Academic Prose De-AI Editor
heise3/academic-deai
Edits Chinese or English scholarly writing for natural phrasing and removes AI-sounding templated structure, while keeping claims, citations and author voice intact.
Write, restructure, or review bilingual Sphinx/MyST user documentation for MotrixLab — task environments (from simple single-page tasks to reusable task families) and framework-level tutorial pages…
Install Write Motrixlab Task Docs
$ npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Motphys/MotrixLab write-motrixlab-task-docs --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Motphys/MotrixLab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/write-motrixlab-task-docs .claude/skills/write-motrixlab-task-docs && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "write-motrixlab-task-docs" agent skill from https://github.com/Motphys/MotrixLab/tree/main/.agents/skills/write-motrixlab-task-docs into .claude/skills/write-motrixlab-task-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-motrixlab-task-docs", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Motphys/MotrixLab/tree/main/.agents/skills/write-motrixlab-task-docsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Motphys/MotrixLab write-motrixlab-task-docs --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Motphys/MotrixLab.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/write-motrixlab-task-docs .agents/skills/write-motrixlab-task-docs && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "write-motrixlab-task-docs" agent skill from https://github.com/Motphys/MotrixLab/tree/main/.agents/skills/write-motrixlab-task-docs into .agents/skills/write-motrixlab-task-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-motrixlab-task-docs", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Motphys/MotrixLab write-motrixlab-task-docs --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Motphys/MotrixLab.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/write-motrixlab-task-docs .cursor/skills/write-motrixlab-task-docs && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "write-motrixlab-task-docs" agent skill from https://github.com/Motphys/MotrixLab/tree/main/.agents/skills/write-motrixlab-task-docs into .cursor/skills/write-motrixlab-task-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-motrixlab-task-docs", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Motphys/MotrixLab.git --path .agents/skills/write-motrixlab-task-docs--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Motphys/MotrixLab write-motrixlab-task-docs --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Motphys/MotrixLab.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/write-motrixlab-task-docs .gemini/skills/write-motrixlab-task-docs && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "write-motrixlab-task-docs" agent skill from https://github.com/Motphys/MotrixLab/tree/main/.agents/skills/write-motrixlab-task-docs into .gemini/skills/write-motrixlab-task-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-motrixlab-task-docs", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Motphys/MotrixLab write-motrixlab-task-docsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Motphys/MotrixLab.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/write-motrixlab-task-docs .github/skills/write-motrixlab-task-docs && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "write-motrixlab-task-docs" agent skill from https://github.com/Motphys/MotrixLab/tree/main/.agents/skills/write-motrixlab-task-docs into .github/skills/write-motrixlab-task-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-motrixlab-task-docs", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Motphys/MotrixLab write-motrixlab-task-docs --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Motphys/MotrixLab.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/write-motrixlab-task-docs .opencode/skills/write-motrixlab-task-docs && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "write-motrixlab-task-docs" agent skill from https://github.com/Motphys/MotrixLab/tree/main/.agents/skills/write-motrixlab-task-docs into .opencode/skills/write-motrixlab-task-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-motrixlab-task-docs", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
write-motrixlab-task-docs- GitHub stars
- 152
- Token cost
- ~1.8k tokens
- SKILL.md length
- 767 words
- Files
- 3 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Write, restructure, or review bilingual Sphinx/MyST user documentation for MotrixLab — task environments (from simple single-page tasks to reusable task families) and framework-level tutorial pages…
- Works in 5 steps: Read repository instructions, the… → Locate the environment registration,… → Treat current code and declarative… → …
- Documenting a registered environment
- SKILL.md covers Read the standard, Establish evidence, Classify the task first and Write for users, plus 3 more sections
- Calls rg, git and uv
What it does
Write Motrixlab Task Docs is an agent skill from Motphys/MotrixLab. Write, restructure, or review bilingual Sphinx/MyST user documentation for MotrixLab — task environments (from simple single-page tasks to reusable task families) and framework-level tutorial pages (concepts, building environments, training, advanced topics) under docs/source/{zhCN,en}/userguide/. Use when documenting a registered environment, its runtime contract, configuration, presets, training evidence, or an implemented extension workflow, or when authoring or restructuring tutorial pages and tutorial…
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/tutorial-standard.md` and `references/writing-standard.md`).
It sits in Writing & Content, covering Translation and Technical writing. The repository describes itself as: A general-purpose machine learning architecture designed for robot training. The licence is Apache-2.0.
When your agent uses it
- Documenting a registered environment
- Its runtime contract
- Training evidence
- An implemented extension workflow
Example prompts
- “/write-motrixlab-task-docs”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read repository instructions, the current documentation page, and the closest maintained task page.
- Locate the environment registration, config factory, environment implementation, relevant model or scene config, training
- Treat current code and declarative config as authoritative. Use tests as supporting evidence, not as a substitute for the
- Separate shared environment behavior from model-, preset-, algorithm-, and terrain-specific values when those variants
- Verify every dimension, formula, reward term, reset randomization, termination condition, command, path, and performance
What it can do on your machine
Read from SKILL.md and the folder at commit 2a4ffb6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
rggituv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git and uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Write Motrixlab Task Docs loads about 1.8k tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 138 tokens; SKILL.md has 767 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Motphys/MotrixLab at commit 2a4ffb6, republished under its Apache-2.0 licence (© Motphys). 767 words, ~1,776 tokens.
Download SKILL.mdSave it as
.claude/skills/write-motrixlab-task-docs/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- write-motrixlab-task-docs
- description
- Write, restructure, or review bilingual Sphinx/MyST user documentation for MotrixLab — task environments (from simple single-page tasks to reusable task families) and framework-level tutorial pages (concepts, building environments, training, advanced topics) under docs/source/{zh_CN,en}/user_guide/. Use when documenting a registered environment, its runtime contract, configuration, presets, training evidence, or an implemented extension workflow, or when authoring or restructuring tutorial pages and tutorial navigation.
Write MotrixLab Task Docs
Create user-facing MotrixLab documentation from current repository evidence. Keep Chinese and English pages aligned, state exact runtime semantics, and validate the rendered Sphinx output. Two surfaces are covered:
- Task-environment pages (
user_guide/envs/): follow references/writing-standard.md. - Framework tutorial pages (
user_guide/tutorial/): follow references/tutorial-standard.md — layered information architecture, macro-before-detail ordering, SVG pipeline diagram rules (compact snake layout, chip sub-items, light/dark pairs), and toctree hygiene.
The evidence, bilingual, and validation rules below apply to both surfaces.
Read the standard
Read the standard for the target surface completely before drafting or restructuring: references/writing-standard.md for task-environment pages, references/tutorial-standard.md for framework tutorial pages. Apply only sections supported by the target; do not add empty boilerplate.
Establish evidence
- Read repository instructions, the current documentation page, and the closest maintained task page.
- Locate the environment registration, config factory, environment implementation, relevant model or scene config, training config, tests, and referenced media. Skip surfaces that do not exist for the task.
- Treat current code and declarative config as authoritative. Use tests as supporting evidence, not as a substitute for the implementation.
- Separate shared environment behavior from model-, preset-, algorithm-, and terrain-specific values when those variants exist.
- Verify every dimension, formula, reward term, reset randomization, termination condition, command, path, and performance claim before writing it.
Prefer rg and concrete source paths. Useful starting searches include:
rg -n "registry\.env|registry\.envcfg" motrix_envs/src configs/task
rg -n "action_space|observation_space|reward|terminated|truncated|reset|random" motrix_envs/src
rg -n "<env-id>|<environment-class>" docs motrix_envs/testsClassify the task first
Choose documentation depth from the implemented reuse boundary and user needs, not from a fixed template:
- Simple task: one main implementation or preset, few meaningful knobs, and no supported extension contract. Use one page. Keep action, observation, reward, termination, and reset explanations concise on that page.
