Skip to content

syahiidkamil/Software-Engineer-AI-Agent-Atlas / .claude/skills/human-writing

human-writing

Verified

Write content in any language indistinguishable from a skilled human writer. Avoids AI-sounding phrases, varies sentence structure, creates natural prose. Detects target language and loads language-specific AI-tells, register, and orthography from `languages/`.

FileKindSize
SKILL.mdskill md5.8 KB
languages/README.mdmarkdown1.5 KB
languages/id.mdmarkdown4.3 KB

languages/README.md

View on GitHub
# Language modules

This folder holds language-specific extensions to `human-writing/SKILL.md`. The parent skill is the trigger and the source of universal writing philosophy; each file here covers what's specific to one language: AI-tells, orthographic rules, register spectrum, common anglicisms, sentence-structure conventions.

## How they're loaded

`SKILL.md` runs Step 0.1 (Detect Language) on every invocation. If the target language has a file here, the skill reads that file *in addition to* SKILL.md before writing. If no file exists, the universal principles in SKILL.md are applied to the target language with care for native conventions.

## Available languages

| Code | File | Language |
|---|---|---|
| `id` | [id.md](./id.md) | Bahasa Indonesia |
| `en` | (default — covered in SKILL.md) | English |

## Adding a new language

1. Create `{iso-code}.md` in this folder. Keep frontmatter out — these are reference documents, not skills.
2. Cover at minimum: AI-tells in this language (transition phrases, filler, sentence patterns), orthographic conventions, register spectrum, common anglicisms or loanword guidance, structural quirks (punctuation habits, voice preference, paragraph rhythm).
3. Reuse the section structure of `id.md` so language modules are visually consistent.
4. Add a row to the table above and to SKILL.md's Step 0.1 manifest.

The skill's trigger description in SKILL.md does **not** need to enumerate languages — language detection happens inside the skill, so a single description scales to N languages without polluting the skill list.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall