Agent skill

Pp Tenki

by mvanhorn in mvanhorn/printing-press-library

Resolve Japan sightseeing places, inspect tenki.jp daily/hourly forecasts, compare user weather thresholds, or check mountain and sakura/foliage evidence with source time and year.

Apache-2.0Auto-check: notes

Install Pp Tenki

skills CLI
$ npx skills add mvanhorn/printing-press-library --skill pp-tenki -a claude-code

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

GitHub CLI
$ gh skill install mvanhorn/printing-press-library pp-tenki --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/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-tenki .claude/skills/pp-tenki && 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/

Facts

Skill name
pp-tenki
GitHub stars
2.1k
Token cost
~2.9k tokens
SKILL.md length
1,148 words
Files
1
Skills in repo
506
Repo updated
First seen
Licence
Apache-2.0

At a glance

Resolve Japan sightseeing places, inspect tenki.jp daily/hourly forecasts, compare user weather thresholds, or check mountain and sakura/foliage evidence with source time and year.

  • Works in 3 steps: Install via the Printing Press… → Verify: tenki-pp-cli --version → Ensure the reported install directory is…
  • SKILL.md covers Prerequisites: Install the CLI, Local checkout, Choose the branch and Examples, plus 5 more sections
  • Calls go and npx; reaches tenki.jp

What it does

Pp Tenki is an agent skill from mvanhorn/printing-press-library. Resolve Japan sightseeing places, inspect tenki.jp daily/hourly forecasts, compare user weather thresholds, or check mountain and sakura/foliage evidence with source time and year.

Its SKILL.md is about 2.9k 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.

Example prompts

  • “/pp-tenki”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

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

  1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and…
  2. Verify: tenki-pp-cli --version
  3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

What it can do on your machine

Read from SKILL.md and the folder at commit 76de244. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • tenki.jp

    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

Pp Tenki loads about 2.9k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 1,148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash

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 mvanhorn/printing-press-library at commit 76de244, republished under its Apache-2.0 licence (© mvanhorn). 1,148 words, ~2,914 tokens.

Download SKILL.mdSave it as .claude/skills/pp-tenki/SKILL.md (or your agent's skills folder).
name
pp-tenki
description
Resolve Japan sightseeing places, inspect tenki.jp daily/hourly forecasts, compare user weather thresholds, or check mountain and sakura/foliage evidence with source time and year.
allowed-tools
Read, Bash
author
zjsng
license
Apache-2.0
argument-hint
<command> [flags]
<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/travel/tenki/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/". -->

tenki.jp

Prerequisites: Install the CLI

This skill drives the tenki-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
    bash
    npx -y @mvanhorn/printing-press-library install tenki --cli-only
  2. Verify: tenki-pp-cli --version
  3. Ensure the reported install directory is on $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:

bash
go install github.com/mvanhorn/printing-press-library/library/travel/tenki/cmd/tenki-pp-cli@latest

If --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.

Local checkout

Before a public-library merge and catalog refresh, build the checkout with Go 1.26.6 or newer:

bash
go build -o bin/tenki-pp-cli ./cmd/tenki-pp-cli
bin/tenki-pp-cli --version

Use bin/tenki-pp-cli instead of the bare command prefix in examples when that verified local binary is not on $PATH.

Use command --help for current flags and bounds. Product commands read public HTML and write only local cache. Do not use this CLI for summit or route safety, historical weather observations, or unpublished future seasons.

Choose the branch

  • Resolve a name/postal code: places search; select the canonical URL explicitly. Leisure searches cover the reported bounded directory, with optional --directory, rather than nationwide keyword search.
  • Inspect identity and forecast reference: places show.
  • Inspect dates: forecast daily; add --detail for separate six-hour intervals and instants.
  • Inspect a supported activity window: forecast hourly --date YYYY-MM-DD --hours HH:00-HH:00.
  • Evaluate supplied thresholds: compare; require at least one criterion and choose its deterministic --sort key when ranking.
  • Inspect mountain evidence: mountain show; --level matches an actual source altitude.
  • Inspect seasonal reports: seasonal list or seasonal show --kind sakura|kouyou --year YYYY. For ended Sakura name discovery, choose a retained prefecture --directory; a miss covers the reported scan.

