Agent skill

Notcrawl

A skill your agent uses for local Notion archive search, sync freshness, Markdown/database exports, git-share snapshots, and Notcrawl repo/release work.

MITAuto-check passedDatabases

Install Notcrawl

skills CLI

$ npx skills add openclaw/notcrawl --skill notcrawl -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install openclaw/notcrawl notcrawl --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/openclaw/notcrawl.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/notcrawl .claude/skills/notcrawl && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "notcrawl" agent skill from https://github.com/openclaw/notcrawl/tree/main/.agents/skills/notcrawl into .claude/skills/notcrawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notcrawl", 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

$skill-installer install https://github.com/openclaw/notcrawl/tree/main/.agents/skills/notcrawl

Type 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.

skills CLI

$ npx skills add openclaw/notcrawl --skill notcrawl -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install openclaw/notcrawl notcrawl --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openclaw/notcrawl.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/notcrawl .agents/skills/notcrawl && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "notcrawl" agent skill from https://github.com/openclaw/notcrawl/tree/main/.agents/skills/notcrawl into .agents/skills/notcrawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notcrawl", 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.

skills CLI

$ npx skills add openclaw/notcrawl --skill notcrawl -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install openclaw/notcrawl notcrawl --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openclaw/notcrawl.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/notcrawl .cursor/skills/notcrawl && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "notcrawl" agent skill from https://github.com/openclaw/notcrawl/tree/main/.agents/skills/notcrawl into .cursor/skills/notcrawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notcrawl", 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

$ gemini skills install https://github.com/openclaw/notcrawl.git --path .agents/skills/notcrawl

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add openclaw/notcrawl --skill notcrawl -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install openclaw/notcrawl notcrawl --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openclaw/notcrawl.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/notcrawl .gemini/skills/notcrawl && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "notcrawl" agent skill from https://github.com/openclaw/notcrawl/tree/main/.agents/skills/notcrawl into .gemini/skills/notcrawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notcrawl", 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.

GitHub CLI

$ gh skill install openclaw/notcrawl notcrawl

Installs 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).

skills CLI

$ npx skills add openclaw/notcrawl --skill notcrawl -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/openclaw/notcrawl.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/notcrawl .github/skills/notcrawl && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "notcrawl" agent skill from https://github.com/openclaw/notcrawl/tree/main/.agents/skills/notcrawl into .github/skills/notcrawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notcrawl", 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.

skills CLI

$ npx skills add openclaw/notcrawl --skill notcrawl -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install openclaw/notcrawl notcrawl --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openclaw/notcrawl.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/notcrawl .opencode/skills/notcrawl && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "notcrawl" agent skill from https://github.com/openclaw/notcrawl/tree/main/.agents/skills/notcrawl into .opencode/skills/notcrawl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "notcrawl", 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: notcrawl
GitHub stars: 134
Token cost: ~698 tokens
SKILL.md length: 262 words
Files: 1
Skills in repo: 1
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses for local Notion archive search, sync freshness, Markdown/database exports, git-share snapshots, and Notcrawl repo/release work.

Works in 4 steps: Resolve scope: workspace, teamspace,… → Check freshness for recent/current… → Use CLI for normal reads; use read-only… → …
Local Notion archive search
SKILL.md covers Sources, Freshness, Query Workflow and SQL, plus 2 more sections
Calls go and sqlite3; needs NOTION_TOKEN

What it does

Notcrawl is an agent skill from openclaw/notcrawl. Use for local Notion archive search, sync freshness, Markdown/database exports, git-share snapshots, and Notcrawl repo/release work.

Its SKILL.md is about 700 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 Databases, covering Markdown. It works with Notion, Git and SQL. The repository describes itself as: Local-first Notion crawler into SQLite and normalized Markdown. The licence is MIT.

When your agent uses it

Local Notion archive search
Markdown/database exports
Git-share snapshots
Notcrawl repo/release work

Example prompts

“/notcrawl”

Requirements

A credential in NOTION_TOKEN

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Resolve scope: workspace, teamspace, page, database, author, keyword, or date range.
Check freshness for recent/current requests.
Use CLI for normal reads; use read-only SQL for precise counts/rankings.
Report absolute date spans, counts, page/database titles, and known gaps.

