@r1z4x/tezgah 1.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (582) hide show
  1. package/CHANGELOG.md +738 -0
  2. package/LICENSE +21 -0
  3. package/MANIFEST +753 -0
  4. package/README.de.md +169 -0
  5. package/README.es.md +168 -0
  6. package/README.fr.md +166 -0
  7. package/README.md +161 -0
  8. package/README.tr.md +163 -0
  9. package/agents/tezgah-reviewer.md +70 -0
  10. package/bin/codegen +337 -0
  11. package/bin/consult +797 -0
  12. package/bin/tezgah-adhd +50 -0
  13. package/bin/tezgah-agents +45 -0
  14. package/bin/tezgah-capture +66 -0
  15. package/bin/tezgah-context +96 -0
  16. package/bin/tezgah-decisions +213 -0
  17. package/bin/tezgah-design +953 -0
  18. package/bin/tezgah-docs +1199 -0
  19. package/bin/tezgah-doctor +497 -0
  20. package/bin/tezgah-dsh +37 -0
  21. package/bin/tezgah-dsh.cmd +70 -0
  22. package/bin/tezgah-gate +75 -0
  23. package/bin/tezgah-import-ai-research +439 -0
  24. package/bin/tezgah-index +32 -0
  25. package/bin/tezgah-lessons +148 -0
  26. package/bin/tezgah-mcp +322 -0
  27. package/bin/tezgah-migrate +324 -0
  28. package/bin/tezgah-pony +50 -0
  29. package/bin/tezgah-research +772 -0
  30. package/bin/tezgah-rollback +93 -0
  31. package/bin/tezgah-route +124 -0
  32. package/bin/tezgah-setup +5798 -0
  33. package/bin/tezgah-status +383 -0
  34. package/bin/tezgah-task +607 -0
  35. package/bin/tezgah-taste +423 -0
  36. package/bin/tezgah-triage +485 -0
  37. package/bin/tezgah.js +36 -0
  38. package/commands/adhd.md +21 -0
  39. package/commands/ponytail.md +21 -0
  40. package/docs/README.md +112 -0
  41. package/docs/architecture.md +226 -0
  42. package/docs/citations-baseline.json +59 -0
  43. package/docs/clarity-baseline.json +116 -0
  44. package/docs/contract.md +416 -0
  45. package/docs/environment.md +141 -0
  46. package/docs/evidence.md +831 -0
  47. package/docs/feature-audit.md +139 -0
  48. package/docs/gate.md +407 -0
  49. package/docs/glossary.md +201 -0
  50. package/docs/hosts.md +400 -0
  51. package/docs/index.json +471 -0
  52. package/docs/judge.md +193 -0
  53. package/docs/layers.md +189 -0
  54. package/docs/models.md +160 -0
  55. package/docs/operations.md +666 -0
  56. package/docs/research.md +809 -0
  57. package/docs/results/paired-outcome-2026-10.jsonl +254 -0
  58. package/docs/results/paired-outcome-2026-10.md +204 -0
  59. package/docs/skills.md +236 -0
  60. package/docs/status-line.md +315 -0
  61. package/docs/testing.md +287 -0
  62. package/docs/vision.md +117 -0
  63. package/hooks/hooks.json +33 -0
  64. package/hooks/projects-auto-init.py +98 -0
  65. package/hooks/projects-posttooluse.py +149 -0
  66. package/hooks/projects-pretooluse.py +40 -0
  67. package/hooks/projects-stop.py +60 -0
  68. package/hooks/tezgah_agents.py +817 -0
  69. package/hooks/tezgah_apps.py +266 -0
  70. package/hooks/tezgah_attest.py +255 -0
  71. package/hooks/tezgah_clarity.py +171 -0
  72. package/hooks/tezgah_components.py +140 -0
  73. package/hooks/tezgah_context.py +2953 -0
  74. package/hooks/tezgah_embed.py +765 -0
  75. package/hooks/tezgah_gate.py +2736 -0
  76. package/hooks/tezgah_guard.py +177 -0
  77. package/hooks/tezgah_index.py +124 -0
  78. package/hooks/tezgah_integrity.py +5141 -0
  79. package/hooks/tezgah_judge.py +487 -0
  80. package/hooks/tezgah_lang.py +230 -0
  81. package/hooks/tezgah_lessons.py +210 -0
  82. package/hooks/tezgah_models.py +855 -0
  83. package/hooks/tezgah_paths.py +1132 -0
  84. package/hooks/tezgah_policy.py +1039 -0
  85. package/hooks/tezgah_rank.py +77 -0
  86. package/hooks/tezgah_replay.py +1109 -0
  87. package/hooks/tezgah_research.py +5176 -0
  88. package/hooks/tezgah_shapes.py +305 -0
  89. package/hooks/tezgah_skill_pick.py +227 -0
  90. package/hooks/tezgah_snapshot.py +490 -0
  91. package/hooks/tezgah_stopspec.py +320 -0
  92. package/hooks/tezgah_task.py +458 -0
  93. package/hooks/tezgah_taste.py +201 -0
  94. package/hooks/tezgah_untrusted.py +112 -0
  95. package/hooks/tezgah_update.py +430 -0
  96. package/hosts/codex/hook.py +268 -0
  97. package/hosts/codex/hooks.json +26 -0
  98. package/hosts/cursor/hook.py +461 -0
  99. package/hosts/cursor/hooks.json +44 -0
  100. package/hosts/dsh/hooks.json +21 -0
  101. package/hosts/dsh/statusline/lib/client.js +138 -0
  102. package/hosts/dsh/statusline/lib/index.js +104 -0
  103. package/hosts/dsh/statusline/package.json +28 -0
  104. package/hosts/omp/hook.py +277 -0
  105. package/hosts/omp/tezgah-hook.ts.in +701 -0
  106. package/hosts/opencode/plugins/tezgah.js +2742 -0
  107. package/hosts/opencode/tui/tezgah-tui.tsx +151 -0
  108. package/output-styles/tezgah.md +142 -0
  109. package/package.json +32 -0
  110. package/packaging/build.sh +342 -0
  111. package/packaging/install.ps1 +166 -0
  112. package/packaging/install.sh +56 -0
  113. package/packaging/upgrade.sh +142 -0
  114. package/skills/ai-research/0-autoresearch-skill/SKILL.md +411 -0
  115. package/skills/ai-research/0-autoresearch-skill/references/agent-continuity.md +95 -0
  116. package/skills/ai-research/0-autoresearch-skill/references/progress-reporting.md +166 -0
  117. package/skills/ai-research/0-autoresearch-skill/references/skill-routing.md +219 -0
  118. package/skills/ai-research/0-autoresearch-skill/templates/findings.md +44 -0
  119. package/skills/ai-research/0-autoresearch-skill/templates/research-log.md +41 -0
  120. package/skills/ai-research/01-model-architecture/litgpt/SKILL.md +469 -0
  121. package/skills/ai-research/01-model-architecture/litgpt/references/custom-models.md +569 -0
  122. package/skills/ai-research/01-model-architecture/litgpt/references/distributed-training.md +452 -0
  123. package/skills/ai-research/01-model-architecture/litgpt/references/supported-models.md +337 -0
  124. package/skills/ai-research/01-model-architecture/litgpt/references/training-recipes.md +620 -0
  125. package/skills/ai-research/01-model-architecture/mamba/SKILL.md +260 -0
  126. package/skills/ai-research/01-model-architecture/mamba/references/architecture-details.md +207 -0
  127. package/skills/ai-research/01-model-architecture/mamba/references/benchmarks.md +256 -0
  128. package/skills/ai-research/01-model-architecture/mamba/references/training-guide.md +389 -0
  129. package/skills/ai-research/01-model-architecture/nanogpt/SKILL.md +290 -0
  130. package/skills/ai-research/01-model-architecture/nanogpt/references/architecture.md +383 -0
  131. package/skills/ai-research/01-model-architecture/nanogpt/references/data.md +477 -0
  132. package/skills/ai-research/01-model-architecture/nanogpt/references/training.md +565 -0
  133. package/skills/ai-research/01-model-architecture/rwkv/SKILL.md +260 -0
  134. package/skills/ai-research/01-model-architecture/rwkv/references/architecture-details.md +345 -0
  135. package/skills/ai-research/01-model-architecture/rwkv/references/rwkv7.md +387 -0
  136. package/skills/ai-research/01-model-architecture/rwkv/references/state-management.md +370 -0
  137. package/skills/ai-research/01-model-architecture/torchtitan/SKILL.md +358 -0
  138. package/skills/ai-research/01-model-architecture/torchtitan/references/checkpoint.md +182 -0
  139. package/skills/ai-research/01-model-architecture/torchtitan/references/custom-models.md +259 -0
  140. package/skills/ai-research/01-model-architecture/torchtitan/references/float8.md +134 -0
  141. package/skills/ai-research/01-model-architecture/torchtitan/references/fsdp.md +127 -0
  142. package/skills/ai-research/02-tokenization/huggingface-tokenizers/SKILL.md +516 -0
  143. package/skills/ai-research/02-tokenization/huggingface-tokenizers/references/algorithms.md +654 -0
  144. package/skills/ai-research/02-tokenization/huggingface-tokenizers/references/integration.md +638 -0
