skills/let-fate-decide/SKILL.md
Draws 4 Tarot cards using os.urandom() to inject entropy into planning. Use when prompts are vague, the user says 'let fate decide', makes Yu-Gi-Oh references, demonstrates indifference about approach, or multiple approaches are equally valid. Interprets the spread to generate actionable next steps from randomized input.
npx skillsauth add philoserf/claude-code-setup skills/let-fate-decideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When the path forward is unclear, let the cards speak.
Run the drawing script:
uv run --script ${CLAUDE_SKILL_DIR}/scripts/draw_cards.py
The script outputs JSON with 4 drawn cards, each with a file path relative to ${CLAUDE_SKILL_DIR}
Read each card's meaning file to understand the draw
Interpret the spread using the guide at references/interpretation-guide.md
Apply the interpretation to the task at hand
ask-questions-if-underspecified) would better serve the user by gathering actual requirementsThe script uses os.urandom() for cryptographic randomness:
The 4 card positions represent:
| Position | Represents | Question It Answers | | -------- | ----------------- | ----------------------------------- | | 1 | The Context | What is the situation really about? | | 2 | The Challenge | What obstacle or tension exists? | | 3 | The Guidance | What approach should be taken? | | 4 | The Outcome | Where does this path lead? |
All 78 card meaning files live directly in assets/:
00-the-fool.md through 21-the-world.mdrank-of-suit.md (e.g., ace-of-wands.md, king-of-pentacles.md)After drawing, read each card's file and synthesize meaning. See references/interpretation-guide.md for the full interpretation workflow.
Key rules:
User: "I dunno, just make it work somehow"
[Draw cards]
1. The Magician (upright) - Context: All tools are available
2. Five of Swords (reversed) - Challenge: Let go of a combative approach
3. The Star (upright) - Guidance: Follow the aspirational path
4. Ten of Pentacles (upright) - Outcome: Long-term stability
Interpretation: The cards suggest you have everything you need (Magician).
The challenge is avoiding overengineering or adversarial thinking about edge
cases (Five of Swords reversed). Follow the clean, hopeful approach (Star)
and build for lasting maintainability (Ten of Pentacles).
Approach: Implement the simplest correct solution with clear structure,
prioritizing long-term readability over clever optimizations.
User: "Should I refactor the auth module or add the new endpoint first?"
[Draw cards]
1. Nine of Swords (reversed) - Context: Anxiety about this is overblown
2. The Tower (reversed) - Challenge: A disruption is being avoided or delayed
3. Four of Swords (reversed) - Guidance: Don't rest yet — act now
4. Eight of Cups (reversed) - Outcome: Reluctance to walk away from sunk cost
Interpretation: The spread is reversal-heavy — something is being overlooked.
The worry about breaking things is exaggerated (Nine of Swords reversed), but
delaying the disruptive change is making it worse (Tower reversed). The cards
say stop hesitating (Four of Swords reversed) and don't cling to the current
auth code just because it exists (Eight of Cups reversed).
Approach: Refactor auth first. The reversed Tower says the upheaval is coming
either way — better to control it now than have it forced later.
If the drawing script fails:
| Rationalization | Why Wrong | | --------------------------------------------------- | ----------------------------------------------------------------- | | "The cards said to, so I must" | Cards inform direction, they don't override safety or correctness | | "This reading justifies my pre-existing preference" | Be honest if the reading challenges your instinct | | "The reversed card means do nothing" | Reversed means a different angle, not inaction | | "Major Arcana overrides user requirements" | User requirements always take priority over card readings | | "I'll keep drawing until I get what I want" | One draw per decision point; accept the reading |
brainstorming insteadtesting
Audits ~/.claude/skills/ for unused entries, duplicate names, missing descriptions, and the longest descriptions. Use when trimming the user-level skill set, asking which skills are unused, finding duplicates, or auditing skill hygiene.
tools
Publishes and manages Flowershow sites with the `fl` CLI (the Go-based successor to the deprecated `@flowershow/publish` npm package). Use when publishing a note or folder to Flowershow, syncing updates to an existing site, managing auth, listing or deleting sites, or installing/upgrading the CLI.
tools
Copy edits prose while preserving voice and register. Use when asked to edit, copy edit, line edit, proofread, revise, polish, tighten, rewrite, or clean up essays, articles, drafts, or fiction. Flags wordiness, passive voice, clichés, hedging, and nominalizations with bracket markup or clean rewrites.
tools
Improves CLAUDE.md by analyzing conversation patterns. Use when Claude keeps repeating a mistake, when teaching a new preference, or when consolidating guidance from repeated instructions. Captures recurring corrections and style preferences into project instructions.