Examples

bash
tenki-pp-cli places search --query 金閣寺 --kind leisure --directory https://tenki.jp/leisure/6/29/ --limit 5 --agent --select results.places.name,results.places.url,results.search_scope
tenki-pp-cli places show --place https://tenki.jp/leisure/6/29/189/7327/ --agent
tenki-pp-cli forecast daily --place https://tenki.jp/forecast/3/16/4410/13101/ --days 3 --agent --select results.periods.date,results.periods.weather,results.periods.precip_probability_pct,results.source
tenki-pp-cli forecast hourly --place https://tenki.jp/forecast/3/16/4410/13101/ --hours 09:00-17:00 --agent --select results.periods.valid_at,results.periods.kind,results.periods.precip_rate_mm_h,results.periods.temperature_c
tenki-pp-cli compare --place https://tenki.jp/forecast/3/16/4410/13101/ --days 3 --max-pop 30 --max-temp 30 --sort max-pop --agent
tenki-pp-cli mountain show --place https://tenki.jp/mountain/famous100/5/25/150.html --level 3000 --limit 8 --agent
tenki-pp-cli seasonal show --kind kouyou --place https://tenki.jp/kouyou/3/13/30139.html --agent --select results.spot,results.source,results.status,results.year
tenki-pp-cli seasonal list --kind sakura --directory https://tenki.jp/sakura/3/16/ --query 上野 --year 2026 --limit 5 --agent
tenki-pp-cli seasonal show --kind sakura --place https://tenki.jp/sakura/3/16/54401.html --year 2026 --agent

Interpret evidence

Read the source timestamps, freshness, actual coverage and destination's forecast_reference_url before interpreting values. meta.source is the actual transport (live/local, or mixed/unavailable for comparisons); meta.metrics counts HTTP requests, cache hits and decoded source-response bytes, not network transfer bytes. Comparison decisions carry meta.data_origin: computed, a separate axis from acquisition. Missing numeric values are null; an explicit provider zero stays zero.

Weather dates/times use Asia/Tokyo. Hourly precipitation describes the preceding start–end hour; temperature/wind belong to valid_at. A 09:00–17:00 comparison uses eight complete rain intervals ending 10:00–17:00 and temperature/wind instants from 09:00 through 17:00, inclusive. The hourly inspection command also shows the 09:00 endpoint and its preceding rain interval. Probabilities are per source interval: their maximum is not the probability of any rain over the outing. Rain thresholds use daily amount in mm or hourly rate in mm/h; wind uses m/s; temperature uses °C. Estimated past hours are estimated_actual, not forecasts or municipal station observations.

Daily temperature minima are morning lows and maxima are daytime highs. Today's temperature fields can mix forecasts with estimated actual values; their per-field type stays explicit and cannot certify a forecast-only criterion. Today's daily period can be partial, with remaining weather/probability coverage beginning at issuance. Four six-hour rain intervals coexist with five instant labels; keep their boundaries distinct. Daily values cannot certify an hourly window. Daily wind is max_of_five_source_instants at 00/06/12/18/24; it is not a continuous daily maximum. Days 12–14 may contain confidence letters and fewer fields; retain unknown values and source confidence letters as supplied.

Municipal weather refers to the government-office vicinity; leisure and seasonal weather refers to the linked municipality. Preserve requested destination identity separately. Mountain main weather is foothill weather. Altitude tables are nearby_model_guidance, with their own model_initial_at; they do not establish summit weather, trail condition or ascent safety. A mountain destination cannot earn a summit suitability result from municipal/foothill evidence.

Seasonal spot reports, predictions and normal periods are distinct evidence. Keep requested_year, actual year, update state, report date and weather issue time separate. A fresh forecast does not refresh seasonal facts. Ended Sakura, a year mismatch or future-date current foliage cannot be positive seasonal evidence. --season pairs evidence without a hidden peak-quality criterion. With no condition preference, report that explicitly and retain the raw condition. --season-condition supplies an exact raw state preference. If the source supplies no applicable exact-date prediction, future seasonal suitability remains unknown while weather criteria can still be evaluated.

Comparison returns meets_criteria, fails_criteria or insufficient_data, with per-criterion pass/fail/unknown, thresholds, source values and coverage. Missing, stale, unknown-freshness, past-estimated, partial or out-of-horizon evidence cannot produce meets_criteria. A definite failed criterion can produce fails_criteria while other criteria remain explicitly unknown. Ties are shown; there is no universal sightseeing score. Thresholds describe the user's preferences.