  145. package/skills/ai-research/02-tokenization/huggingface-tokenizers/references/pipeline.md +724 -0
  146. package/skills/ai-research/02-tokenization/huggingface-tokenizers/references/training.md +566 -0
  147. package/skills/ai-research/02-tokenization/sentencepiece/SKILL.md +235 -0
  148. package/skills/ai-research/02-tokenization/sentencepiece/references/algorithms.md +201 -0
  149. package/skills/ai-research/02-tokenization/sentencepiece/references/training.md +305 -0
  150. package/skills/ai-research/03-fine-tuning/axolotl/SKILL.md +158 -0
  151. package/skills/ai-research/03-fine-tuning/axolotl/references/api.md +5549 -0
  152. package/skills/ai-research/03-fine-tuning/axolotl/references/dataset-formats.md +1030 -0
  153. package/skills/ai-research/03-fine-tuning/axolotl/references/index.md +16 -0
  154. package/skills/ai-research/03-fine-tuning/axolotl/references/other.md +3564 -0
  155. package/skills/ai-research/03-fine-tuning/llama-factory/SKILL.md +80 -0
  156. package/skills/ai-research/03-fine-tuning/llama-factory/references/_images.md +24 -0
  157. package/skills/ai-research/03-fine-tuning/llama-factory/references/advanced.md +1056 -0
  158. package/skills/ai-research/03-fine-tuning/llama-factory/references/getting_started.md +350 -0
  159. package/skills/ai-research/03-fine-tuning/llama-factory/references/index.md +20 -0
  160. package/skills/ai-research/03-fine-tuning/llama-factory/references/other.md +32 -0
  161. package/skills/ai-research/03-fine-tuning/peft/SKILL.md +431 -0
  162. package/skills/ai-research/03-fine-tuning/peft/references/advanced-usage.md +515 -0
  163. package/skills/ai-research/03-fine-tuning/peft/references/troubleshooting.md +481 -0
  164. package/skills/ai-research/03-fine-tuning/unsloth/SKILL.md +80 -0
  165. package/skills/ai-research/03-fine-tuning/unsloth/references/index.md +8 -0
  166. package/skills/ai-research/03-fine-tuning/unsloth/references/llms.md +83 -0
  167. package/skills/ai-research/04-mechanistic-interpretability/nnsight/SKILL.md +436 -0
  168. package/skills/ai-research/04-mechanistic-interpretability/nnsight/references/README.md +79 -0
  169. package/skills/ai-research/04-mechanistic-interpretability/nnsight/references/api.md +345 -0
  170. package/skills/ai-research/04-mechanistic-interpretability/nnsight/references/tutorials.md +301 -0
  171. package/skills/ai-research/04-mechanistic-interpretability/pyvene/SKILL.md +473 -0
  172. package/skills/ai-research/04-mechanistic-interpretability/pyvene/references/README.md +74 -0
  173. package/skills/ai-research/04-mechanistic-interpretability/pyvene/references/api.md +384 -0
  174. package/skills/ai-research/04-mechanistic-interpretability/pyvene/references/tutorials.md +377 -0
  175. package/skills/ai-research/04-mechanistic-interpretability/saelens/SKILL.md +386 -0
  176. package/skills/ai-research/04-mechanistic-interpretability/saelens/references/README.md +71 -0
  177. package/skills/ai-research/04-mechanistic-interpretability/saelens/references/api.md +334 -0
  178. package/skills/ai-research/04-mechanistic-interpretability/saelens/references/tutorials.md +319 -0
  179. package/skills/ai-research/04-mechanistic-interpretability/transformer-lens/SKILL.md +346 -0
  180. package/skills/ai-research/04-mechanistic-interpretability/transformer-lens/references/README.md +55 -0
  181. package/skills/ai-research/04-mechanistic-interpretability/transformer-lens/references/api.md +363 -0
  182. package/skills/ai-research/04-mechanistic-interpretability/transformer-lens/references/tutorials.md +340 -0
  183. package/skills/ai-research/05-data-processing/nemo-curator/SKILL.md +383 -0
  184. package/skills/ai-research/05-data-processing/nemo-curator/references/deduplication.md +88 -0
  185. package/skills/ai-research/05-data-processing/nemo-curator/references/filtering.md +103 -0
  186. package/skills/ai-research/05-data-processing/ray-data/SKILL.md +326 -0
  187. package/skills/ai-research/05-data-processing/ray-data/references/integration.md +83 -0
  188. package/skills/ai-research/05-data-processing/ray-data/references/transformations.md +84 -0
  189. package/skills/ai-research/06-post-training/grpo-rl-training/README.md +98 -0
  190. package/skills/ai-research/06-post-training/grpo-rl-training/SKILL.md +572 -0
  191. package/skills/ai-research/06-post-training/miles/SKILL.md +315 -0
  192. package/skills/ai-research/06-post-training/miles/references/api-reference.md +142 -0
  193. package/skills/ai-research/06-post-training/miles/references/troubleshooting.md +353 -0
  194. package/skills/ai-research/06-post-training/openrlhf/SKILL.md +249 -0
  195. package/skills/ai-research/06-post-training/openrlhf/references/algorithm-comparison.md +405 -0
  196. package/skills/ai-research/06-post-training/openrlhf/references/custom-rewards.md +531 -0
  197. package/skills/ai-research/06-post-training/openrlhf/references/hybrid-engine.md +288 -0
  198. package/skills/ai-research/06-post-training/openrlhf/references/multi-node-training.md +455 -0
  199. package/skills/ai-research/06-post-training/simpo/SKILL.md +219 -0
  200. package/skills/ai-research/06-post-training/simpo/references/datasets.md +479 -0
  201. package/skills/ai-research/06-post-training/simpo/references/hyperparameters.md +453 -0
  202. package/skills/ai-research/06-post-training/simpo/references/loss-functions.md +351 -0
  203. package/skills/ai-research/06-post-training/slime/SKILL.md +464 -0
  204. package/skills/ai-research/06-post-training/slime/references/api-reference.md +393 -0
  205. package/skills/ai-research/06-post-training/slime/references/troubleshooting.md +387 -0
  206. package/skills/ai-research/06-post-training/torchforge/SKILL.md +433 -0
  207. package/skills/ai-research/06-post-training/torchforge/references/api-reference.md +328 -0
  208. package/skills/ai-research/06-post-training/torchforge/references/troubleshooting.md +410 -0
  209. package/skills/ai-research/06-post-training/trl-fine-tuning/SKILL.md +455 -0
  210. package/skills/ai-research/06-post-training/trl-fine-tuning/references/dpo-variants.md +228 -0
  211. package/skills/ai-research/06-post-training/trl-fine-tuning/references/online-rl.md +83 -0
  212. package/skills/ai-research/06-post-training/trl-fine-tuning/references/reward-modeling.md +123 -0
  213. package/skills/ai-research/06-post-training/trl-fine-tuning/references/sft-training.md +169 -0
  214. package/skills/ai-research/06-post-training/verl/SKILL.md +391 -0
  215. package/skills/ai-research/06-post-training/verl/references/api-reference.md +302 -0
  216. package/skills/ai-research/06-post-training/verl/references/troubleshooting.md +392 -0
  217. package/skills/ai-research/07-safety-alignment/constitutional-ai/SKILL.md +290 -0
  218. package/skills/ai-research/07-safety-alignment/llamaguard/SKILL.md +337 -0
  219. package/skills/ai-research/07-safety-alignment/nemo-guardrails/SKILL.md +297 -0
  220. package/skills/ai-research/07-safety-alignment/prompt-guard/SKILL.md +312 -0
  221. package/skills/ai-research/08-distributed-training/accelerate/SKILL.md +332 -0
  222. package/skills/ai-research/08-distributed-training/accelerate/references/custom-plugins.md +454 -0
  223. package/skills/ai-research/08-distributed-training/accelerate/references/megatron-integration.md +490 -0
  224. package/skills/ai-research/08-distributed-training/accelerate/references/performance.md +526 -0
  225. package/skills/ai-research/08-distributed-training/deepspeed/SKILL.md +141 -0
  226. package/skills/ai-research/08-distributed-training/deepspeed/references/08.md +18 -0
  227. package/skills/ai-research/08-distributed-training/deepspeed/references/09.md +174 -0
  228. package/skills/ai-research/08-distributed-training/deepspeed/references/2020.md +379 -0