- Configurable task: users need substantial runtime-contract or tuning guidance. Keep an overview and add only the design or tuning page that answers a distinct user question.
- Reusable task family: one stable environment contract intentionally supports multiple models, assets, terrains, or task variants. A multi-page structure may include overview, design, tuning, and extension guidance as justified.
Extend the current navigation rather than inventing a second hierarchy. Do not split a short section into its own page. Do not create an adding-a-robot, adding-a-model, or adding-a-task page unless the repository implements a stable extension workflow and users are expected to use it.
Keep model/config responsibility boundaries in a short opening explanation when needed. Do not create a standalone boundary, lifecycle, or configuration-schema chapter by default.
Show full SKILL.md (375 more words)Show less
Write for users
- Lead with what the task does and what the user can configure or run.
- Use exact public names, Env IDs, config fields, units, shapes, and source-derived formulas.
- Use tables for repeated mappings and comparisons. Prefer concise prose or a list when a simple task has only one or two obvious items. Follow the table shapes in the writing standard when a table is warranted.
- Explain why each reward or randomization exists, not only how it is computed.
- Distinguish
terminatedfailures fromtruncatedtime limits. - Distinguish task, initial-state, and observation randomization from physical domain randomization. State explicitly when physical parameters are not randomized.
- Describe only implemented capability. Do not turn a plausible design, unused config, or test fixture into a current claim.
- Avoid internal lifecycle narration, implementation history, compatibility notes, and
dataclasses.replaceexamples unless the user explicitly asks for them.
Keep bilingual pages aligned
Edit docs/source/zh_CN/ and docs/source/en/ together unless the user explicitly scopes the work to one language. Preserve
technical identifiers across languages and translate meaning rather than sentence structure. Use established terminology from
the neighboring pages. Keep section order, figures, tables, and toctree/link changes mirrored on both sides — restructure one
language only together with the other.
Handle media and performance evidence
Generate videos and posters with the dedicated docs/scripts/ tools, never placeholder images or ad-hoc play.py
recordings; verify camera framing by actually looking at the output before embedding. The exact commands, camera-framing
acceptance rules, and directive syntax are specified in writing-standard.md section 8.
Performance prose must match plot/log evidence.
Validate and proofread
Run the build checks in writing-standard.md section 10, at minimum:
git diff --check -- <changed-docs>
.venv/bin/sphinx-build -W --keep-going -b html docs/source <zh-output-dir>
.venv/bin/sphinx-build -W --keep-going -D language=en -b html docs/source <en-output-dir>Use uv run --extra docs sphinx-build if the repository virtual environment is unavailable. If registration or generated
environment overview content changed, also run docs/scripts/generate_env_docs.py --check.
Then perform the content proofread required by section 10: re-read the finished page and re-derive every quantitative claim (observation dimensions per group, noise/randomization interval semantics, weights, thresholds, scales, durations) from the current implementation, and confirm the Chinese and English pages state identical numbers. Do not trust what was written from memory during drafting.
Inspect the final HTML for the changed page, especially wide tables, formulas, captions, navigation titles, and internal links. Report warnings or unrelated failures precisely; do not claim an unobserved build succeeded.
© Motphys, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in .agents/skills/write-motrixlab-task-docs of Motphys/MotrixLab.
- SKILL.md
- references/tutorial-standard.md
- references/writing-standard.md
Open the folder on GitHubat commit 2a4ffb6
Compare with similar skills
Write Motrixlab Task Docs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Write Motrixlab Task Docs this skillMotphys/MotrixLab | 152 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Academic Prose De-AI Editorheise3/academic-deai | 209 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Aholo Viewer Docsmanycoretech/aholo-viewer | 1.1k | — | ~341 | Automated safety check: Pass | MIT | |
| Docs Leadlablup/backend.ai-webui | 133 | — | ~2.9k | Automated safety check: Pass | LGPL-3.0 | |
| Chinese Documentation Style GuidejnMetaCode/superpowers-zh | 8.3k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Docs Changelog Writerlobehub/lobehub | 83k | — | ~948 | Automated safety check: Pass | Custom licence |
Similar skills
Aholo Viewer Docs
manycoretech/aholo-viewer
Guides writing and maintaining Aholo Viewer documentation: README, AGENTS.md, architecture notes, bilingual manual pages and AI collaboration guides.
