Aas Discover
sickn33/agentic-awesome-skills
Discover AAS skills for an explicit task and compare their complete instructions without installing them.
Discover Japanese RV parks and permitted overnight stops, compare vehicle limits and facilities, screen services or prepare booking contacts through Kurumatabi.
$ npx skills add mvanhorn/printing-press-library --skill pp-kurumatabi -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kurumatabi --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/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-kurumatabi .claude/skills/pp-kurumatabi && 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 "pp-kurumatabi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kurumatabi into .claude/skills/pp-kurumatabi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kurumatabi", 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/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kurumatabiType 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 mvanhorn/printing-press-library --skill pp-kurumatabi -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kurumatabi --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cli-skills/pp-kurumatabi .agents/skills/pp-kurumatabi && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pp-kurumatabi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kurumatabi into .agents/skills/pp-kurumatabi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kurumatabi", 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 mvanhorn/printing-press-library --skill pp-kurumatabi -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kurumatabi --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cli-skills/pp-kurumatabi .cursor/skills/pp-kurumatabi && 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 "pp-kurumatabi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kurumatabi into .cursor/skills/pp-kurumatabi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kurumatabi", 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/mvanhorn/printing-press-library.git --path cli-skills/pp-kurumatabi--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 mvanhorn/printing-press-library --skill pp-kurumatabi -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kurumatabi --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cli-skills/pp-kurumatabi .gemini/skills/pp-kurumatabi && 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 "pp-kurumatabi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kurumatabi into .gemini/skills/pp-kurumatabi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kurumatabi", 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 mvanhorn/printing-press-library pp-kurumatabiInstalls 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 mvanhorn/printing-press-library --skill pp-kurumatabi -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .github/skills && cp -r skills-src/cli-skills/pp-kurumatabi .github/skills/pp-kurumatabi && 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 "pp-kurumatabi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kurumatabi into .github/skills/pp-kurumatabi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kurumatabi", 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 mvanhorn/printing-press-library --skill pp-kurumatabi -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mvanhorn/printing-press-library pp-kurumatabi --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cli-skills/pp-kurumatabi .opencode/skills/pp-kurumatabi && 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 "pp-kurumatabi" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-kurumatabi into .opencode/skills/pp-kurumatabi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-kurumatabi", 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.
pp-kurumatabiDiscover Japanese RV parks and permitted overnight stops, compare vehicle limits and facilities, screen services or prepare booking contacts through Kurumatabi.
Pp Kurumatabi is an agent skill from mvanhorn/printing-press-library. Discover Japanese RV parks and permitted overnight stops, compare vehicle limits and facilities, screen services or prepare booking contacts through Kurumatabi. Use for RV Park / くるま旅 searches, vehicle-size checks, dump-station evidence, or use kurumatabi.
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed. The licence is Apache-2.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit d9a1696. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gonpxFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
kurumatabi.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pp Kurumatabi loads about 4k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 1,851 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, BashAutomated 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.
The full file from mvanhorn/printing-press-library at commit d9a1696, republished under its Apache-2.0 licence (© mvanhorn). 1,851 words, ~4,040 tokens.
.claude/skills/pp-kurumatabi/SKILL.md (or your agent's skills folder).<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/travel/kurumatabi/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
The CLI is published in the travel catalog. This amendment awaits maintainer review; to try the proposed fixes before merge, build from its source checkout with go build -o kurumatabi-pp-cli ./cmd/kurumatabi-pp-cli and place the binary on the runtime PATH. The installer instructions below apply to the currently published CLI. Verify with command -v kurumatabi-pp-cli and plain kurumatabi-pp-cli version.
This skill drives the kurumatabi-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:npx -y @mvanhorn/printing-press-library install kurumatabi --cli-onlykurumatabi-pp-cli --version$PATH for the agent/runtime that will invoke this skill.If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:
go install github.com/mvanhorn/printing-press-library/library/travel/kurumatabi/cmd/kurumatabi-pp-cli@latestIf --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.
Search the official RV Park and Kurumatabi ecosystem, inspect vehicle limits and facility fees, then compare evidence and prepare a host handoff. Cached observations support proximity and required-service screening without claiming live vacancies or dated stay totals.
Use for official RV Park / Kurumatabi search, vehicle compatibility evidence, facility and membership comparison, cached waypoint proximity and booking preparation. Read public Japanese records and preserve their evidence.
Choose another tool or a human workflow for reservations/payments, account operations, dated live vacancy, inclusive stay quotes, road routing/clearance, or general outdoor-camping permission. The CLI returns contact links without sending messages or booking.
These commands derive decisions across published evidence and cached observations.
parks fit — Compare your vehicle with one park’s published dimensions and membership rules.