  229. package/skills/ai-research/08-distributed-training/deepspeed/references/2023.md +280 -0
  230. package/skills/ai-research/08-distributed-training/deepspeed/references/assets.md +180 -0
  231. package/skills/ai-research/08-distributed-training/deepspeed/references/index.md +36 -0
  232. package/skills/ai-research/08-distributed-training/deepspeed/references/mii.md +119 -0
  233. package/skills/ai-research/08-distributed-training/deepspeed/references/other.md +1192 -0
  234. package/skills/ai-research/08-distributed-training/megatron-core/SKILL.md +366 -0
  235. package/skills/ai-research/08-distributed-training/megatron-core/references/benchmarks.md +250 -0
  236. package/skills/ai-research/08-distributed-training/megatron-core/references/parallelism-guide.md +405 -0
  237. package/skills/ai-research/08-distributed-training/megatron-core/references/production-examples.md +474 -0
  238. package/skills/ai-research/08-distributed-training/megatron-core/references/training-recipes.md +548 -0
  239. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/SKILL.md +231 -0
  240. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_dcp_async_recipe.md +14 -0
  241. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_dcp_overview.md +19 -0
  242. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_dcp_recipe.md +18 -0
  243. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_ddp_notes.md +10 -0
  244. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_device_mesh_tutorial.md +22 -0
  245. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_examples_fsdp2.md +15 -0
  246. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_fsdp1_api.md +9 -0
  247. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_fsdp2_tutorial.md +45 -0
  248. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_fully_shard_api.md +49 -0
  249. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/pytorch_tp_tutorial.md +22 -0
  250. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/ray_train_fsdp2_example.md +13 -0
  251. package/skills/ai-research/08-distributed-training/pytorch-fsdp2/references/torchtitan_fsdp_notes.md +14 -0
  252. package/skills/ai-research/08-distributed-training/pytorch-lightning/SKILL.md +346 -0
  253. package/skills/ai-research/08-distributed-training/pytorch-lightning/references/callbacks.md +437 -0
  254. package/skills/ai-research/08-distributed-training/pytorch-lightning/references/distributed.md +491 -0
  255. package/skills/ai-research/08-distributed-training/pytorch-lightning/references/hyperparameter-tuning.md +557 -0
  256. package/skills/ai-research/08-distributed-training/ray-train/SKILL.md +406 -0
  257. package/skills/ai-research/08-distributed-training/ray-train/references/multi-node.md +629 -0
  258. package/skills/ai-research/09-infrastructure/lambda-labs/SKILL.md +545 -0
  259. package/skills/ai-research/09-infrastructure/lambda-labs/references/advanced-usage.md +612 -0
  260. package/skills/ai-research/09-infrastructure/lambda-labs/references/troubleshooting.md +531 -0
  261. package/skills/ai-research/09-infrastructure/modal/SKILL.md +341 -0
  262. package/skills/ai-research/09-infrastructure/modal/references/advanced-usage.md +504 -0
  263. package/skills/ai-research/09-infrastructure/modal/references/troubleshooting.md +495 -0
  264. package/skills/ai-research/09-infrastructure/skypilot/SKILL.md +509 -0
  265. package/skills/ai-research/09-infrastructure/skypilot/references/advanced-usage.md +492 -0
  266. package/skills/ai-research/09-infrastructure/skypilot/references/troubleshooting.md +571 -0
  267. package/skills/ai-research/10-optimization/awq/SKILL.md +310 -0
  268. package/skills/ai-research/10-optimization/awq/references/advanced-usage.md +325 -0
  269. package/skills/ai-research/10-optimization/awq/references/troubleshooting.md +345 -0
  270. package/skills/ai-research/10-optimization/bitsandbytes/SKILL.md +411 -0
  271. package/skills/ai-research/10-optimization/bitsandbytes/references/memory-optimization.md +522 -0
  272. package/skills/ai-research/10-optimization/bitsandbytes/references/qlora-training.md +522 -0
  273. package/skills/ai-research/10-optimization/bitsandbytes/references/quantization-formats.md +448 -0
  274. package/skills/ai-research/10-optimization/flash-attention/SKILL.md +367 -0
  275. package/skills/ai-research/10-optimization/flash-attention/references/benchmarks.md +216 -0
  276. package/skills/ai-research/10-optimization/flash-attention/references/transformers-integration.md +294 -0
  277. package/skills/ai-research/10-optimization/gguf/SKILL.md +427 -0
  278. package/skills/ai-research/10-optimization/gguf/references/advanced-usage.md +505 -0
  279. package/skills/ai-research/10-optimization/gguf/references/troubleshooting.md +443 -0
  280. package/skills/ai-research/10-optimization/gptq/SKILL.md +450 -0
  281. package/skills/ai-research/10-optimization/gptq/references/calibration.md +338 -0
  282. package/skills/ai-research/10-optimization/gptq/references/integration.md +130 -0
  283. package/skills/ai-research/10-optimization/gptq/references/troubleshooting.md +96 -0
  284. package/skills/ai-research/10-optimization/hqq/SKILL.md +445 -0
  285. package/skills/ai-research/10-optimization/hqq/references/advanced-usage.md +529 -0
  286. package/skills/ai-research/10-optimization/hqq/references/troubleshooting.md +504 -0
  287. package/skills/ai-research/10-optimization/ml-training-recipes/SKILL.md +319 -0
  288. package/skills/ai-research/10-optimization/ml-training-recipes/references/architecture.md +320 -0
  289. package/skills/ai-research/10-optimization/ml-training-recipes/references/biomedical.md +498 -0
  290. package/skills/ai-research/10-optimization/ml-training-recipes/references/domain-specific.md +626 -0
  291. package/skills/ai-research/10-optimization/ml-training-recipes/references/experiment-loop.md +129 -0
  292. package/skills/ai-research/10-optimization/ml-training-recipes/references/optimizers.md +330 -0
  293. package/skills/ai-research/10-optimization/ml-training-recipes/references/scaling-and-selection.md +428 -0
  294. package/skills/ai-research/11-evaluation/bigcode-evaluation-harness/SKILL.md +405 -0
  295. package/skills/ai-research/11-evaluation/bigcode-evaluation-harness/references/benchmarks.md +394 -0
  296. package/skills/ai-research/11-evaluation/bigcode-evaluation-harness/references/custom-tasks.md +425 -0
  297. package/skills/ai-research/11-evaluation/bigcode-evaluation-harness/references/issues.md +395 -0
  298. package/skills/ai-research/11-evaluation/lm-evaluation-harness/SKILL.md +490 -0
  299. package/skills/ai-research/11-evaluation/lm-evaluation-harness/references/api-evaluation.md +491 -0
  300. package/skills/ai-research/11-evaluation/lm-evaluation-harness/references/benchmark-guide.md +489 -0
  301. package/skills/ai-research/11-evaluation/lm-evaluation-harness/references/custom-tasks.md +603 -0
  302. package/skills/ai-research/11-evaluation/lm-evaluation-harness/references/distributed-eval.md +520 -0
  303. package/skills/ai-research/11-evaluation/nemo-evaluator/SKILL.md +494 -0
  304. package/skills/ai-research/11-evaluation/nemo-evaluator/references/adapter-system.md +341 -0
  305. package/skills/ai-research/11-evaluation/nemo-evaluator/references/configuration.md +448 -0
  306. package/skills/ai-research/11-evaluation/nemo-evaluator/references/custom-benchmarks.md +316 -0
  307. package/skills/ai-research/11-evaluation/nemo-evaluator/references/execution-backends.md +362 -0
  308. package/skills/ai-research/12-inference-serving/llama-cpp/SKILL.md +258 -0
  309. package/skills/ai-research/12-inference-serving/llama-cpp/references/optimization.md +90 -0
  310. package/skills/ai-research/12-inference-serving/llama-cpp/references/quantization.md +214 -0
