Neat-Freak Knowledge Closeout
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
Read BEFORE writing or editing any durable document in this repo — docs/.md, stdlib/.md, tracker/readme.md, AGENTS.md, any README.
Install Write Docs
$ npx skills add cdiggins/plato --skill write-docs -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cdiggins/plato write-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/cdiggins/plato.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/write-docs .claude/skills/write-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-docs" agent skill from https://github.com/cdiggins/plato/tree/main/.claude/skills/write-docs into .claude/skills/write-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-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/cdiggins/plato/tree/main/.claude/skills/write-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 cdiggins/plato --skill write-docs -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cdiggins/plato write-docs --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdiggins/plato.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/write-docs .agents/skills/write-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-docs" agent skill from https://github.com/cdiggins/plato/tree/main/.claude/skills/write-docs into .agents/skills/write-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-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 cdiggins/plato --skill write-docs -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cdiggins/plato write-docs --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdiggins/plato.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/write-docs .cursor/skills/write-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-docs" agent skill from https://github.com/cdiggins/plato/tree/main/.claude/skills/write-docs into .cursor/skills/write-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-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/cdiggins/plato.git --path .claude/skills/write-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 cdiggins/plato --skill write-docs -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cdiggins/plato write-docs --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdiggins/plato.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/write-docs .gemini/skills/write-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-docs" agent skill from https://github.com/cdiggins/plato/tree/main/.claude/skills/write-docs into .gemini/skills/write-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-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 cdiggins/plato write-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 cdiggins/plato --skill write-docs -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cdiggins/plato.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/write-docs .github/skills/write-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-docs" agent skill from https://github.com/cdiggins/plato/tree/main/.claude/skills/write-docs into .github/skills/write-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-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 cdiggins/plato --skill write-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 cdiggins/plato write-docs --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdiggins/plato.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/write-docs .opencode/skills/write-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-docs" agent skill from https://github.com/cdiggins/plato/tree/main/.claude/skills/write-docs into .opencode/skills/write-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-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-docs- GitHub stars
- 106
- Token cost
- ~1.1k tokens
- SKILL.md length
- 508 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Read BEFORE writing or editing any durable document in this repo — docs/.md, stdlib/.md, tracker/readme.md, AGENTS.md, any README.
- The user says document X
- SKILL.md covers The one rule that keeps…, Also, Scope and Before you finish
- Calls python
- Update the docs
What it does
Write Docs is an agent skill from cdiggins/plato. Read BEFORE writing or editing any durable document in this repo — docs/.md, stdlib/.md, tracker/readme.md, AGENTS.md, any README. Enforces the no-drifting-facts rule (state design, never measurements) plus the one-authority-per-fact rules from docs/documentation-conventions.md. Use when the user says "document X", "write a doc", "update the docs", "write this up", or when a task produces a lasting write-up. Skip for dated snapshots, docs/archive/, and generated files.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Technical documentation. The repository describes itself as: A simple and efficient cross-platform programming language. The licence is MIT.
When your agent uses it
- The user says document X
- Update the docs
- A task produces a lasting write-up
Example prompts
- “document X”
- “write a doc”
- “update the docs”
- “/write-docs”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit f6e02cf. 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:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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 Docs loads about 1.1k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 508 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 cdiggins/plato at commit f6e02cf, republished under its MIT licence (© cdiggins). 508 words, ~1,061 tokens.
Download SKILL.mdSave it as
.claude/skills/write-docs/SKILL.md (or your agent's skills folder).- name
- write-docs
- description
- Read BEFORE writing or editing any durable document in this repo — docs/*.md, stdlib/*.md, tracker/readme.md, AGENTS.md, any README. Enforces the no-drifting-facts rule (state design, never measurements) plus the one-authority-per-fact rules from docs/documentation-conventions.md. Use when the user says "document X", "write a doc", "update the docs", "write this up", or when a task produces a lasting write-up. Skip for dated snapshots, docs/archive/**, and generated files.
- argument-hint
- path to the document being written or edited
Writing durable docs in the Plato repo
Normative source: docs/documentation-conventions.md.
Read it when a case is not covered below. This skill is the working checklist.
Worked example of the style: stdlib/VERIFICATION.md.
The one rule that keeps getting violated
A durable document states design, not measurements.
Before writing any number, apply the three-month test: will this still be true in three months? If no, it is a measurement — do not write it. Name its authority instead.
Stale numbers are worse than absent ones: a reader cannot tell a stale figure from a fresh one, so one rotten number discredits the document. A second copy of an enforced value (a ratchet ceiling) rots silently while the enforced copy moves.
Drop on sight
- Scope preambles that inventory a directory ("
stdlib/, 424 files — foundation 133, …"). - "Current state (measured
<date>)" tables. The date makes it more dangerous, not less. - Restated ratchet ceilings, finding counts, diagnostic counts, test tallies, generated-file counts, per-gate timings.
- Any number a script already produces.
Keep
- Normative limits from a spec ("
TupleNstops at 10 fields"). - Historical incident figures tied to a finished event ("that shape produced 40 CS0736 errors").
- Orders of magnitude, stated as such ("runs in seconds", "fires in the thousands").
- Identifiers, paths, flags, rule codes, issue ids.
Say where the number lives instead
| Question | Authority |
|---|---|
| what do the gates say now? | plato_check, or python tools/record-gates.py --dry-run |
| what did they say at commit X? | docs/gate-log.md |
| a ratchet ceiling | the constant in the test that enforces it |
| how long a gate takes | .\tools\gate-timings.ps1 |
| burn-down status | python tools/track.py show <id> |
Show full SKILL.md (250 more words)Show less
Also
- One authority per fact. If another file already states it, link — do not restate. Two copies become two different rules.