Large-motorhome service-stop planner can act on explicit evidence and unresolved checks.
kurumatabi-pp-cli parks fit rvpark/1086 --length-m 6 --width-m 2.2 --height-m 3 --vehicle van --membership nonmember --agentparks match — Screen cached parks into proven, uncertain and ruled-out service matches.
Pet-owning van planner; Large-motorhome service-stop planner can act on explicit evidence and unresolved checks.
kurumatabi-pp-cli parks match --require electricity,water,pets --membership nonmember --agentparks compare — Compare park evidence without inventing total prices or unknown facilities.
Pet-owning van planner; Club and nonmember tariff comparer can act on explicit evidence and unresolved checks.
kurumatabi-pp-cli parks compare rvpark/1086 yypark/213 --agentparks near — Rank cached parks by straight-line distance from an explicit waypoint.
Pet-owning van planner can act on explicit evidence and unresolved checks.
kurumatabi-pp-cli parks near --latitude 36.7 --longitude 138.2 --limit 5 --agentparks audit — Surface disabled-icon conflicts, stale observations and qualified opening notes.
Club and nonmember tariff comparer; Large-motorhome service-stop planner can act on explicit evidence and unresolved checks.
kurumatabi-pp-cli parks audit rvpark/712 --agentStart with kurumatabi-pp-cli parks --help; use each leaf's help for flags. parks filters returns exact prefecture, type, vehicle, facility and opening-period vocabularies. Source campground slugs are camp3000 and campjrva; RV parks use rvpark, 湯YOU parks yypark.
A park identity is kind/numeric-id or its canonical https://www.kurumatabi.com/park/kind/id.html URL. Keep Japanese names and source URLs in the answer.
kurumatabi-pp-cli parks search --prefecture nagano --type rvpark --agent --select results.id,results.name,metaKeep identifiers, Japanese names and source coverage.
kurumatabi-pp-cli parks fit rvpark/1086 --length-m 6 --width-m 2.2 --height-m 3 --vehicle van --membership nonmember --agentUnknown constraints require host confirmation.
kurumatabi-pp-cli parks compare rvpark/1086 yypark/213 --agentTariff audiences and fees remain separate.
kurumatabi-pp-cli parks near --latitude 36.7 --longitude 138.2 --limit 5 --agentRanks only cached observed parks; distance is straight line.
kurumatabi-pp-cli parks match --require electricity,water,pets --membership nonmember --agentUnknown evidence never becomes a proven match.
_off legacy icons override positive alt labels. Generic dump-station presence leaves black/grey permission unknown until explicit evidence exists.observed_at is JST retrieval time; source_updated_date_jst is the provider publication date. Confirm current operation and material conditions directly with the host.Public search and detail require no account. The native search session is memory-only and is used only to preserve filter pagination.
Run kurumatabi-pp-cli doctor to verify setup.
Use --agent for compact JSON and --select to preserve just the fields needed. --json preserves full structured detail. Arrays stay [] when empty. Missing dimension/coordinate values use null; facilities, fee kinds and live vacancy have explicit unknown states. Machine stdout contains only the selected output, while hints/errors go to stderr.
Search has separate output/scan caps: --limit (1..100) and --max-scan-pages (1..5). Read the provider total, scanned denominator, completion/truncation and note from metadata. Cached search/near/match are observed-pool results, not nationwide discovery. Near distances are straight line; match partitions contain only displayed candidate IDs. Compare records exclude failed fetches and include meta.fetch_failures.
Use kurumatabi-pp-cli agent-context --json for actual runtime paths. Domain cache defaults follow the runtime data path; --db chooses an explicit SQLite observation store. --no-cache skips live cache writes and auto fallback. Search does not overwrite richer cached detail. --max-age controls stale-read hints; audit also flags old publication/observation evidence.
The generated recall, teach, learnings and playbook commands operate on local state. Use recall before repeated discovery when that state is populated; always verify recalled IDs against fresh source data for travel decisions. Teach structural questions after a useful workflow; strip personal identifiers and sensitive data. Pass arbitrary user text as argv/tool input or read it from a file rather than interpolating it into shell source. --no-learn or KURUMATABI_NO_LEARN=true disables the loop for deterministic verification.
Use kurumatabi-pp-cli feedback --help to inspect the local feedback command. Report provider drift with the actual canonical URL and bounded evidence; keep credential/session values out of reports.
Ordinary output goes to stdout. Inspect kurumatabi-pp-cli --help for shared output/delivery options before selecting an external destination; this skill authorizes read-only planning only.
Inspect kurumatabi-pp-cli profile --help for the generated local profile commands. Preserve existing profiles and prefer explicit --db or runtime home settings for isolated checks.