  311. package/skills/ai-research/12-inference-serving/llama-cpp/references/server.md +126 -0
  312. package/skills/ai-research/12-inference-serving/sglang/SKILL.md +442 -0
  313. package/skills/ai-research/12-inference-serving/sglang/references/deployment.md +491 -0
  314. package/skills/ai-research/12-inference-serving/sglang/references/radix-attention.md +414 -0
  315. package/skills/ai-research/12-inference-serving/sglang/references/structured-generation.md +542 -0
  316. package/skills/ai-research/12-inference-serving/tensorrt-llm/SKILL.md +187 -0
  317. package/skills/ai-research/12-inference-serving/tensorrt-llm/references/multi-gpu.md +299 -0
  318. package/skills/ai-research/12-inference-serving/tensorrt-llm/references/optimization.md +243 -0
  319. package/skills/ai-research/12-inference-serving/tensorrt-llm/references/serving.md +471 -0
  320. package/skills/ai-research/12-inference-serving/vllm/SKILL.md +364 -0
  321. package/skills/ai-research/12-inference-serving/vllm/references/optimization.md +227 -0
  322. package/skills/ai-research/12-inference-serving/vllm/references/quantization.md +285 -0
  323. package/skills/ai-research/12-inference-serving/vllm/references/server-deployment.md +256 -0
  324. package/skills/ai-research/12-inference-serving/vllm/references/troubleshooting.md +448 -0
  325. package/skills/ai-research/13-mlops/mlflow/SKILL.md +704 -0
  326. package/skills/ai-research/13-mlops/mlflow/references/deployment.md +745 -0
  327. package/skills/ai-research/13-mlops/mlflow/references/model-registry.md +771 -0
  328. package/skills/ai-research/13-mlops/mlflow/references/tracking.md +681 -0
  329. package/skills/ai-research/13-mlops/swanlab/SKILL.md +406 -0
  330. package/skills/ai-research/13-mlops/swanlab/references/integrations.md +305 -0
  331. package/skills/ai-research/13-mlops/swanlab/references/visualization.md +234 -0
  332. package/skills/ai-research/13-mlops/tensorboard/SKILL.md +629 -0
  333. package/skills/ai-research/13-mlops/tensorboard/references/integrations.md +639 -0
  334. package/skills/ai-research/13-mlops/tensorboard/references/profiling.md +546 -0
  335. package/skills/ai-research/13-mlops/tensorboard/references/visualization.md +621 -0
  336. package/skills/ai-research/13-mlops/weights-and-biases/SKILL.md +590 -0
  337. package/skills/ai-research/13-mlops/weights-and-biases/references/artifacts.md +585 -0
  338. package/skills/ai-research/13-mlops/weights-and-biases/references/integrations.md +701 -0
  339. package/skills/ai-research/13-mlops/weights-and-biases/references/sweeps.md +848 -0
  340. package/skills/ai-research/14-agents/a-evolve/SKILL.md +383 -0
  341. package/skills/ai-research/14-agents/a-evolve/references/README.md +831 -0
  342. package/skills/ai-research/14-agents/a-evolve/references/api.md +594 -0
  343. package/skills/ai-research/14-agents/a-evolve/references/architecture.md +417 -0
  344. package/skills/ai-research/14-agents/a-evolve/references/design-patterns.md +462 -0
  345. package/skills/ai-research/14-agents/a-evolve/references/examples.md +352 -0
  346. package/skills/ai-research/14-agents/a-evolve/references/issues.md +591 -0
  347. package/skills/ai-research/14-agents/a-evolve/references/releases.md +112 -0
  348. package/skills/ai-research/14-agents/a-evolve/references/tutorials.md +819 -0
  349. package/skills/ai-research/14-agents/autogpt/SKILL.md +403 -0
  350. package/skills/ai-research/14-agents/autogpt/references/advanced-usage.md +536 -0
  351. package/skills/ai-research/14-agents/autogpt/references/troubleshooting.md +421 -0
  352. package/skills/ai-research/14-agents/crewai/SKILL.md +498 -0
  353. package/skills/ai-research/14-agents/crewai/references/flows.md +439 -0
  354. package/skills/ai-research/14-agents/crewai/references/tools.md +430 -0
  355. package/skills/ai-research/14-agents/crewai/references/troubleshooting.md +481 -0
  356. package/skills/ai-research/14-agents/langchain/SKILL.md +480 -0
  357. package/skills/ai-research/14-agents/langchain/references/agents.md +500 -0
  358. package/skills/ai-research/14-agents/langchain/references/integration.md +563 -0
  359. package/skills/ai-research/14-agents/langchain/references/rag.md +601 -0
  360. package/skills/ai-research/14-agents/llamaindex/SKILL.md +569 -0
  361. package/skills/ai-research/14-agents/llamaindex/references/agents.md +84 -0
  362. package/skills/ai-research/14-agents/llamaindex/references/data_connectors.md +109 -0
  363. package/skills/ai-research/14-agents/llamaindex/references/query_engines.md +407 -0
  364. package/skills/ai-research/15-rag/chroma/SKILL.md +406 -0
  365. package/skills/ai-research/15-rag/chroma/references/integration.md +39 -0
  366. package/skills/ai-research/15-rag/faiss/SKILL.md +221 -0
  367. package/skills/ai-research/15-rag/faiss/references/index_types.md +281 -0
  368. package/skills/ai-research/15-rag/pinecone/SKILL.md +358 -0
  369. package/skills/ai-research/15-rag/pinecone/references/deployment.md +182 -0
  370. package/skills/ai-research/15-rag/qdrant/SKILL.md +493 -0
  371. package/skills/ai-research/15-rag/qdrant/references/advanced-usage.md +649 -0
  372. package/skills/ai-research/15-rag/qdrant/references/troubleshooting.md +632 -0
  373. package/skills/ai-research/15-rag/sentence-transformers/SKILL.md +255 -0
  374. package/skills/ai-research/15-rag/sentence-transformers/references/models.md +124 -0
  375. package/skills/ai-research/16-prompt-engineering/dspy/SKILL.md +590 -0
  376. package/skills/ai-research/16-prompt-engineering/dspy/references/examples.md +664 -0
  377. package/skills/ai-research/16-prompt-engineering/dspy/references/modules.md +476 -0
  378. package/skills/ai-research/16-prompt-engineering/dspy/references/optimizers.md +567 -0
  379. package/skills/ai-research/16-prompt-engineering/guidance/SKILL.md +572 -0
  380. package/skills/ai-research/16-prompt-engineering/guidance/references/backends.md +555 -0
  381. package/skills/ai-research/16-prompt-engineering/guidance/references/constraints.md +675 -0
  382. package/skills/ai-research/16-prompt-engineering/guidance/references/examples.md +768 -0
  383. package/skills/ai-research/16-prompt-engineering/instructor/SKILL.md +740 -0
  384. package/skills/ai-research/16-prompt-engineering/instructor/references/examples.md +108 -0
  385. package/skills/ai-research/16-prompt-engineering/instructor/references/providers.md +71 -0
  386. package/skills/ai-research/16-prompt-engineering/instructor/references/validation.md +607 -0
  387. package/skills/ai-research/16-prompt-engineering/outlines/SKILL.md +652 -0
  388. package/skills/ai-research/16-prompt-engineering/outlines/references/backends.md +616 -0
  389. package/skills/ai-research/16-prompt-engineering/outlines/references/examples.md +774 -0
  390. package/skills/ai-research/16-prompt-engineering/outlines/references/json_generation.md +653 -0
  391. package/skills/ai-research/17-observability/langsmith/SKILL.md +422 -0
  392. package/skills/ai-research/17-observability/langsmith/references/advanced-usage.md +549 -0
  393. package/skills/ai-research/17-observability/langsmith/references/troubleshooting.md +538 -0
  394. package/skills/ai-research/17-observability/phoenix/SKILL.md +475 -0
  395. package/skills/ai-research/17-observability/phoenix/references/advanced-usage.md +620 -0
  396. package/skills/ai-research/17-observability/phoenix/references/troubleshooting.md +539 -0
  397. package/skills/ai-research/18-multimodal/audiocraft/SKILL.md +564 -0
  398. package/skills/ai-research/18-multimodal/audiocraft/references/advanced-usage.md +667 -0
  399. package/skills/ai-research/18-multimodal/audiocraft/references/troubleshooting.md +505 -0
  400. package/skills/ai-research/18-multimodal/blip-2/SKILL.md +564 -0
  401. package/skills/ai-research/18-multimodal/blip-2/references/advanced-usage.md +681 -0