What it can do on your machine

Read from SKILL.md and the folder at commit f857533. 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:
- go
- sqlite3
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 these keys or tokens, usually read from environment variables:
- NOTION_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Notcrawl loads about 698 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~35
When it runs · the whole SKILL.md, loaded when a task matches: ~698

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 openclaw/notcrawl at commit f857533, republished under its MIT licence (© openclaw). 262 words, ~698 tokens.

Download SKILL.mdSave it as .claude/skills/notcrawl/SKILL.md (or your agent's skills folder).

name: notcrawl
description: Use for local Notion archive search, sync freshness, Markdown/database exports, git-share snapshots, and Notcrawl repo/release work.

Notcrawl

Use local archive data first for Notion questions. Browse or hit the Notion API only when the archive is stale, missing the requested scope, or the user asks for current external context.

Sources

DB: ~/.notcrawl/notcrawl.db
Config: ~/.notcrawl/config.toml
Cache: ~/.notcrawl/cache
Markdown archive: ~/.notcrawl/pages
Git share repo: ~/.notcrawl/share
Repo: the local notcrawl checkout
Preferred CLI: notcrawl; fallback to go run ./cmd/notcrawl from the repo if the installed binary is stale

Freshness

For recent/current questions, check freshness before analysis:

bash

sqlite3 ~/.notcrawl/notcrawl.db \
  "select coalesce(max(synced_at), 0) from sync_state;"

Routine refresh:

bash

notcrawl doctor
notcrawl sync --source desktop

API refresh:

bash

notcrawl sync --source api

Use notcrawl sync --source all only when both desktop and API sources are configured and the broader refresh is intentional.

Query Workflow

Resolve scope: workspace, teamspace, page, database, author, keyword, or date range.
Check freshness for recent/current requests.
Use CLI for normal reads; use read-only SQL for precise counts/rankings.
Report absolute date spans, counts, page/database titles, and known gaps.

Common commands:

bash

notcrawl search "query"
notcrawl databases
notcrawl report
notcrawl sql "select count(*) from pages;"

SQL

Use notcrawl sql for exact counts, joins, and database/page inventory queries when normal CLI reads are too coarse. The command only allows read-only select, with, and pragma queries.

Useful examples:

bash

notcrawl sql "select count(*) as pages from pages;"
notcrawl sql "select parent_table, count(*) as pages from pages group by parent_table order by pages desc;"
notcrawl sql "select title, last_edited_time from pages order by coalesce(last_edited_time, created_time, 0) desc limit 20;"

Do not use SQL to mutate the archive.

When the installed CLI lacks a new feature, build or run from the repository checkout before concluding the feature is missing.

Notion Boundaries

Desktop mode snapshots the local Notion SQLite database read-only and must not write to Notion application storage. API mode requires NOTION_TOKEN; do not invent token availability. Git-share snapshots and Markdown exports must not include secrets.

Verification

For repo edits, prefer existing Go gates:

bash

GOWORK=off go test ./...

Then run targeted CLI smoke for the touched surface, for example:

bash

notcrawl doctor
notcrawl status --json
notcrawl search "test"

Files

Just SKILL.md in .agents/skills/notcrawl of openclaw/notcrawl.

Open the folder on GitHubat commit f857533

Compare with similar skills

Notcrawl 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.

Notcrawl compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Notcrawl this skillopenclaw/notcrawl	134	—	~698	Automated safety check: Pass	MIT	yesterday
Take Doc Screenshotspgplex/pgconsole	155	—	~841	Automated safety check: Pass	Apache-2.0	1 mo ago
Wtfnoobnooc/agent	1.4k	—	~2.1k	Automated safety check: Notes	None	1 mo ago
Postgres Commit History Articledigoal/blog	8.6k	—	~2.3k	Automated safety check: Pass	GPL-2.0	10 days ago
DB AI GitHub Paper Weekly Newsdigoal/blog	8.6k	—	~1.2k	Automated safety check: Pass	GPL-2.0	10 days ago
Drizzle Migration Conflictsickn33/agentic-awesome-skills	47k	1 repos	~2.5k	Automated safety check: Notes	Apache-2.0	yesterday