Domain commands use 0 success, 2 usage/input error, 3 uncached ID, 5 source failure, including a partial comparison, and 7 throttling. Unknown source evidence can be a successful JSON result; inspect its decision and predicates instead of treating exit 0 as permission.
Validate positive finite vehicle measurements in metres, finite coordinate ranges and supported filter labels before network work. Negative numeric flags should use --longitude=-120 form. --dry-run short-circuits before source/cache I/O.
The source tree includes an MCP build target mirroring the nine park planning commands with source-aware local-state hints. Build it with go build -o kurumatabi-pp-mcp ./cmd/kurumatabi-pp-mcp. Raw HTML source diagnostics are excluded from MCP. No remote listener is deployed. Inspect the README/build tree before choosing an MCP installation surface.
Run kurumatabi-pp-cli parks filters --json or kurumatabi-pp-cli parks --help to discover the current domain surface. Detailed semantics and current bounds are in the source README and command help.
A partial comparison is emitted on stdout and returns exit5. Explicit file/webhook delivery occurs only after success; failed comparisons do not deliver the partial buffer.
Search caches every observation in the bounded page scan before applying the returned-row limit. Detail, fit, compare, audit and handoff require detailed observations for local reads or automatic fallback; refresh a search-only card with parks detail ID --data-source live. Multiple bath/onsen icons retain every source observation and qualified fee evidence.
MCP comparison failures retain bounded partial JSON in the first content block, with isError: true and a separate diagnostic capped at 4,000 bytes. Oversized evidence uses an explicit preview; total failure text is bounded to 64,000 bytes. learnings forget atomically removes matched teachings and reconciles existing inferred query/resource/venue families against all retained evidence. Supported rules keep their IDs and refreshed examples; unsupported rules are removed. Manually taught and unrelated rules remain. Explicit teach-pattern updates replace the complete recorded scope and examples; later inference preserves that manual definition. Verified prefix patterns require one literal match, including % and _ characters.
Native park MCP mirrors and the comparison recipe force --no-learn after caller arguments, preventing automatic journaling or preference derivation. Explicit recall and local-writing tools retain their own behavior. Ordinary CLI learning remains optional through the documented controls. Native reads can still refresh the evidence cache; --no-cache disables those cache writes and fallback.
export source exports canonical link objects from the first catalog page as JSONL or a JSON array, with a limit of 1 through 200 links. It does not export detailed records or claim nationwide coverage. Invalid options and failed source reads leave a destination untouched; dry runs do not create output files. Source redirects must stay within the requested effective origin; foreign host, port or scheme changes are refused before custom credentials can be sent.
MCP hints reflect durable effects: filters, near and match are read-only and do not expose receipt writes; search, detail, fit, compare, audit, handoff and the comparison recipe may refresh the evidence cache and advertise local writes. Explicit learning readers and workflow status also advertise local writes because their normal CLI paths can update learning/journal state. Typed context/SQL tools remain read-only. The named variadic park-id input for parks_compare accepts a whitespace-separated ID list; scalar text inputs remain one argument, and flag-like tokens are rejected.
kurumatabi-pp-cli export --format json --limit 20 --no-learn source
kurumatabi-pp-cli parks compare rvpark/1086 yypark/213 --agent --no-learnThe catalog export covers first-page link objects only. MCP named comparison input uses park-id: "rvpark/1086 yypark/213"; scalar recall questions remain one argument. Framework recall checks actual cached resource identity before promoting aliases. A known conflicting identity stays a mismatch; a missing resource stays explicitly warned and still requires fresh source verification.
Source and agent capabilities include bounded catalog export, truthful MCP local-state hints, safe named comparisons and evidence-aware alias recall in addition to the five domain feature groups above.
Synthesized recall checks any extractable cached identity too; a known conflicting target stays a mismatch. Identifier-verified patterns with no extractable identity retain their existing behavior without invented entities, and every recalled travel ID still needs fresh source verification.
Synthesized identity validation follows the exact entity substituted into its resource ID; another entity in a compound query cannot validate a conflicting target. Forgetting a teaching preserves an inferred rule only when at least two distinct compatible bindings remain, ignores unusable rows, and repairs examples from those compatible supporters.
Recall limits apply after cached identity validation and accepted-ID deduplication, so rejected candidates do not consume the requested result count.
Recall checks later bindings when an earlier one conflicts, selects one compatible binding per pattern, and ranks before deduplicating typed resource IDs. Accepted targets are removed from contradictory mismatch alternatives. --limit caps returned results and diagnostic rows; it does not promise a cap on local validation work, which depends on the learned pattern store. Full validation preserves confidence and identity ranking.