  402. package/skills/ai-research/18-multimodal/blip-2/references/troubleshooting.md +527 -0
  403. package/skills/ai-research/18-multimodal/clip/SKILL.md +253 -0
  404. package/skills/ai-research/18-multimodal/clip/references/applications.md +208 -0
  405. package/skills/ai-research/18-multimodal/cosmos-policy/SKILL.md +402 -0
  406. package/skills/ai-research/18-multimodal/cosmos-policy/references/libero-commands.md +175 -0
  407. package/skills/ai-research/18-multimodal/cosmos-policy/references/robocasa-commands.md +147 -0
  408. package/skills/ai-research/18-multimodal/llava/SKILL.md +304 -0
  409. package/skills/ai-research/18-multimodal/llava/references/training.md +198 -0
  410. package/skills/ai-research/18-multimodal/openpi/SKILL.md +480 -0
  411. package/skills/ai-research/18-multimodal/openpi/references/checkpoints-and-env-map.md +86 -0
  412. package/skills/ai-research/18-multimodal/openpi/references/config-recipes.md +50 -0
  413. package/skills/ai-research/18-multimodal/openpi/references/pytorch-gotchas.md +49 -0
  414. package/skills/ai-research/18-multimodal/openpi/references/remote-client-pattern.md +48 -0
  415. package/skills/ai-research/18-multimodal/openpi/references/training-debugging.md +46 -0
  416. package/skills/ai-research/18-multimodal/openvla-oft/SKILL.md +441 -0
  417. package/skills/ai-research/18-multimodal/openvla-oft/references/aloha-workflow.md +141 -0
  418. package/skills/ai-research/18-multimodal/openvla-oft/references/config-troubleshooting.md +97 -0
  419. package/skills/ai-research/18-multimodal/openvla-oft/references/libero-workflow.md +115 -0
  420. package/skills/ai-research/18-multimodal/openvla-oft/references/paper-and-checkpoints.md +84 -0
  421. package/skills/ai-research/18-multimodal/segment-anything/SKILL.md +500 -0
  422. package/skills/ai-research/18-multimodal/segment-anything/references/advanced-usage.md +590 -0
  423. package/skills/ai-research/18-multimodal/segment-anything/references/troubleshooting.md +485 -0
  424. package/skills/ai-research/18-multimodal/stable-diffusion/SKILL.md +519 -0
  425. package/skills/ai-research/18-multimodal/stable-diffusion/references/advanced-usage.md +717 -0
  426. package/skills/ai-research/18-multimodal/stable-diffusion/references/troubleshooting.md +556 -0
  427. package/skills/ai-research/18-multimodal/whisper/SKILL.md +317 -0
  428. package/skills/ai-research/18-multimodal/whisper/references/languages.md +190 -0
  429. package/skills/ai-research/19-emerging-techniques/knowledge-distillation/SKILL.md +458 -0
  430. package/skills/ai-research/19-emerging-techniques/knowledge-distillation/references/minillm.md +335 -0
  431. package/skills/ai-research/19-emerging-techniques/long-context/SKILL.md +536 -0
  432. package/skills/ai-research/19-emerging-techniques/long-context/references/extension_methods.md +469 -0
  433. package/skills/ai-research/19-emerging-techniques/long-context/references/fine_tuning.md +612 -0
  434. package/skills/ai-research/19-emerging-techniques/long-context/references/rope.md +403 -0
  435. package/skills/ai-research/19-emerging-techniques/model-merging/SKILL.md +497 -0
  436. package/skills/ai-research/19-emerging-techniques/model-merging/references/coefficient-tuning.md +415 -0
  437. package/skills/ai-research/19-emerging-techniques/model-merging/references/evaluation.md +463 -0
  438. package/skills/ai-research/19-emerging-techniques/model-merging/references/examples.md +429 -0
  439. package/skills/ai-research/19-emerging-techniques/model-merging/references/methods.md +353 -0
  440. package/skills/ai-research/19-emerging-techniques/model-pruning/SKILL.md +495 -0
  441. package/skills/ai-research/19-emerging-techniques/model-pruning/references/wanda.md +348 -0
  442. package/skills/ai-research/19-emerging-techniques/moe-training/SKILL.md +526 -0
  443. package/skills/ai-research/19-emerging-techniques/moe-training/references/architectures.md +433 -0
  444. package/skills/ai-research/19-emerging-techniques/moe-training/references/inference.md +349 -0
  445. package/skills/ai-research/19-emerging-techniques/moe-training/references/training.md +426 -0
  446. package/skills/ai-research/19-emerging-techniques/speculative-decoding/SKILL.md +467 -0
  447. package/skills/ai-research/19-emerging-techniques/speculative-decoding/references/lookahead.md +310 -0
  448. package/skills/ai-research/19-emerging-techniques/speculative-decoding/references/medusa.md +351 -0
  449. package/skills/ai-research/20-ml-paper-writing/academic-plotting/SKILL.md +479 -0
  450. package/skills/ai-research/20-ml-paper-writing/academic-plotting/references/data-visualization.md +509 -0
  451. package/skills/ai-research/20-ml-paper-writing/academic-plotting/references/diagram-generation.md +395 -0
  452. package/skills/ai-research/20-ml-paper-writing/academic-plotting/references/style-guide.md +305 -0
  453. package/skills/ai-research/20-ml-paper-writing/ml-paper-writing/SKILL.md +982 -0
  454. package/skills/ai-research/20-ml-paper-writing/ml-paper-writing/references/checklists.md +348 -0
  455. package/skills/ai-research/20-ml-paper-writing/ml-paper-writing/references/citation-workflow.md +563 -0
  456. package/skills/ai-research/20-ml-paper-writing/ml-paper-writing/references/reviewer-guidelines.md +349 -0
  457. package/skills/ai-research/20-ml-paper-writing/ml-paper-writing/references/sources.md +165 -0
  458. package/skills/ai-research/20-ml-paper-writing/ml-paper-writing/references/writing-guide.md +477 -0
  459. package/skills/ai-research/20-ml-paper-writing/presenting-conference-talks/SKILL.md +298 -0
  460. package/skills/ai-research/20-ml-paper-writing/presenting-conference-talks/references/slide-templates.md +505 -0
  461. package/skills/ai-research/20-ml-paper-writing/systems-paper-writing/SKILL.md +270 -0
  462. package/skills/ai-research/20-ml-paper-writing/systems-paper-writing/references/checklist.md +279 -0
  463. package/skills/ai-research/20-ml-paper-writing/systems-paper-writing/references/reviewer-guidelines.md +116 -0
  464. package/skills/ai-research/20-ml-paper-writing/systems-paper-writing/references/section-blueprints.md +400 -0
  465. package/skills/ai-research/20-ml-paper-writing/systems-paper-writing/references/systems-conferences.md +261 -0
  466. package/skills/ai-research/20-ml-paper-writing/systems-paper-writing/references/writing-patterns.md +231 -0
  467. package/skills/ai-research/21-research-ideation/brainstorming-research-ideas/SKILL.md +384 -0
  468. package/skills/ai-research/21-research-ideation/creative-thinking-for-research/SKILL.md +366 -0
  469. package/skills/ai-research/22-agent-native-research-artifact/compiler/SKILL.md +245 -0
  470. package/skills/ai-research/22-agent-native-research-artifact/compiler/references/ara-schema.md +439 -0
  471. package/skills/ai-research/22-agent-native-research-artifact/compiler/references/exploration-tree-spec.md +125 -0
  472. package/skills/ai-research/22-agent-native-research-artifact/compiler/references/validation-checklist.md +149 -0
  473. package/skills/ai-research/22-agent-native-research-artifact/research-manager/SKILL.md +324 -0
  474. package/skills/ai-research/22-agent-native-research-artifact/research-manager/references/event-taxonomy.md +124 -0
  475. package/skills/ai-research/22-agent-native-research-artifact/research-manager/references/provenance-tags.md +190 -0
  476. package/skills/ai-research/22-agent-native-research-artifact/research-manager/references/session-protocol.md +162 -0
  477. package/skills/ai-research/22-agent-native-research-artifact/rigor-reviewer/SKILL.md +322 -0
  478. package/skills/ai-research/22-agent-native-research-artifact/rigor-reviewer/references/review-dimensions.md +182 -0
  479. package/skills/ai-research/SKILL.md +101 -0
