit clone --depth 1 https://github.com/chama-x/GroundRulesWrote 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/chama-x/groundrules/apple-writing-philosophy)<a href="https://agentmods.dev/skills/chama-x/groundrules/apple-writing-philosophy"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/apple-writing-philosophy/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/chama-x/groundrules/apple-writing-philosophy"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/apple-writing-philosophy.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 | $0.00110 | $0.01306 |
| Opus 5 | $0.00055 | $0.00653 |
| Sonnet 5 | $0.00022 | $0.00261 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
apple-writing-philosophy 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Like Apple: A Reasoning Process, Not a Style
The one first principle everything else derives from
Attention is the scarcest resource the reader has, and every claim has to survive the reader's skepticism. Apple copy isn't decorated to look a certain way — it's engineered against those two constraints. Understand this and you can produce the "Apple sound" for a product Apple never made, without an example to imitate.
Two consequences follow logically:
- Since attention is scarce, anything that doesn't do direct work is a cost, not a neutral addition → short sentences, one idea per unit, aggressive cutting.
- Since claims must survive skepticism, vague praise is worthless (anyone can say "amazing"), but concrete/falsifiable facts carry weight (a rival literally cannot claim a specific number or feature it doesn't have) → concreteness, feature-first specificity, letting emotion arrive second.
Everything below is this principle applied to one decision at a time. Don't memorize rules — rederive them each time by asking: does this line respect the reader's attention, and would this claim survive skepticism?
The reasoning procedure — run this on your own draft
For each sentence or headline:
-
Isolate the single idea. Before writing, state in one clause what this line needs to do. Can't state it in one clause? You don't know what the line is for yet. Check: delete everything except that clause — still true and complete? If deleting anything changes the meaning, a second idea got smuggled in. Split it.
-
Test every claim for competitor-transferability. For each claim, ask: could a rival honestly say this exact sentence about itself? If yes, it's marketing wallpaper — swap the adjective for the specific fact (a number, a named capability, a visible outcome) that makes the sentence untransferable. This isn't "prefer concrete words as style" — it's "abstract claims don't survive scrutiny, so they don't belong."
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.
- 9d ago First seen · 109 lines · 110 tokens per session scan A 71036d37152f
apple-writing-philosophy is a skill published in the GitHub repository chama-x/GroundRules (5 stars, last pushed 25d ago), licensed MIT. It adds 110 tokens to every session and 1,306 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.
Other skills, from other repositories
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
compute-methods
Environment-verified friction sheets for field-standard computational tools (Rydberg pair interactions, QEC circuits, qLDPC decoding, code distance, atom dynamics, optics, quantum chemistry). Each sheet lists the tools the field actually uses, the first-use frictions that make agents wrongly abandon them, and one-line…
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.