Similar skills

Take Doc Screenshots
pgplex/pgconsole
Take screenshots of the running pgconsole app for documentation.
155 GitHub stars~841 tokensUpdated 1 mo ago
DatabasesAuto-check passed
Wtf
noobnooc/agent
Pre-launch and pre-commit audit for vibe coding projects. An agent skill from noobnooc/agent.
1.4k GitHub stars~2.1k tokensUpdated 1 mo ago
DatabasesAuto-check: notes
Postgres Commit History Article
digoal/blog
Analyze PostgreSQL git commit history between two commit ids and, when valuable DBA/application-developer changes exist, write a Chinese Markdown article for WeChat/公众号 readers with examples checked…
8.6k GitHub stars~2.3k tokensUpdated 10 days ago
DatabasesAuto-check passed
DB AI GitHub Paper Weekly News
digoal/blog
抓取并汇总"数据库、AI、GitHub、AI 论文"近 1 周新闻，输出图文并茂（含 mermaid 图）的 markdown 周报到当前项目的 markdown/ 目录。覆盖 10 个数据源：postgresweekly.com/issues（自动解析最新 issue…
8.6k GitHub stars~1.2k tokensUpdated 10 days ago
DatabasesAuto-check passed
Drizzle Migration Conflict
sickn33/agentic-awesome-skills
Diagnose, repair, and prevent Drizzle Kit migration conflicts involving generated SQL, snapshots, journals, merge queues, and team workflows.
47k GitHub starsUsed in 1 repo~2.5k tokens
DatabasesAuto-check: notes
Notcrawl
steipete/agent-scripts
Notion archive: desktop/API sync, Markdown export, page search, read-only SQL.
7.3k GitHub stars~272 tokensUpdated 3 days ago
DatabasesAuto-check passed

Works with

Questions about Notcrawl

What does Notcrawl do?

A skill your agent uses for local Notion archive search, sync freshness, Markdown/database exports, git-share snapshots, and Notcrawl repo/release work. Notcrawl is an agent skill from openclaw/notcrawl. Use for local Notion archive search, sync freshness, Markdown/database exports, git-share snapshots, and Notcrawl repo/release work.

When should I use Notcrawl?

Notcrawl fits situations like: local Notion archive search; markdown/database exports; Git-share snapshots; notcrawl repo/release work.

How do I install Notcrawl in Claude Code?

Run `npx skills add openclaw/notcrawl --skill notcrawl -a claude-code`. Or copy the skill folder (.agents/skills/notcrawl in openclaw/notcrawl) into .claude/skills/notcrawl in your project. Claude Code loads it when a task matches its description.

How do I install Notcrawl in Codex?

Run `npx skills add openclaw/notcrawl --skill notcrawl -a codex`. Or copy the skill folder (.agents/skills/notcrawl in openclaw/notcrawl) into .agents/skills/notcrawl in your project. Codex loads it when a task matches its description.

Can I use Notcrawl 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 openclaw/notcrawl --skill notcrawl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/notcrawl, .gemini/skills/notcrawl, .github/skills/notcrawl and .opencode/skills/notcrawl in your project.

What does Notcrawl need to run?

Going by SKILL.md and its folder, Notcrawl needs the command-line tools its instructions call (go and sqlite3) and credentials named NOTION_TOKEN. Our summary lists: A credential in NOTION_TOKEN.

Does Notcrawl 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 Notcrawl 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 Notcrawl use?

Notcrawl 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 Notcrawl use?

About 698 tokens (SKILL.md is roughly 2.8k 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 Notcrawl?

Skills that share tags, products or a category with Notcrawl: Take Doc Screenshots (pgplex/pgconsole, 155 stars), Wtf (noobnooc/agent, 1.4k stars), Postgres Commit History Article (digoal/blog, 8.6k stars) and DB AI GitHub Paper Weekly News (digoal/blog, 8.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Notcrawl?

openclaw (a GitHub organization) maintains it in openclaw/notcrawl, which has 134 GitHub stars. The repository was last updated on October 7, 2026.

Source: openclaw/notcrawl on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Notcrawl

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Notcrawl

Sources

Freshness

Query Workflow

SQL

Notion Boundaries

Verification

Files

Compare with similar skills

Similar skills

Take Doc Screenshots

Wtf

Postgres Commit History Article

DB AI GitHub Paper Weekly News

Drizzle Migration Conflict

Notcrawl

Related

Questions about Notcrawl