npx claudepluginhub pjt222/agent-almanacThis skill uses the workspace's default tool permissions.
---
Designs puzzles that teach mechanics through play, create 'aha' moments, and balance challenge without frustration. Draws from The Witness, Portal, Baba Is You, and escape rooms. Use for puzzle or game-design tasks.
Fetches Sudoku puzzles of various difficulties, stores as JSON in workspace, renders printable PDFs or images on demand, reveals solutions for cells, boxes, or full puzzles.
Share bugs, ideas, or general feedback.
Parse and validate PILES notation strings for puzzle piece fusion groups.
generate_puzzle()"1-2-3,4-5")"center", "ring1", "R1")library(jigsawR)
result <- validate_piles_syntax("1-2-3,4-5")
# Returns TRUE if valid, error message if invalid
Check for common syntax errors:
"1-2(-3)-4" with mismatched ()-, ,, :, (, ) and keywords allowed"1-2,,3-4" (double comma)Expected: TRUE for valid syntax, descriptive error for invalid.
On failure: Print the exact PILES string and the validation error message.
groups <- parse_piles("1-2-3,4-5")
# Returns: list(c(1, 2, 3), c(4, 5))
For strings with ranges:
groups <- parse_piles("1:6,7-8")
# Returns: list(c(1, 2, 3, 4, 5, 6), c(7, 8))
Expected: List of integer vectors, one per fusion group, with correct piece IDs and group boundaries.
On failure: Check that the PILES string passed syntax validation in Step 1 first. If parsing returns unexpected groups, verify that - separates pieces within a group and , separates groups, and that range notation (:) expands to inclusive endpoints.
Describe each group for the user:
"1-2-3,4-5" -> "Group 1: fuse pieces 1, 2, and 3. Group 2: fuse pieces 4 and 5.""1:6" -> "Group 1: fuse pieces 1 through 6 (6 pieces).""center,ring1" -> "Group 1: center piece. Group 2: all pieces in ring 1."Expected: Each fusion group is described in plain language with piece counts and identifiers, making the notation understandable to non-technical users.
On failure: If keywords cannot be explained (e.g., "ring1" has no clear meaning), the notation may require a puzzle result object for context. Advise the user to provide the puzzle type or use numeric piece IDs instead.
If a puzzle result object is available, verify:
# Generate the puzzle first
puzzle <- generate_puzzle(type = "hexagonal", grid = c(3), size = c(200))
# Parse with puzzle context (resolves keywords)
groups <- parse_fusion("center,ring1", puzzle)
Check:
Expected: All piece IDs valid. Adjacent pieces fuse cleanly.
On failure: List invalid piece IDs or non-adjacent pairs.
Verify parse/serialize fidelity:
original <- "1-2-3,4-5"
groups <- parse_piles(original)
roundtrip <- to_piles(groups)
# roundtrip should equal original (or canonical equivalent)
groups2 <- parse_piles(roundtrip)
identical(groups, groups2) # Must be TRUE
Expected: Round-trip produces identical group lists, confirming that parse_piles() and to_piles() are inverses.
On failure: If round-trip differs, check whether the serializer normalizes the notation (e.g., sorting piece IDs or converting ranges to explicit lists). Canonical differences are acceptable as long as identical(groups, groups2) returns TRUE.
# Basic syntax
"1-2" # Fuse pieces 1 and 2
"1-2-3,4-5" # Two groups: (1,2,3) and (4,5)
"1:6" # Range: pieces 1 through 6
# Keywords (require puzzle_result)
"center" # Center piece (hex/concentric)
"ring1" # All pieces in ring 1
"R1" # Row 1 (rectangular)
"boundary" # All boundary pieces
# Functions
parse_piles("1-2-3,4-5") # Parse PILES string
parse_fusion("1-2-3", puzzle) # Auto-detect format
to_piles(list(c(1,2), c(3,4))) # Convert to PILES
validate_piles_syntax("1-2(-3)-4") # Validate syntax
validate_piles_syntax() returns TRUE for valid stringsparse_piles() returns correct group lists"center" require a puzzle result object. Pass it to parse_fusion(), not parse_piles()."1:6" includes both endpoints (1, 2, 3, 4, 5, 6).generate-puzzle — generate puzzles with fusion groupsadd-puzzle-type — new types need PILES/fusion supportrun-puzzle-tests — test PILES parsing with the full suite