Docs Lead
lablup/backend.ai-webui
A skill your agent uses whenever the user mentions docs, the manual, documentation, terminology, translations, or screenshots — including indirect mentions like "이 PR 문서 영향 봐줘", "문서 점검", "용어 통일"…
Chinese Documentation Style Guide
jnMetaCode/superpowers-zh
Reference rules for typesetting Chinese technical documents: spacing around English and digits, punctuation, term handling, bilingual API docs and README layout.
Docs Changelog Writer
lobehub/lobehub
Writes bilingual English and Chinese product changelog pages for docs/changelog, with date-based file names, frontmatter rules and a factual, user-first tone.
Docs Website
kurotu/VRCQuestTools
Use this skill FIRST for any task whose output lives in the Website/ directory — the VRCQuestTools user manual / docs site (Docusaurus, bilingual en/ja).
Related
Categories
Questions about Write Motrixlab Task Docs
What does Write Motrixlab Task Docs do?
Write, restructure, or review bilingual Sphinx/MyST user documentation for MotrixLab — task environments (from simple single-page tasks to reusable task families) and framework-level tutorial pages…. Write Motrixlab Task Docs is an agent skill from Motphys/MotrixLab. Write, restructure, or review bilingual Sphinx/MyST user documentation for MotrixLab — task environments (from simple single-page tasks to reusable task families) and framework-level tutorial pages (concepts, building environments, training, advanced topics) under docs/source/{zhCN,en}/userguide/.
When should I use Write Motrixlab Task Docs?
Write Motrixlab Task Docs fits situations like: documenting a registered environment; its runtime contract; training evidence; an implemented extension workflow.
How do I install Write Motrixlab Task Docs in Claude Code?
Run `npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a claude-code`. Or copy the skill folder (.agents/skills/write-motrixlab-task-docs in Motphys/MotrixLab) into .claude/skills/write-motrixlab-task-docs in your project. Claude Code loads it when a task matches its description.
How do I install Write Motrixlab Task Docs in Codex?
Run `npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a codex`. Or copy the skill folder (.agents/skills/write-motrixlab-task-docs in Motphys/MotrixLab) into .agents/skills/write-motrixlab-task-docs in your project. Codex loads it when a task matches its description.
Can I use Write Motrixlab Task Docs in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Motphys/MotrixLab --skill write-motrixlab-task-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/write-motrixlab-task-docs, .gemini/skills/write-motrixlab-task-docs, .github/skills/write-motrixlab-task-docs and .opencode/skills/write-motrixlab-task-docs in your project.
What does Write Motrixlab Task Docs need to run?
Going by SKILL.md and its folder, Write Motrixlab Task Docs needs the command-line tools its instructions call (rg, git and uv).
Does Write Motrixlab Task Docs access the network?
SKILL.md contains no URLs. Its commands use git and uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Write Motrixlab Task Docs safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Write Motrixlab Task Docs use?
Write Motrixlab Task Docs is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Write Motrixlab Task Docs use?
About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.
What are the alternatives to Write Motrixlab Task Docs?
Skills that share tags, products or a category with Write Motrixlab Task Docs: Academic Prose De-AI Editor (heise3/academic-deai, 209 stars), Aholo Viewer Docs (manycoretech/aholo-viewer, 1.1k stars), Docs Lead (lablup/backend.ai-webui, 133 stars) and Chinese Documentation Style Guide (jnMetaCode/superpowers-zh, 8.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Write Motrixlab Task Docs?
Motphys (a GitHub organization) maintains it in Motphys/MotrixLab, which has 152 GitHub stars. The repository was last updated on October 7, 2026.
Source: Motphys/MotrixLab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.