Show full SKILL.md (419 more words)Show less

Output and bounded acquisition

Serialize source calls, including MCP command calls. Pacing is capped at one request per second per provider client/CLI or MCP invocation. Separate concurrent invocations do not coordinate; --rate-limit only lowers the per-invocation ceiling and does not enforce an aggregate or global limit.

--agent sets JSON, compact, noninteractive defaults. Product stdout is one compact {meta,results} document; diagnostics use stderr. --select projects comma-separated dotted paths, including array fields. A wholly absent path is an error. Required-input --dry-run --json succeeds without inputs/network; real invalid inputs exit 2, source errors 5, exhausted rate limits 7. Structured unavailable statuses are ordinary product outcomes.

Search returns at most 50 candidates across at most two pages. Compare accepts up to five places, fourteen dates and seventy cells; hourly output caps at 72 source rows. Daily unsupported_dates identifies absent requested dates before the output limit; partial_horizon distinguishes mixed coverage and truncated identifies row limiting. Dates outside returned source coverage stay unavailable. --refresh/--data-source live fetch again; --data-source local reads cache only; --allow-stale explicitly permits marked stale cache without positive suitability. --timeout bounds the whole command. --cache-dir selects a local page cache. Cache TTL is one hour for weather/seasonal/model pages and seven days for directories, a CLI policy rather than a verified seasonal/model provider cadence.

Access

No credentials are needed for public HTML. There is no verified supported public tenki.jp API. Terms Article 8(6) restrict non-browser/RSS acquisition. Successful HTTP access and public distribution do not establish provider authorization. Respect source denials and propagate rate limits. Preserve missing evidence instead of substituting another provider, invented future-season facts or zero-valued failed fetches.

Unique Capabilities

Evidence-based planning
  • compare — Compare selected Japan destinations and dates against explicit weather thresholds.

    Compare selected Japan destinations and dates against explicit weather thresholds.

    bash
    tenki-pp-cli compare --place https://tenki.jp/forecast/3/16/4410/13101/ --days 2 --max-pop 40 --agent
  • compare — Evaluate a specific JST outing window with complete hourly evidence.

    Evaluate a specific JST outing window with complete hourly evidence.

    bash
    tenki-pp-cli compare --place https://tenki.jp/forecast/3/16/4410/13101/ --hours 09:00-17:00 --max-pop 40 --agent
  • compare — Pair seasonal spot status with its actual forecast municipality.

    Pair seasonal spot status with its actual forecast municipality.

    bash
    tenki-pp-cli compare --place https://tenki.jp/kouyou/4/19/30314.html --season kouyou --max-pop 40 --agent
  • compare — Explain missing, stale, unsupported or mismatched evidence before recommending.

    Explain missing, stale, unsupported or mismatched evidence before recommending.

    bash
    tenki-pp-cli compare --place https://tenki.jp/forecast/3/16/4410/13101/ --days 14 --max-wind 8 --agent

Auth Setup

No credentials are required for public HTML pages. Access is undocumented and subject to tenki.jp terms; there is no verified supported public API.

Run tenki-pp-cli doctor to verify setup.

© 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

Files

Just SKILL.md in cli-skills/pp-tenki of mvanhorn/printing-press-library.

Open the folder on GitHubat commit 76de244

Compare with similar skills

Pp Tenki 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.

Pp Tenki compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pp Tenki this skillmvanhorn/printing-press-library2.1k—~2.9kAutomated safety check: NotesApache-2.0
Dailysickn33/agentic-awesome-skills47k3 repos~3.6kAutomated safety check: PassMIT
Node Inspect Debuggeropenclaw/openclaw392k1 repos~894Automated safety check: PassMIT
Daily Giftsickn33/agentic-awesome-skills47k1 repos~1.4kAutomated safety check: PassMIT-0
Blender Motion State Inspectionaffaan-m/ECC276k1 repos~2kAutomated safety check: PassMIT
Inspect Diskfelixrieseberg/windows9524k—~1.3kAutomated safety check: PassCustom licence

Similar skills

  • Daily

    sickn33/agentic-awesome-skills

    Documentation and capabilities reference for Daily. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 3 repos~3.6k tokens
    AI & LLM EngineeringAuto-check passed
  • Node Inspect Debugger

    openclaw/openclaw

    Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

    392k GitHub starsUsed in 1 repo~894 tokens
    Frontend & DesignAuto-check passed
  • Daily Gift

    sickn33/agentic-awesome-skills

    Relationship-aware daily gift engine with five-stage creative pipeline — editorial judgment, synthesis, concept generation, visual strategy, and rendering in H5, image, or video

    47k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • A skill your agent uses when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.