- Name the mechanism, not the moment. "The corpus floor stops an empty enumeration from passing", not "the corpus floor is 300".
- Prefer a rule to a report. "A ceiling is lowered, never raised" outlives "the ceiling is 33".
- When a document and a gate disagree, the gate is right. Several status blocks in this repo describe blockers that were fixed after they were written. Re-measure before quoting status prose.
- Declare the omission. Where a reader expects numbers, say in one sentence that the document records none and why — otherwise the next author helpfully adds them back.
- Mark inferred claims as inferred. Confidence is a fact about the claim; it does not drift.
Scope
Applies to docs/*.md, docs/design/**, stdlib/*.md, tracker/readme.md, AGENTS.md, and every
README.md. docs/README.md says which tier a document is in.
Does not apply to dated snapshots (*-YYYY-MM-DD.md), docs/reports/**, docs/essays/**,
docs/discussions/**, docs/archive/**, or generated files (docs/gate-log.md,
docs/status-report*, docs/types-and-concepts-*.txt) — recording a moment is their whole purpose,
and the date in the name is the honest label.
For README voice and structure, use the write-readme skill; this skill governs which facts any
document may state.
Before you finish
Re-read your own draft hunting only for numbers, and delete or re-home each one that fails the three-month test. This is the step that gets skipped — the rule is easy to agree with while drafting and easy to violate in the same paragraph.
© cdiggins, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/write-docs of cdiggins/plato.
Open the folder on GitHubat commit f6e02cf
Compare with similar skills
Write 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 Docs this skillcdiggins/plato | 106 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Compound Learning WriterEveryInc/compound-engineering-plugin | 25k | — | ~2k | Automated safety check: Pass | MIT | |
| Compound Learnings RefreshEveryInc/compound-engineering-plugin | 25k | — | ~2k | Automated safety check: Pass | MIT | |
| Dsh Web Documentationzhu1090093659/dsh-web | 8.4k | — | ~479 | Automated safety check: Pass | Apache-2.0 | |
| Codebase Handbook BuilderRuhan-Wang/Harness_Handbook | 331 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Compound Learning Writer
EveryInc/compound-engineering-plugin
Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.
Compound Learnings Refresh
EveryInc/compound-engineering-plugin
Audits a repo's stored learnings against the current codebase, fixes stale, overlapping or superseded docs and reports on every document.
Dsh Web Documentation
zhu1090093659/dsh-web
A skill your agent uses when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
Codebase Handbook Builder
Ruhan-Wang/Harness_Handbook
Generates, refreshes, validates and uses a compact handbook that maps where a change touches in a repository, using the active Codex session and no external LLM API.
New Command Docs
tractorjuice/arc-kit
This skill should be used when a new ArcKit command has been added and documentation needs updating across the repository.
More from cdiggins/plato
Track Backlog
cdiggins/plato
View and manage the tracker backlog — show in-progress work, current priorities, sprint contents; triage untriaged items; promote ideas to ready; plan a sprint (big rocks + little rocks…
Track Idea
cdiggins/plato
Log a new idea into tracker/ with elaboration — assumptions, design decisions, related work links, approach brainstorm, and simplest implementation.
Track Issue
cdiggins/plato
Log a concrete issue (bug, technical debt, open design problem, or retire candidate) into tracker/ with elaboration — symptoms/impact, affected code links, root-cause notes, fix approaches, and…
Write Readme
cdiggins/plato
Write or review a project README.md in plain technical-writer prose — problem it solves and doesn't, honest assessment of tested vs untested, trade-offs, prior art, organization, and usage.
Related
Categories
Questions about Write Docs
What does Write Docs do?
Read BEFORE writing or editing any durable document in this repo — docs/.md, stdlib/.md, tracker/readme.md, AGENTS.md, any README. Write Docs is an agent skill from cdiggins/plato.md, any README.
When should I use Write Docs?
Write Docs fits situations like: the user says document X; update the docs; A task produces a lasting write-up.
How do I install Write Docs in Claude Code?
Run `npx skills add cdiggins/plato --skill write-docs -a claude-code`. Or copy the skill folder (.claude/skills/write-docs in cdiggins/plato) into .claude/skills/write-docs in your project. Claude Code loads it when a task matches its description.
How do I install Write Docs in Codex?
Run `npx skills add cdiggins/plato --skill write-docs -a codex`. Or copy the skill folder (.claude/skills/write-docs in cdiggins/plato) into .agents/skills/write-docs in your project. Codex loads it when a task matches its description.
Can I use Write 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 cdiggins/plato --skill write-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-docs, .gemini/skills/write-docs, .github/skills/write-docs and .opencode/skills/write-docs in your project.
What does Write Docs need to run?
Going by SKILL.md and its folder, Write Docs needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Write Docs access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Write 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 Docs use?
Write Docs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Write Docs use?
About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Write Docs?
Skills that share tags, products or a category with Write Docs: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Compound Learning Writer (EveryInc/compound-engineering-plugin, 25k stars), Compound Learnings Refresh (EveryInc/compound-engineering-plugin, 25k stars) and Dsh Web Documentation (zhu1090093659/dsh-web, 8.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Write Docs?
cdiggins (a GitHub user) maintains it in cdiggins/plato, which has 106 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 26, 2026.
Source: cdiggins/plato on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.