Only a genuinely absent cached resource uses the warned missing-row fallback. Cancellation and unreadable cached payloads fail the command; they do not produce an exact result.
© mvanhorn, 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
Just SKILL.md in cli-skills/pp-kurumatabi of mvanhorn/printing-press-library.
Open the folder on GitHubat commit d9a1696
Pp Kurumatabi 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 |
|---|---|---|---|---|---|---|
| Pp Kurumatabi this skillmvanhorn/printing-press-library | 2.1k | — | ~4k | Automated safety check: Notes | Apache-2.0 | |
| Aas Discoversickn33/agentic-awesome-skills | 47k | 1 repos | ~523 | Automated safety check: Pass | MIT | |
| Discover Pluginsruvnet/ruflo | 74k | — | ~2k | Automated safety check: Notes | MIT | |
| Discovertaishi-i/awesome-japanese-nlp-resources | 1k | — | ~6.5k | Automated safety check: Notes | CC0-1.0 | |
| Comparetaishi-i/awesome-japanese-nlp-resources | 1k | — | ~4.1k | Automated safety check: Notes | CC0-1.0 | |
| Verify and StopJuliusBrussee/caveman | 111k | 1 repos | ~176 | Automated safety check: Pass | Apache-2.0 |
sickn33/agentic-awesome-skills
Discover AAS skills for an explicit task and compare their complete instructions without installing them.
ruvnet/ruflo
Discover and recommend ruflo plugins based on your workflow, installed MCP tools, and current task
taishi-i/awesome-japanese-nlp-resources
Given a Japanese NLP GitHub repo/model/dataset (URL / owner/repo / tool name) OR a topic, find what's already in awesome-japanese-nlp-resources and discover related resources NOT yet listed…
taishi-i/awesome-japanese-nlp-resources
Compare several Japanese NLP libraries, models, or datasets for a keyword (a specific tool name, or a function/task like '形態素解析') across a handful of criteria chosen for that comparison, rendered as…
JuliusBrussee/caveman
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile…
brycewang-stanford/Auto-Empirical-Research-Skills
Discovery phase combining research interviews, literature search, data discovery, and ideation.
mvanhorn/printing-press-library
Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.
mvanhorn/printing-press-library
Search, browse, and download Google Fonts from the terminal via the gfonts CLI.
mvanhorn/printing-press-library
The free, offline Trigger phrases: search 1688 for, find a factory on 1688 for, wholesale price on 1688 for, who is the cheapest supplier on 1688 for, compare 1688 suppliers for, use 1688, run 1688.
mvanhorn/printing-press-library
Inspect known Activity Japan plan IDs or URLs, compare dated prices and sessions, check language-sitemap coverage, and hand off to canonical booking pages.
mvanhorn/printing-press-library
Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...
mvanhorn/printing-press-library
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.
Discover Japanese RV parks and permitted overnight stops, compare vehicle limits and facilities, screen services or prepare booking contacts through Kurumatabi. Pp Kurumatabi is an agent skill from mvanhorn/printing-press-library. Discover Japanese RV parks and permitted overnight stops, compare vehicle limits and facilities, screen services or prepare booking contacts through Kurumatabi.
Pp Kurumatabi fits situations like: RV Park / くるま旅 searches; vehicle-size checks; dump-station evidence.
Run `npx skills add mvanhorn/printing-press-library --skill pp-kurumatabi -a claude-code`. Or copy the skill folder (cli-skills/pp-kurumatabi in mvanhorn/printing-press-library) into .claude/skills/pp-kurumatabi in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mvanhorn/printing-press-library --skill pp-kurumatabi -a codex`. Or copy the skill folder (cli-skills/pp-kurumatabi in mvanhorn/printing-press-library) into .agents/skills/pp-kurumatabi in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvanhorn/printing-press-library --skill pp-kurumatabi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pp-kurumatabi, .gemini/skills/pp-kurumatabi, .github/skills/pp-kurumatabi and .opencode/skills/pp-kurumatabi in your project.
Going by SKILL.md and its folder, Pp Kurumatabi needs the command-line tools its instructions call (go and npx). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.
SKILL.md names 1 domain. In commands or code: kurumatabi.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Pp Kurumatabi is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Pp Kurumatabi: Aas Discover (sickn33/agentic-awesome-skills, 47k stars), Discover Plugins (ruvnet/ruflo, 74k stars), Discover (taishi-i/awesome-japanese-nlp-resources, 1k stars) and Compare (taishi-i/awesome-japanese-nlp-resources, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,056 GitHub stars. The repository holds 506 skills in this directory. The repository was last updated on October 9, 2026.
Source: mvanhorn/printing-press-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.