    276k GitHub starsUsed in 1 repo~2k tokens
    Game DevelopmentAuto-check passed
  • Inspect Disk

    felixrieseberg/windows95

    Inspect or modify the Windows 95 disk image offline with mtools — no QEMU, no Electron, no boot.

    24k GitHub stars~1.3k tokensUpdated 29 days ago
    Auto-check passed
  • Conflict resolution flow — understand the local git conflicts, present a resolution plan, and resolve them after the user approves it.

    61k GitHub stars~772 tokensUpdated today
    DevelopmentAuto-check passed

More from mvanhorn/printing-press-library

All 506 skills in this repo
  • Agent Desktop

    mvanhorn/printing-press-library

    Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.

    2.1k GitHub stars~2.3k tokensUpdated yesterday
    Auto-check: notes
  • Gfonts

    mvanhorn/printing-press-library

    Search, browse, and download Google Fonts from the terminal via the gfonts CLI.

    2.1k GitHub stars~574 tokensUpdated yesterday
    Auto-check passed
  • Pp 1688

    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.

    2.1k GitHub stars~3k tokensUpdated yesterday
    Auto-check: notes
  • Pp Activity Japan

    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.

    2.1k GitHub stars~2k tokensUpdated yesterday
    Auto-check: notes
  • Pp Adminbyrequest

    mvanhorn/printing-press-library

    Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...

    2.1k GitHub stars~3.3k tokensUpdated yesterday
    Auto-check: notes
  • Pp Agent Capture

    mvanhorn/printing-press-library

    macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.

    2.1k GitHub stars~1.6k tokensUpdated yesterday
    Auto-check: notes

Questions about Pp Tenki

What does Pp Tenki do?

Resolve Japan sightseeing places, inspect tenki.jp daily/hourly forecasts, compare user weather thresholds, or check mountain and sakura/foliage evidence with source time and year. Pp Tenki is an agent skill from mvanhorn/printing-press-library.jp daily/hourly forecasts, compare user weather thresholds, or check mountain and sakura/foliage evidence with source time and year.

How do I install Pp Tenki in Claude Code?

Run `npx skills add mvanhorn/printing-press-library --skill pp-tenki -a claude-code`. Or copy the skill folder (cli-skills/pp-tenki in mvanhorn/printing-press-library) into .claude/skills/pp-tenki in your project. Claude Code loads it when a task matches its description.

How do I install Pp Tenki in Codex?

Run `npx skills add mvanhorn/printing-press-library --skill pp-tenki -a codex`. Or copy the skill folder (cli-skills/pp-tenki in mvanhorn/printing-press-library) into .agents/skills/pp-tenki in your project. Codex loads it when a task matches its description.

Can I use Pp Tenki 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 mvanhorn/printing-press-library --skill pp-tenki -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-tenki, .gemini/skills/pp-tenki, .github/skills/pp-tenki and .opencode/skills/pp-tenki in your project.

What does Pp Tenki need to run?

Going by SKILL.md and its folder, Pp Tenki needs the command-line tools its instructions call (go and npx). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.

Does Pp Tenki access the network?

SKILL.md names 1 domain. In commands or code: tenki.jp; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Pp Tenki safe to install?

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.

What licence does Pp Tenki use?

Pp Tenki 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.

How many tokens does Pp Tenki use?

About 2.9k tokens (SKILL.md is roughly 12k 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 Pp Tenki?

Skills that share tags, products or a category with Pp Tenki: Daily (sickn33/agentic-awesome-skills, 47k stars), Node Inspect Debugger (openclaw/openclaw, 392k stars), Daily Gift (sickn33/agentic-awesome-skills, 47k stars) and Blender Motion State Inspection (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pp Tenki?

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.