New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Solitaire Play

by pockebot in pockebot/openpocket

Play Klondike Solitaire in mobile solitaire apps. An agent skill from pockebot/openpocket.

MITAuto-check passed

Install Solitaire Play

skills CLI
$ npx skills add pockebot/openpocket --skill solitaire-play -a claude-code

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

GitHub CLI
$ gh skill install pockebot/openpocket solitaire-play --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/pockebot/openpocket.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/solitaire-play .claude/skills/solitaire-play && 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
solitaire-play
GitHub stars
847
Token cost
~958 tokens
SKILL.md length
487 words
Files
2
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Play Klondike Solitaire in mobile solitaire apps. An agent skill from pockebot/openpocket.

  • Works in 6 steps: Safe foundation moves → Reveal facedown cards → Build/merge tableau stacks → …
  • The user asks to play/solve/win solitaire
  • SKILL.md covers Preconditions, Rules Primer (Klondike), Operation Mapping on Phone and Move Priority (Default…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Solitaire Play is an agent skill from pockebot/openpocket. Play Klondike Solitaire in mobile solitaire apps. Use when the user asks to play/solve/win solitaire, needs move-by-move card decisions, or asks for solitaire operation guidance on phone UI (tap, swipe-based drag, stock cycling, and foundation strategy).

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It works with Tableau. The repository describes itself as: 🐹 An Intelligent Phone That Never Sleeps. The licence is MIT.

When your agent uses it

  • The user asks to play/solve/win solitaire
  • Needs move-by-move card decisions
  • Asks for solitaire operation guidance on phone UI (tap
  • Swipe-based drag

Example prompts

  • “/solitaire-play”

Workflow steps

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

  1. Safe foundation moves
  2. Reveal facedown cards
  3. Build/merge tableau stacks
  4. Use empty columns correctly
  5. Play waste efficiently
  6. Draw from stock

What it can do on your machine

Read from SKILL.md and the folder at commit d4dae3d. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Solitaire Play loads about 958 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 487 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~958

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 pockebot/openpocket at commit d4dae3d, republished under its MIT licence (© pockebot). 487 words, ~958 tokens.

Download SKILL.mdSave it as .claude/skills/solitaire-play/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
solitaire-play
description
Play Klondike Solitaire in mobile solitaire apps. Use when the user asks to play/solve/win solitaire, needs move-by-move card decisions, or asks for solitaire operation guidance on phone UI (tap, swipe-based drag, stock cycling, and foundation strategy).

Solitaire Play

Use this skill to play standard Klondike Solitaire in mobile apps with deterministic and low-risk moves.

Preconditions

  • Confirm the game screen is visible (tableau columns, stock/waste, foundations).
  • Dismiss popups, ads, tutorials, and rate dialogs first.
  • Detect whether the app is Draw-1 or Draw-3 by tapping stock once and observing waste behavior.

Rules Primer (Klondike)

  • Goal: move all cards to 4 foundations (A -> K by suit).
  • Tableau build rule: descending rank with alternating colors (e.g., red 9 on black 10).
  • Only Kings (or King-led stacks) can move to empty tableau columns.
  • Face-down cards in tableau are revealed when the covering face-up card(s) are moved away.
  • Stock/Waste:
    • Draw-1: one card enters waste per stock tap.
    • Draw-3: three cards cycle per stock tap; only top waste card is playable.

Operation Mapping on Phone

Use available phone actions to emulate card interactions:

  • Single-card quick move:
    • Prefer tap on card if app supports auto-move to foundation/tableau.
  • Precise move (card/stack relocation):
    • Prefer drag(x1, y1, x2, y2, durationMs).
    • Recommended durationMs: 250-450.
  • Long press (if app requires hold before drag):
    • Use long_press_drag(x1, y1, x2, y2, holdMs, durationMs).
    • Recommended holdMs: 400-700; durationMs: 220-380.
  • Scrolling within menus/history:
    • Use swipe with long vertical distance.
  • Never rely on random gestures. Keep start/end points centered on visible card bodies.

Move Priority (Default Heuristic)

Apply this priority order each turn:

  1. Safe foundation moves:
    • Move Aces and Twos to foundation immediately.
    • Move higher cards to foundation when it does not block revealing facedown tableau cards.
  2. Reveal facedown cards:
    • Prefer tableau moves that uncover hidden cards over cosmetic rearrangement.
  3. Build/merge tableau stacks:
    • Create longer alternating descending stacks only when it enables future reveals or king placement.
  4. Use empty columns correctly:
    • Move a King (or King-led stack) to empty tableau columns when it helps reveal cards.
  5. Play waste efficiently:
    • Try waste top card to tableau first, then to foundation.
  6. Draw from stock:
    • Draw only when no productive tableau/foundation move exists.
Show full SKILL.md (166 more words)Show less

Procedure

  1. Observe state:
    • Identify all playable face-up tableau tails.
    • Check waste top card and foundation tops.
  2. Execute one highest-priority legal move.
  3. Re-evaluate board after every move (never assume expected outcome).
  4. If no move exists, tap stock once and repeat evaluation.
  5. If stock recycle/reset is available, recycle and continue.
  6. Stop when either:
    • all cards reach foundation (win), or
    • no legal moves remain after full stock cycle (stalled/loss state).

Failure Handling

  • If drag misses target:
    • Retry once with more centered coordinates and slightly longer duration (+100ms).
  • If app does not support tap auto-move:
    • Switch to explicit drag-only flow using drag / long_press_drag.
  • If animation blocks actions:
    • Use a short wait before next move.
  • If board recognition is uncertain (overlap, tiny cards, occlusion):
    • Avoid risky multi-card drags; prefer reversible moves or stock draw.