  480. package/skills/ai-research/SOURCE +38 -0
  481. package/skills/ai-research/index/1-frame.md +18 -0
  482. package/skills/ai-research/index/2-data.md +21 -0
  483. package/skills/ai-research/index/3-train.md +48 -0
  484. package/skills/ai-research/index/4-measure.md +25 -0
  485. package/skills/ai-research/index/5-run.md +23 -0
  486. package/skills/ai-research/index/6-write.md +35 -0
  487. package/skills/ai-research/library.json +3456 -0
  488. package/skills/analyze-app/EVALS.md +82 -0
  489. package/skills/analyze-app/SKILL.md +188 -0
  490. package/skills/design-contract/EVALS.md +80 -0
  491. package/skills/design-contract/SKILL.md +171 -0
  492. package/skills/design-library/EVALS.md +85 -0
  493. package/skills/design-library/INDEX.md +59 -0
  494. package/skills/design-library/SKILL.md +58 -0
  495. package/skills/design-library/SOURCE +131 -0
  496. package/skills/design-library/adaptive-interfaces/skills/colour-independence/SKILL.md +90 -0
  497. package/skills/design-library/adaptive-interfaces/skills/flexible-typography/SKILL.md +83 -0
  498. package/skills/design-library/adaptive-interfaces/skills/information-density/SKILL.md +87 -0
  499. package/skills/design-library/adaptive-interfaces/skills/preference-audit/SKILL.md +70 -0
  500. package/skills/design-library/adaptive-interfaces/skills/responsive-accessibility/SKILL.md +86 -0
  501. package/skills/design-library/adaptive-interfaces/skills/responsive-review/SKILL.md +76 -0
  502. package/skills/design-library/adaptive-interfaces/skills/simplified-views/SKILL.md +97 -0
  503. package/skills/design-library/adaptive-interfaces/skills/specify/SKILL.md +63 -0
  504. package/skills/design-library/adaptive-interfaces/skills/user-preference-respect/SKILL.md +100 -0
  505. package/skills/design-library/cognitive-accessibility/skills/adaptive-personalisation/SKILL.md +61 -0
  506. package/skills/design-library/cognitive-accessibility/skills/assess-load/SKILL.md +48 -0
  507. package/skills/design-library/cognitive-accessibility/skills/cognitive-load-assessment/SKILL.md +60 -0
  508. package/skills/design-library/cognitive-accessibility/skills/contextual-help-design/SKILL.md +61 -0
  509. package/skills/design-library/cognitive-accessibility/skills/error-prevention-recovery/SKILL.md +71 -0
  510. package/skills/design-library/cognitive-accessibility/skills/focus-attention-design/SKILL.md +67 -0
  511. package/skills/design-library/cognitive-accessibility/skills/memory-load-reduction/SKILL.md +60 -0
  512. package/skills/design-library/cognitive-accessibility/skills/plain-language-design/SKILL.md +78 -0
  513. package/skills/design-library/cognitive-accessibility/skills/review/SKILL.md +56 -0
  514. package/skills/design-library/cognitive-accessibility/skills/simplify/SKILL.md +39 -0
  515. package/skills/design-library/cognitive-accessibility/skills/wayfinding-navigation/SKILL.md +64 -0
  516. package/skills/design-library/design-research/skills/behavioural-analytics/SKILL.md +33 -0
  517. package/skills/design-library/design-research/skills/qual-quant-triangulation/SKILL.md +33 -0
  518. package/skills/design-library/inclusive-interaction/skills/audit/SKILL.md +50 -0
  519. package/skills/design-library/inclusive-interaction/skills/design-flow/SKILL.md +58 -0
  520. package/skills/design-library/inclusive-interaction/skills/feedback-and-status/SKILL.md +76 -0
  521. package/skills/design-library/inclusive-interaction/skills/gesture-alternatives/SKILL.md +70 -0
  522. package/skills/design-library/inclusive-interaction/skills/keyboard-navigation/SKILL.md +99 -0
  523. package/skills/design-library/inclusive-interaction/skills/keyboard-review/SKILL.md +54 -0
  524. package/skills/design-library/inclusive-interaction/skills/motion-sensitivity/SKILL.md +79 -0
  525. package/skills/design-library/inclusive-interaction/skills/multi-modal-input/SKILL.md +70 -0
  526. package/skills/design-library/inclusive-interaction/skills/touch-target-design/SKILL.md +71 -0
  527. package/skills/design-library/inclusive-interaction/skills/voice-interaction/SKILL.md +68 -0
  528. package/skills/design-library/visual-critique/skills/critique-affordance/SKILL.md +45 -0
  529. package/skills/design-library/visual-critique/skills/critique-brand-consistency/SKILL.md +42 -0
  530. package/skills/design-library/visual-critique/skills/critique-color/SKILL.md +44 -0
  531. package/skills/design-library/visual-critique/skills/critique-composition/SKILL.md +46 -0
  532. package/skills/design-library/visual-critique/skills/critique-information-density/SKILL.md +45 -0
  533. package/skills/design-library/visual-critique/skills/critique-typography/SKILL.md +45 -0
  534. package/skills/design-library/visual-critique/skills/critique-visual-hierarchy/SKILL.md +40 -0
  535. package/skills/feature-audit/EVALS.md +83 -0
  536. package/skills/feature-audit/SKILL.md +326 -0
  537. package/skills/harness/EVALS.md +81 -0
  538. package/skills/harness/SKILL.md +88 -0
  539. package/skills/i-have-adhd/EVALS.md +80 -0
  540. package/skills/i-have-adhd/SKILL.md +183 -0
  541. package/skills/no-ai-slop/EVALS.md +89 -0
  542. package/skills/no-ai-slop/SKILL.md +209 -0
  543. package/skills/no-ai-slop/eval.md +52 -0
  544. package/skills/plan-add/EVALS.md +79 -0
  545. package/skills/plan-add/SKILL.md +179 -0
  546. package/skills/plan-add/render_table.py +72 -0
  547. package/skills/plan-status/EVALS.md +78 -0
  548. package/skills/plan-status/SKILL.md +52 -0
  549. package/skills/plan-sync/EVALS.md +80 -0
  550. package/skills/plan-sync/SKILL.md +69 -0
  551. package/skills/pm-frameworks/SKILL.md +33 -0
  552. package/skills/pm-frameworks/SOURCE +39 -0
  553. package/skills/pm-frameworks/intended-vs-implemented/SKILL.md +42 -0
  554. package/skills/pm-frameworks/opportunity-solution-tree/SKILL.md +64 -0
  555. package/skills/ponytail/EVALS.md +80 -0
  556. package/skills/ponytail/SKILL.md +124 -0
  557. package/skills/product-analysis/EVALS.md +103 -0
  558. package/skills/product-analysis/SKILL.md +361 -0
  559. package/skills/research/EVALS.md +104 -0
  560. package/skills/research/SKILL.md +570 -0
  561. package/skills/rl-env/SKILL.md +53 -0
  562. package/skills/rl-env/SOURCE +41 -0
  563. package/skills/rl-env/generate-nemo-gym-env/SKILL.md +169 -0
  564. package/skills/rl-env/generate-nemo-gym-env/references/architecture.md +114 -0
  565. package/skills/rl-env/generate-openenv-env/SKILL.md +183 -0
  566. package/skills/rl-env/generate-openenv-env/references/architecture.md +82 -0
  567. package/skills/rl-env/generate-ors-env/SKILL.md +209 -0
  568. package/skills/rl-env/generate-ors-env/references/architecture.md +113 -0
  569. package/skills/rl-env/generate-verifiers-env/SKILL.md +188 -0
  570. package/skills/rl-env/generate-verifiers-env/references/architecture.md +119 -0
  571. package/skills/rl-env/rl-env-from-description/SKILL.md +124 -0
  572. package/skills/rl-env/rl-env-from-description/references/interview.md +75 -0
  573. package/skills/rl-env/rl-env-from-description/references/nemo_gym.md +41 -0
  574. package/skills/rl-env/rl-env-from-description/references/openenv.md +35 -0
  575. package/skills/rl-env/rl-env-from-description/references/ors.md +50 -0
  576. package/skills/rl-env/rl-env-from-description/references/verifiers.md +39 -0
  577. package/skills/tezgah-contract/EVALS.md +78 -0
  578. package/skills/tezgah-contract/SKILL.md +792 -0
  579. package/statusline.py +129 -0
  580. package/workflows/graph-impact.js +153 -0
  581. package/workflows/graph-map.js +158 -0
  582. package/workflows/graph-review.js +170 -0
@@ -0,0 +1,320 @@
1
+ #!/usr/bin/env python3
2
+ """The Stop rule's evidence fold as a declared past-time temporal spec (plan 063,
3
+ roadmap R16), run in shadow beside the imperative `_evidence_block`.
