Agent skill
hol4
HOL4 proof development pipeline - planning, sketching, and proving phases. (project)
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/development/hol4
SKILL.md
HOL4 Proof Pipeline Skills
Three-phase proof development methodology:
/hol4-plan
Interactive proof planning. Creates mathematical argument with validated assumptions. See plan.md
/hol4-sketch
Translate plan to HOL4 sketch. Creates SML with cheats + task files for subagents. See sketch.md
/hol4-prove
Fill in cheats and complete proofs. Interactive or autonomous mode. See prove.md
Autonomous Execution
python hol_planner.py --goal "prove theorem X"
python hol_sketch.py --plan plan.md --workdir /path
python hol_proof_agent.py --task TASK_foo.md
python hol_pipeline.py --theorem X --workdir /path # end-to-end
Methodology Prompts
Full prompts in prompts/hol4/:
planner.md- Planning methodologysketch_impl.md- Sketching methodologyproof_agent.template.md- Proving methodology
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?