write-docs
Skill0 starsChanged 46 days agoMITView on GitHub
Write, edit, restructure, illustrate and publish Nemi Docs documents. Use when the user wants to draft, write up, edit, rewrite, proofread, translate, extend or summarise a document in Nemi, add a picture to one, turn notes or a file into a doc, or publish a doc as a web page.
43 other projects use a version of this.
Adopted by
Most recently taken up by
- alchemy-run/alchemy-effecttheir own version, first seen Nov 9, 2026
- alchemy-run/alchemytheir own version, first seen Nov 8, 2026
- adhamhaithameid/write-skillstheir own version, first seen Nov 8, 2026
- dzhng/jevgreptheir own version, first seen Nov 7, 2026
- oberon-systems/enggraphtheir own version, first seen Nov 6, 2026
- dzhng/skillstheir own version, first seen Nov 4, 2026
Used with
Projects with it also use close-spec, design-with-images and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 5 projects that use this
dzhngSkilldesign-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
Also in 5 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 5 projects that use this
LucasMatuszewskiSkillaudit-agents
Audit and maintain agent configuration files (.claude/agents, AGENTS.md, CLAUDE.md, agent-memory). Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines. Fixes all issues and commits.
Also in 5 projects that use this
wolverin0Skillaudit-decisions
Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.
Also in 4 projects that use this
rhnfzlSkillexplore-unknowns
Walk the user through mapping the unknowns of a task before, during, and after they build it, and hand them a four-quadrant map (settled ground, open decisions, taste, and landmines) they keep. Reach for this eagerly whenever a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, a build-queue or architecture-changing task is about to start, a mid-build deviation needs capturing, or a finished change needs buy-in or verified understanding before merge. Trigger even when the skill is not named: "do a blindspot pass", "find my unknown unknowns", "interview me about this change", "brainstorm the approach for a task I am about to build", "help me scope this", "what am I missing here", "plan this before I build", "I know nothing about X in this codebase". When a territory profile is present it reads memory and the graph first and feeds the map into the build pipeline; without one it degrades to a plain general map. Not for trivial or mechanical tasks with clear acceptance criteria, single-fact lookups, pure debugging of a known symptom, or pure code review, those have their own tools. Do not use it to run the build itself; the map is the deliverable and implementation remains a separate task, whether it has not started or is already underway.
Also in 5 projects that use this
- +6 more from dzhng
Other versions43 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 43
- tldraw/tldraw★ 51ksame name
- tabler/tabler★ 42ksame name
- videojs/video.js★ 40ksame name
- PrefectHQ/prefect★ 24ksame name
- comet-ml/opik★ 23ksame name
- coder/coder★ 17ksame name
- browseros-ai/BrowserOS★ 14ksame name
- Agenta-AI/agenta★ 4.9ksame name
- liveblocks/liveblocks★ 4.8ksame name
- dzhng/jevgrep★ 3.2ksame name
33 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- build-sheetsSkill
- convert-and-editSkill
- draw-on-canvasSkill
- nemi-basicsSkill
- organize-filesSkill
- plan-with-calendarSkill
- read-and-extractSkill
- run-formsSkill
- share-and-collectSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 42 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
start the body with a heading that is exactly the title.
- Distinctive: line 21
Never open the body with a heading that disagrees with the title.
- Distinctive: line 63
Use headings for anything longer than a screen, tables for anything the reader will compare, task lists for action items with owners.
“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Nemi Docs
A Nemi Doc is a collaborative document stored in the Docs app, not in the file tree. It is read and written as Markdown.
Markdown that survives
Supported: headings, bold, italic, strike, ==highlight==, inline code and fenced code blocks, links, images, quotes, nested lists, task lists (- [ ]), GFM tables, horizontal rules and hard line breaks. Anything else (HTML, footnotes, math, custom containers) becomes plain text, so do not use it.
Titles
Until the user renames a doc by hand, its first h1 or h2 becomes its title. So either:
- give
titleand start the body with the first section (no heading repeating the title), or - start the body with a heading that is exactly the title.
Never open the body with a heading that disagrees with the title.
Create
- Pick the workspace (
workspace_listif the user has several and did not say). doc_createwithtitleand the wholebodyin one call. Write the real content, not a skeleton, unless the user asked for an outline.- Reply with what you wrote in a sentence or two and the document's title. Do not paste the whole document back.
Edit
There is no partial edit. Every change is: read, change the text, write it all back.
doc_list(it shows previews) to find the doc, thendoc_getfor the full Markdown.- Make the change on that Markdown. Keep everything you were not asked to change exactly as it was, including headings, links, image lines and task list states. Do not "improve" untouched paragraphs.
doc_updatewithmode"replace" and the complete new body.- To add at the end only (a new meeting's notes, a log entry), use
mode"append" with just the new part; no need to read first.
Others may be editing the same document live. Read immediately before you write, and keep the gap short. If the user says someone else is working in it, append instead of replacing when that does the job.
Pictures
doc_add_image is the only way to put a picture in a doc. Give a file_id for an image in the file tree (find it with file_list) or a Gallery photo_id, an optional caption, and position "start" or "end". A share link or a download link pasted into the Markdown will not render as a picture. To put a picture in the middle, add it, then doc_get, move the image line to where it belongs, and doc_update replace.
From a file to a doc
To turn a PDF, Word file, notes or a transcript into a Nemi Doc: file_read the file (follow next_offset for long ones), then doc_create with the result written as proper Markdown. Say in the reply which file it came from.
Publish
doc_publish puts the doc on the open web as a read-only page anyone can open without an account, that search engines may find, and that follows every later save. Only the doc's creator can publish.
- Confirm before publishing unless the user asked for it in so many words.
- Reply with the address and say plainly that it is public.
publishedfalse takes the page down and the address stops working.
Delete
doc_delete is permanent and only the creator can do it. Confirm first, naming the document.
Good documents
- Match the user's language. A Dutch request gets a Dutch document.
- Use headings for anything longer than a screen, tables for anything the reader will compare, task lists for action items with owners.
- Meeting notes: date, attendees, decisions, action items as a task list with names.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