4
+
5
+ **What is declared.** `ROW_ATOMS` are the ten row-local predicates the spec reads,
6
+ each computed once per row by the readers `tezgah_integrity` already has.
7
+ `FORMULAS` are seven past-time LTL formulas over them, evaluated at the last row
8
+ of the trace: `("S", a, b)` is "a since b" (b held at some row and a at every row
9
+ after it), `("O", a)` is "once a", plus `not`/`and`/`or`. `ORDER` is the
10
+ decision list: the first class whose condition holds is the verdict, in the
11
+ order the imperative fold returns them.
12
+
13
+ **What is not a formula, stated so the bounds cannot be gamed.**
14
+ - The scope selector is `tezgah_integrity._stop_block`, shared with the
15
+ imperative fold: which rows the fold reads (this turn, the session before this
16
+ turn, the settled-bookkeeping and idle-turn claim fallbacks), the lost-began
17
+ path, and the "evidence tampered" guard (a `ledger_damage` row says the trace
18
+ is not a trace; it is checked before any fold). The spec replaces only the
19
+ fold the selector calls.
20
+ - `SCOPE_ATOMS`: the turn marker `T`, which scopes "partial failure" to the
21
+ newest turn of the rows given (`_partial_state`).
22
+ - The reply atoms - the external-state claim and the selector's work flag - are
23
+ constants over one trace, passed in, never read off a row.
24
+ - `ESCAPES` lists, before any shadow row exists, the predicates that are not
25
+ row-local and count against the "<= 3" bar; `NOT_COUNTED` lists the rest of
26
+ the candidates plan 063 named and why each does not count.
27
+
28
+ **The monitor** (`fold`) is one in-process pass over the rows at Stop: atoms per
29
+ row, then each formula's value from its value at the previous row. Nothing is
30
+ persisted between Stops. `shadow` records its verdict beside the imperative one
31
+ as a `stop_spec` row and never feeds the verdict; `TEZGAH_STOPSPEC_STRICT` turns a
32
+ disagreement into an exception, for the test suite.
33
+ """
34
+ import os
35
+ import sys
36
+
37
+ HERE = os.path.dirname(os.path.abspath(__file__))
38
+ if HERE not in sys.path:
39
+ sys.path.insert(0, HERE)
40
+ import tezgah_integrity as ti # noqa: E402
41
+
42
+ STRICT = "TEZGAH_STOPSPEC_STRICT"
43
+ ROW_KIND = "stop_spec"
44
+
45
+ ROW_ATOMS = (
46
+ "Vany", # a verify-family row: verify, verify_ok, verify_fail (`_last_verify`)
47
+ "Vfail", # a verify_fail row
48
+ "P", # a check whose pass was seen (`passing_check`)
49
+ "C", # a write the freshness fold counts as a change (`_change_row`)
50
+ "U", # a UI source write (`_ui_write`)
51
+ "Sp", # a screen proof: a UI check that passed, a screen read (`_ui_evidence`)
52
+ "Dc", # a component write (`_design_evidence`)
53
+ "Dk", # a `tezgah-design check` that passed
54
+ "X", # a read of an external system's own state (`_external_read_row`)
55
+ "W", # a work row (`WORK_KINDS`)
56
+ )
57
+ SCOPE_ATOMS = ("T",) # the turn marker
58
+
59
+ # `Pb` is P read through escapes E1 and E2 below: the same pass, placed at its
60
+ # check's start and kept only in the newest change's repository. Not an atom of
61
+ # its own - a pass relocated by two declared non-row-local joins.
62
+ FORMULAS = {
63
+ "check failed": ("S", ("not", "Vany"), "Vfail"),
64
+ "partial failure": ("and", ("S", ("not", "T"), "Vfail"),
65
+ ("not", ("S", ("not", "Vany"), "P"))),
66
+ "no ui_ok": ("or",
67
+ ("and", ("O", "U"),
68
+ ("not", ("S", ("not", "U"), ("and", "Sp", ("not", "U"))))),
69
+ ("and", ("O", "Dc"), ("not", ("S", ("not", "Dc"), "Dk")))),
70
+ "fresh": ("S", ("not", "C"), ("and", ("or", "Pb", "Sp", "X"), ("not", "C"))),
71
+ "stale": ("O", "Pb"),
72
+ "worked": ("O", "W"),
73
+ "read": ("O", "X"),
74
+ }
75
+
76
+ # The decision list. `unread` is the external claim with no read (`read` false).
77
+ ORDER = (
78
+ ("check failed", "check failed"),
79
+ ("partial failure", "partial failure"),
80
+ ("no ui_ok", "no ui_ok"),
81
+ ("allow", "fresh and not unread"),
82
+ ("stale evidence", "not fresh and stale"),
83
+ ("no verify_ok", "not fresh and (worked or the selector's work flag)"),
84
+ ("no external read", "unread"),
85
+ )
86
+
87
+ # Pre-registered 2026-10-06, before any shadow row: the non-row-local predicates
88
+ # that count against GO 4 (<= 3).
89
+ ESCAPES = (
90
+ ("E1 began-join", "Pb sits at the newest earlier `began` row of the pass's id "
91
+ "(`_last_pass`): an id join across rows"),
92
+ ("E2 repo-bind", "Pb counts only in the repository of the newest change's "
93
+ "target (`_change_repo`): needs the last C before the fold"),
94
+ ("E3 lost-began", "an unanswered check `began` row against the session's "
95
+ "delivered set (`unanswered`, `_began_fold`), in the selector"),
96
+ )
97
+ NOT_COUNTED = (
98
+ ("session fallbacks", "scope selector (plan 063 part 3): `_settled`, "
99
+ "`_bookkeeping_turn`, `_before_turn`, the idle-turn claim "
100
+ "fallback choose the rows, the formulas judge them"),
101
+ ("reply atoms", "DONE/VERIFIED, NEGATED, the external claim and the shape classes are "
102
+ "constants over one trace, read off the reply, not a row"),
103
+ ("evidence tampered", "a trace-validity guard in the selector, before the fold"),
104
+ )
105
+ # GO 2's live floor: shadow rows needed before the 99% bar is read. At 400 a
106
+ # 99% rate is 4 disagreements, so one more or less moves it by 0.25 pp.
107
+ MIN_LIVE_N = 400
108
+
109
+
110
+ def _nodes(formula, out):
111
+ """Every subformula of `formula`, children before parents, each once."""
112
+ if isinstance(formula, tuple):
113
+ for arg in formula[1:]:
114
+ _nodes(arg, out)
115
+ if formula not in out:
116
+ out.append(formula)
117
+ return out
118
+
119
+
120
+ _OPS = {"not": "not {0}", "O": "{0} or {self}", "S": "{1} or ({0} and {self})"}
121
+
122
+
123
+ def _source(formula):
124
+ """The monitor of one formula as Python source: one assignment per
125
+ subformula, run once over no row (all atoms false) and then once per row.
126
+ A temporal node reads its own variable before reassigning it, which is its
127
+ value at the previous row - the whole state the monitor keeps."""