Completion Criteria

  • Success: all four foundations are complete from Ace to King.
  • Partial completion report:
    • include draw mode (Draw-1/Draw-3),
    • number of foundations completed,
    • whether the run is solvable/stalled from current state.

© pockebot, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/solitaire-play of pockebot/openpocket.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit d4dae3d

Compare with similar skills

Solitaire Play 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.

Solitaire Play compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Solitaire Play this skillpockebot/openpocket847—~958Automated safety check: PassMIT
Tableau Dashboard CreatorKilo-Org/kilo-marketplace190—~3.8kAutomated safety check: NotesMIT
Bi Measure BuilderOneWave-AI/claude-skills328—~2.2kAutomated safety check: PassMIT
Consumer Goods Tpe Dashboard Configureforcedotcom/sf-skills1.1k—~1.5kAutomated safety check: PassApache-2.0
Normalisation Juridique Fr Christophe Quezel Ambrunazlawve-ai/awesome-legal-skills842—~2.6kAutomated safety check: PassCustom licence
TableauLeoYeAI/openclaw-master-skills2.2k—~4.8kAutomated safety check: PassMIT

Similar skills

  • Tableau Dashboard Creator

    Kilo-Org/kilo-marketplace

    Takes a plain-language dashboard request through brand setup, data exploration, planning, an interactive HTML mock and a Tableau implementation spec.

    190 GitHub stars~3.8k tokensUpdated 10 days ago
    Data & AnalyticsAuto-check: notes

  • Bi Measure Builder

    OneWave-AI/claude-skills

    Writes, explains, debugs, and optimizes BI calculations - Power BI / Fabric DAX measures and calculated columns, Tableau calculated fields (FIXED/INCLUDE/EXCLUDE LOD expressions, table…

    328 GitHub stars~2.2k tokensUpdated 7 days ago
    Data & AnalyticsAuto-check passed

  • Consumer Goods Tpe Dashboard Configure

    forcedotcom/sf-skills

    End-to-end headless setup of Trade Promotion Effectiveness (TPE) dashboards for a Trade Promotion Management (TPM) Cloud org, covering tenant pairing checks, permission sets, SSOT and Tableau Next…

    1.1k GitHub stars~1.5k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed

  • Tableau

    LeoYeAI/openclaw-master-skills

    Expert on modern configuration converter — converts Excel/CSV/XML/YAML into Protobuf-backed JSON/Text/Bin configs via protogen + confgen pipeline.

    2.2k GitHub stars~4.8k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

  • Chart Selector

    revfactory/harness-100

    Methodology for selecting optimal chart types based on data type and analysis purpose.

    1.3k GitHub stars~1.1k tokensUpdated 6 mo ago
    Data & AnalyticsAuto-check passed

More from pockebot/openpocket

All 23 skills in this repo

  • Capcut Edit

    pockebot/openpocket

    Edit videos and beautify photos in CapCut on mobile. An agent skill from pockebot/openpocket.

    847 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Clash Of Clans Play

    pockebot/openpocket

    Play Clash of Clans on mobile with autonomous tactical decisions.

    847 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Duolingo Play

    pockebot/openpocket

    Help users complete Duolingo language lessons. An agent skill from pockebot/openpocket.

    847 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed

  • Human Auth Biometric

    pockebot/openpocket

    Handle biometric authentication delegation (fingerprint, face recognition) when the Agent Phone lacks biometric hardware.

    847 GitHub stars~506 tokensUpdated 3 mo ago
    Auto-check passed

  • Human Auth Camera

    pockebot/openpocket

    Handle camera photo capture delegation from Human Phone. An agent skill from pockebot/openpocket.

    847 GitHub stars~569 tokensUpdated 3 mo ago
    Auto-check passed

  • Human Auth Contacts Data

    pockebot/openpocket

    Handle contacts, calendar, files, and notification data delegation from Human Phone.

    847 GitHub stars~669 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Solitaire Play

What does Solitaire Play do?

Play Klondike Solitaire in mobile solitaire apps. An agent skill from pockebot/openpocket. Solitaire Play is an agent skill from pockebot/openpocket. Play Klondike Solitaire in mobile solitaire apps.

When should I use Solitaire Play?

Solitaire Play fits situations like: the user asks to play/solve/win solitaire; needs move-by-move card decisions; asks for solitaire operation guidance on phone UI (tap; swipe-based drag.

How do I install Solitaire Play in Claude Code?

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

How do I install Solitaire Play in Codex?

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

Can I use Solitaire Play 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 pockebot/openpocket --skill solitaire-play -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/solitaire-play, .gemini/skills/solitaire-play, .github/skills/solitaire-play and .opencode/skills/solitaire-play in your project.

What does Solitaire Play need to run?

SKILL.md names no scripts, command-line tools or credentials: Solitaire Play is instructions for the agent only.

Does Solitaire Play 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 Solitaire Play 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 Solitaire Play use?

Solitaire Play 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 Solitaire Play use?

About 958 tokens (SKILL.md is roughly 3.8k 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 Solitaire Play?

Skills that share tags, products or a category with Solitaire Play: Tableau Dashboard Creator (Kilo-Org/kilo-marketplace, 190 stars), Bi Measure Builder (OneWave-AI/claude-skills, 328 stars), Consumer Goods Tpe Dashboard Configure (forcedotcom/sf-skills, 1.1k stars) and Normalisation Juridique Fr Christophe Quezel Ambrunaz (lawve-ai/awesome-legal-skills, 842 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Solitaire Play?

pockebot (a GitHub organization) maintains it in pockebot/openpocket, which has 847 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 9, 2026.

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