Borrowing it
Nothing to install: this file belongs to joesaby/doctree-mcp. 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/joesaby/doctree-mcp/main/.claude/skills/doc-write/SKILL.mdgit clone --depth 1 https://github.com/joesaby/doctree-mcpWrote 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/joesaby/doctree-mcp/doc-write)<a href="https://agentmods.dev/skills/joesaby/doctree-mcp/doc-write"><img src="https://agentmods.dev/badge/skills/joesaby/doctree-mcp/doc-write.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.00963 |
| Opus 5 | $0.00018 | $0.00481 |
| Sonnet 5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
doc-write 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Documentation
Create a new markdown document in the knowledge base using the doctree-mcp wiki curation tools.
Requires WIKI_WRITE=1 in the MCP server configuration. If the write tools are unavailable, tell the user to add "WIKI_WRITE": "1" to their doctree env config.
Workflow
Follow these steps in order. Do NOT skip the duplicate check — it prevents content sprawl.
Step 1: Check for duplicates
Before writing anything, check if similar content already exists:
find_similar(content: "<the content you plan to write>")
If matches are found with overlap > 0.35 — UPDATE WORKFLOW:
- Read the existing doc — call
navigate_tree(doc_id, root_node_id)to get the full content - Decide what to keep vs. replace — identify sections that overlap with your new content
- Compose the merged content — write the full updated markdown (don't just append)
- Overwrite — call
write_wiki_entrywith the same path andoverwrite: true:
write_wiki_entry(
path: "<same path as existing file>",
frontmatter: { ... }, ← keep existing frontmatter, update tags if needed
content: "<full merged content>",
overwrite: true
)
If overlap is below 0.35 — proceed to Step 2 (scaffold a new entry).
Step 2: Generate a scaffold
Get suggestions for path, frontmatter, and structure:
draft_wiki_entry(
topic: "$ARGUMENTS",
raw_content: "<the content to turn into a wiki entry>"
)
Review what comes back:
- Suggested path — adjust if needed (e.g., put runbooks in
runbooks/, guides inguides/) - Inferred frontmatter — type, category, tags derived from similar docs
- Glossary hits — acronyms detected in the content
- Duplicate warnings — similar docs that might overlap
Step 3: Dry-run validation
Validate the entry without writing to disk:
write_wiki_entry(
path: "<path from step 2, adjusted if needed>",
frontmatter: {
"title": "<title>",
"description": "<one-line summary>",
"type": "<runbook|guide|reference|tutorial|architecture|adr|...>",
"category": "<domain grouping>",
"tags": ["<relevant>", "<terms>"]
},
content: "<full markdown content>",
dry_run: true
)
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.
- 5d ago First seen · 115 lines · 37 tokens per session scan A dee342565406
doc-write is a skill published in the GitHub repository joesaby/doctree-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 963 once invoked, about $0.0002 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…