128
+ nodes = _nodes(formula, [])
129
+ var = {n: "v%d" % k for k, n in enumerate(nodes)}
130
+ atoms = sorted({n for n in nodes if isinstance(n, str)})
131
+
132
+ def body(leaf):
133
+ lines = []
134
+ for n in nodes:
135
+ if isinstance(n, str):
136
+ expr = leaf(n)
137
+ elif n[0] in ("and", "or"):
138
+ expr = "(%s)" % (" %s " % n[0]).join(var[a] for a in n[1:])
139
+ else:
140
+ expr = _OPS[n[0]].format(*(var[a] for a in n[1:]), self=var[n])
141
+ lines.append("%s = %s" % (var[n], expr))
142
+ return lines
143
+
144
+ src = ["def monitor(trace):"]
145
+ src += [" c_%s = trace.col(%r)" % (a, a) for a in atoms]
146
+ src += [" %s = False" % var[n] for n in nodes]
147
+ src += [" " + line for line in body(lambda a: "False")]
148
+ src += [" for i in range(len(trace.rows)):"]
149
+ src += [" " + line for line in body(lambda a: "c_%s[i]" % a)]
150
+ src += [" return %s" % var[nodes[-1]]]
151
+ return "\n".join(src)
152
+
153
+
154
+ def compile_table(formulas=None):
155
+ """Per formula, its monitor: a function of a `Trace`, compiled from the
156
+ table at import (and from a mutant's table by the mutation run)."""
157
+ out = {}
158
+ for name, f in (formulas or FORMULAS).items():
159
+ scope = {}
160
+ exec(compile(_source(f), "<stopspec %s>" % name, "exec"), scope)
161
+ out[name] = scope["monitor"]
162
+ return out
163
+
164
+
165
+ _TABLE = compile_table()
166
+
167
+
168
+ class Trace:
169
+ """The atom columns of one trace, each computed once and only when a formula
170
+ the decision list reaches reads it - the way the imperative fold never reads
171
+ a UI write once the newest check has failed. X is read only when the reply
172
+ makes an external claim, as the imperative fold reads it."""
173
+
174
+ def __init__(self, rows, external):
175
+ self.rows, self.external, self.cols, self._masked = rows, external, {}, {}
176
+
177
+ def masked(self, i):
178
+ if i not in self._masked:
179
+ self._masked[i] = ti.mask(str(self.rows[i].get("detail") or ""))
180
+ return self._masked[i]
181
+
182
+ def col(self, name):
183
+ if name not in self.cols:
184
+ self.cols[name] = (self._pb() if name == "Pb"
185
+ else [self.atom(name, i, r) for i, r in enumerate(self.rows)])
186
+ return self.cols[name]
187
+
188
+ def atom(self, name, i, row):
189
+ kind = str(row.get("kind"))
190
+ if name == "Vany":
191
+ return kind in ("verify", "verify_ok", "verify_fail")
192
+ if name == "Vfail":
193
+ return kind == "verify_fail"
194
+ if name == "P":
195
+ return ti.passing_check(row)
196
+ if name == "C":
197
+ return ti._change_row(row)
198
+ if name == "U":
199
+ # `_ui_write` is None for a row `_change_row` refuses: ask it only of
200
+ # the change rows, so the C test is paid once per row
201
+ return self.col("C")[i] and bool(ti._ui_write(row))
202
+ if name == "Sp":
203
+ return ((self.col("P")[i] and bool(ti.UI_CHECK.search(self.masked(i))))
204
+ or ti._screen_read(row)
205
+ or (bool(ti.UI_TOOL_CMD.search(self.masked(i)))
206
+ and row.get("exit") in (None, 0) and not row.get("fail_class")))
207
+ if name == "Dc":
208
+ return self.col("U")[i] and bool(ti.DESIGN_COMPONENT.search(self.masked(i)))
209
+ if name == "Dk":
210
+ return self.col("P")[i] and bool(ti.DESIGN_CHECK.search(self.masked(i)))
211
+ if name == "X":
212
+ return (self.external is not None
213
+ and kind in ("run", "verify", "verify_ok", "verify_fail")
214
+ and bool(ti.EXTERNAL_READ.search(self.masked(i))))
215
+ if name == "W":
216
+ return kind in ti.WORK_KINDS
217
+ if name == "T":
218
+ return kind == ti.TURN_KIND
219
+ raise KeyError(name)
220
+
221
+ def _pb(self):
222
+ """P through escapes E1 (placed at its check's `began` row) and E2 (kept
223
+ only in the newest change's repository)."""
224
+ out, starts, waiting = [False] * len(self.rows), [], {}
225
+ passing = self.col("P")
226
+ for i, row in enumerate(self.rows):
227
+ digest, kind = row.get("id"), row.get("kind")
228
+ if kind == ti.BEGAN_KIND:
229
+ if digest:
230
+ waiting.setdefault(digest, []).append(i)
231
+ continue
232
+ start = (waiting[digest].pop()
233
+ if kind in ti.OUTCOME_KINDS and waiting.get(digest) else i)
234
+ if passing[i]:
235
+ starts.append((start, row.get("repo")))
236
+ changes = self.col("C")
237
+ last = max((i for i, c in enumerate(changes) if c), default=-1)
238
+ repo = ti._change_repo(self.rows, last)
239
+ for start, where in starts:
240
+ if ti._same_repo(where, repo):
241
+ out[start] = True
242
+ return out
243
+
244
+
245
+ def verdict(rows, worked, external, table=None):
246
+ """The class `ORDER` picks, or None to allow; a formula is evaluated only
247
+ when the list reaches it."""
248
+ table, trace = table or _TABLE, Trace(rows, external)
249
+
250
+ def holds(name):
251
+ return table[name](trace)
252
+
253
+ for cls in ("check failed", "partial failure", "no ui_ok"):
254
+ if holds(cls):
255
+ return cls
256
+ unread = external is not None and not holds("read")
257
+ if holds("fresh"):
258
+ if not unread:
259
+ return None
260
+ elif holds("stale"):
261
+ return "stale evidence"
262
+ elif worked or holds("worked"):
263
+ return "no verify_ok"
264
+ return "no external read" if unread else None
265
+
266
+
267
+ def fold(rows, worked, external, where="this turn", table=None):
268
+ """`_evidence_block`'s signature and contract, the class from the spec. The
269
+ text is the class itself: shadow reads only the class (part 10, the switch,
270
+ would carry the imperative texts over)."""
271
+ cls = verdict(rows, worked, external, table)
272
+ return (cls, cls)
273
+
274
+
275
+ def judge(text, session_id, rows, cwd, shape, table=None):
276
+ """(the spec's verdict class, whether the selector reached the fold) for one
277
+ Stop: the shared selector with the spec as its fold. A verdict the selector
278
+ made alone (a shape class, "evidence tampered", a lost check) is the
279
+ imperative one by construction."""
280
+ reached = []
281
+
282
+ def spec_fold(r, w, e, where="this turn"):
283
+ reached.append(True)
284
+ return fold(r, w, e, where, table)
285
+
286
+ cls = ti._stop_block(text, session_id, rows=rows, cwd=cwd, shape=shape,
287
+ fold=spec_fold)[0]
288
+ return cls, bool(reached)
289
+
290
+
291
+ def check(imperative, text, session_id, rows, cwd, shape):
292
+ """(spec class, agree, fold reached) for one Stop; raises under
293
+ `TEZGAH_STOPSPEC_STRICT` when the two disagree."""
294
+ spec, reached = judge(text, session_id, rows, cwd, shape)
295
+ agree = spec == imperative
296
+ if not agree and os.environ.get(STRICT):
297
+ raise AssertionError("stop spec disagrees: imperative %r, spec %r"
298
+ % (imperative, spec))
299
+ return spec, agree, reached
300
+
301
+
302
+ def shadow(imperative, text, session_id, rows, cwd, shape, key):
303
+ """Record the spec's verdict beside the imperative one as one `stop_spec`
304
+ row per reply per turn: `agree fold: <class>`, `disagree selector: <imp> ->
305
+ <spec>` and so on, where `fold` says the selector reached the fold and
306
+ `selector` says it decided alone (GO 2 reads only the first). Never returns
307
+ a verdict: the caller's is final. A failure of the spec is recorded as
308
+ `error: <type>` and re-raised only under the strict switch."""
309
+ if any(r.get("kind") == ROW_KIND and r.get("id") == key for r in rows):
310
+ return
311
+ try:
312
+ spec, agree, reached = check(imperative, text, session_id, rows, cwd, shape)
313
+ where = "fold" if reached else "selector"
314
+ detail = ("agree %s: %s" % (where, imperative or "ok") if agree else
315
+ "disagree %s: %s -> %s" % (where, imperative or "ok", spec or "ok"))
316
+ except Exception as exc:
317
+ if os.environ.get(STRICT):
318
+ raise
319
+ detail = "error: %s" % type(exc).__name__
320
+ ti.note(session_id, ROW_KIND, detail, id=key)