templates/skills/languages/lisp/SKILL.md
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
npx skillsauth add hivellm/rulebook LispInstall 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.
CRITICAL: Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
# Complete quality check sequence:
sbcl --eval '(ql:quickload :sblint)' --eval '(sblint:run-lint "src/")' # Linting
sbcl --load tests/run-tests.lisp # All tests
sbcl --eval '(asdf:make :your-system)' # Build with ASDF
CRITICAL: Use SBCL 2.3+ or CCL with ASDF3 and modern tooling.
(defsystem "your-system"
:description "Your system description"
:version "0.1.0"
:author "Your Name <[email protected]>"
:license "MIT"
:depends-on (:alexandria
:cl-ppcre
:str)
:components ((:module "src"
:components
((:file "package")
(:file "main" :depends-on ("package")))))
:in-order-to ((test-op (test-op "your-system/tests"))))
(defsystem "your-system/tests"
:depends-on ("your-system"
"fiveam")
:components ((:module "tests"
:components
((:file "package")
(:file "main-tests" :depends-on ("package")))))
:perform (test-op (o c) (symbol-call :fiveam :run! :your-system-tests)))
IMPORTANT: These commands MUST match your GitHub Actions workflows!
# Pre-Commit Checklist (MUST match .github/workflows/*.yml)
# 1. Lint (matches workflow)
sblint your-system.asd
# 2. Load system (check for errors - matches workflow)
sbcl --non-interactive --load your-system.asd \
--eval '(ql:quickload :your-system)' \
--eval '(quit)'
# 3. Run tests (matches workflow)
sbcl --non-interactive \
--eval '(ql:quickload :your-system/tests)' \
--eval '(asdf:test-system :your-system)' \
--eval '(quit)'
# If ANY fails: ❌ DO NOT COMMIT - Fix first!
(in-package :your-system/tests)
(def-suite your-system-tests
:description "Main test suite")
(in-suite your-system-tests)
(test process-data-test
"Test data processing"
(is (equal '(2 4 6) (process-data '(1 2 3))))
(is (null (process-data '())))
(signals error (process-data nil)))
(test validate-input-test
"Test input validation"
(is-true (validate-input "test"))
(is-false (validate-input "")))
<!-- LISP:END -->research
Create structured analyses with numbered findings, execution plans, and task materialization
research
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
development
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
data-ai
Autonomous AI agent loop for iterative task implementation (@hivehub/rulebook ralph)