Menu
For complex behavior: build from tiny functions, chain transformations, make code read like a pipeline of operations.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Conducts iterative deep research on any topic using web search, progressive exploration, and structured synthesis. Use when asked for comprehensive research, deep investigation, thorough analysis, or multi-source exploration of any topic. Triggers: research, investigate, deep dive, comprehensive analysis, explore thoroughly, find everything about.
For cross-cutting concerns: add behavior without modifying functions, caching, timing, logging, validation wrappers.
For performance work: measure before changing, profile to find bottlenecks, compare before and after.
For symbolic computation: ASTs, mathematical expressions, code that manipulates code structure, expression transformations.
For ordered processing: A* search, Dijkstra, event simulation, task scheduling. Efficient min/max extraction with heap-based queue.
For dynamic programming: overlapping subproblems, recursive solutions with repeated computations, memoization to avoid redundant work.
| name | compose-small-helpers |
| description | For complex behavior: build from tiny functions, chain transformations, make code read like a pipeline of operations. |
Build complex operations from tiny, single-purpose functions.
# Instead of one complex function:
def process(text):
words = text.lower().split()
words = [w for w in words if len(w) > 2]
words = [w for w in words if w not in stopwords]
counts = {}
for w in words:
counts[w] = counts.get(w, 0) + 1
return sorted(counts.items(), key=lambda x: -x[1])[:10]
# Compose small helpers:
def process(text):
return top_n(10, count(remove_stopwords(filter_short(tokenize(text)))))
def tokenize(text):
return text.lower().split()
def filter_short(words, min_len=3):
return [w for w in words if len(w) >= min_len]
def remove_stopwords(words):
return [w for w in words if w not in STOPWORDS]
def count(items):
from collections import Counter
return Counter(items)
def top_n(n, counter):
return counter.most_common(n)
# Spell correction (spell.py)
def correction(word):
return max(candidates(word), key=P)
def candidates(word):
return known([word]) or known(edits1(word)) or known(edits2(word)) or [word]
def known(words):
return set(w for w in words if w in WORDS)
def P(word, N=sum(WORDS.values())):
return WORDS[word] / N
# Each function is tiny but composable!
# Rainfall problem (DocstringFixpoint.ipynb)
def rainfall(numbers):
return mean(non_negative(upto(-999, numbers)))
# Sudoku (sudoku.py)
def solve(grid):
return search(parse_grid(grid))
# Lisp interpreter (lis.py)
def repl():
while True:
print(lispstr(eval(parse(input('> ')))))
# Each layer does one thing, composes naturally
tokenize, count, filter_short