survival_resource_rules
Apply AutoAscend nutrition and emergency resource rules to symbolic NetHack state memory.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- survival_resource_rules
- description
- Apply AutoAscend nutrition and emergency resource rules to symbolic NetHack state memory.
02 资源文件 3
- 脚本scripts/survival_rules.py2.1 KB
- 脚本scripts/survival.py1.4 KB
- 脚本tests/test_survival.py545 B
03 SKILL.md 正文
Survival and Resource Rules
Use this skill when hunger, food, corpse, or prayer decisions should preempt ordinary exploration. It is designed for AutoAscend-style symbolic control and bounded recovery tests.
Inputs
- State memory with
hero.hunger,hero.turn,hero.last_prayer_turn,inventory, and optionalcorpses. - Optional rule parameters when importing the helper function.
Outputs
- Recommended survival action.
- Target item or corpse.
- Rule name and semantic action queue.
Workflow
- Prefer fresh safe corpses while the hero is not satiated.
- If hungry or worse, eat carried food rations or equivalent inventory food.
- If fainting and prayer cooldown elapsed, pray.
- Otherwise return an explicit no-action result.
Validation
Run python scripts/survival_rules.py memory.json --output survival.json or the tests. The tests cover safe-corpse preference, ration fallback, prayer cooldown, and no-action cases.
Limitations
The skill does not identify real NetHack corpse safety from glyphs. Callers must provide safety metadata or combine it with a richer parser.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).