arscontexta 0.6.0

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 (418) hide show
  1. package/.claude-plugin/marketplace.json +11 -0
  2. package/.claude-plugin/plugin.json +22 -0
  3. package/README.md +683 -0
  4. package/agents/knowledge-guide.md +49 -0
  5. package/bin/cli.mjs +66 -0
  6. package/generators/agents-md.md +240 -0
  7. package/generators/claude-md.md +379 -0
  8. package/generators/features/atomic-notes.md +124 -0
  9. package/generators/features/ethical-guardrails.md +58 -0
  10. package/generators/features/graph-analysis.md +188 -0
  11. package/generators/features/helper-functions.md +92 -0
  12. package/generators/features/maintenance.md +164 -0
  13. package/generators/features/methodology-knowledge.md +70 -0
  14. package/generators/features/mocs.md +144 -0
  15. package/generators/features/multi-domain.md +61 -0
  16. package/generators/features/personality.md +71 -0
  17. package/generators/features/processing-pipeline.md +428 -0
  18. package/generators/features/schema.md +149 -0
  19. package/generators/features/self-evolution.md +229 -0
  20. package/generators/features/self-space.md +78 -0
  21. package/generators/features/semantic-search.md +99 -0
  22. package/generators/features/session-rhythm.md +85 -0
  23. package/generators/features/templates.md +85 -0
  24. package/generators/features/wiki-links.md +88 -0
  25. package/generators/soul-md.md +121 -0
  26. package/hooks/hooks.json +45 -0
  27. package/hooks/scripts/auto-commit.sh +44 -0
  28. package/hooks/scripts/session-capture.sh +35 -0
  29. package/hooks/scripts/session-orient.sh +86 -0
  30. package/hooks/scripts/write-validate.sh +42 -0
  31. package/methodology/AI shifts knowledge systems from externalizing memory to externalizing attention.md +59 -0
  32. package/methodology/BM25 retrieval fails on full-length descriptions because query term dilution reduces match scores.md +39 -0
  33. package/methodology/IBIS framework maps claim-based architecture to structured argumentation.md +58 -0
  34. package/methodology/LLM attention degrades as context fills.md +49 -0
  35. package/methodology/MOC construction forces synthesis that automated generation from metadata cannot replicate.md +49 -0
  36. package/methodology/MOC maintenance investment compounds because orientation savings multiply across every future session.md +41 -0
  37. package/methodology/MOCs are attention management devices not just organizational tools.md +51 -0
  38. package/methodology/PKM failure follows a predictable cycle.md +50 -0
  39. package/methodology/ThreadMode to DocumentMode transformation is the core value creation step.md +52 -0
  40. package/methodology/WIP limits force processing over accumulation.md +53 -0
  41. package/methodology/Zeigarnik effect validates capture-first philosophy because open loops drain attention.md +42 -0
  42. package/methodology/academic research uses structured extraction with cross-source synthesis.md +566 -0
  43. package/methodology/adapt the four-phase processing pipeline to domain-specific throughput needs.md +197 -0
  44. package/methodology/agent notes externalize navigation intuition that search cannot discover and traversal cannot reconstruct.md +48 -0
  45. package/methodology/agent self-memory should be architecturally separate from user knowledge systems.md +48 -0
  46. package/methodology/agent session boundaries create natural automation checkpoints that human-operated systems lack.md +56 -0
  47. package/methodology/agent-cognition.md +107 -0
  48. package/methodology/agents are simultaneously methodology executors and subjects creating a unique trust asymmetry.md +66 -0
  49. package/methodology/aspect-oriented programming solved the same cross-cutting concern problem that hooks solve.md +39 -0
  50. package/methodology/associative ontologies beat hierarchical taxonomies because heterarchy adapts while hierarchy brittles.md +53 -0
  51. package/methodology/attention residue may have a minimum granularity that cannot be subdivided.md +46 -0
  52. package/methodology/auto-commit hooks eliminate prospective memory failures by converting remember-to-act into guaranteed execution.md +47 -0
  53. package/methodology/automated detection is always safe because it only reads state while automated remediation risks content corruption.md +42 -0
  54. package/methodology/automation should be retired when its false positive rate exceeds its true positive rate or it catches zero issues.md +56 -0
  55. package/methodology/backlinks implicitly define notes by revealing usage context.md +35 -0
  56. package/methodology/backward maintenance asks what would be different if written today.md +62 -0
  57. package/methodology/balance onboarding enforcement and questions to prevent premature complexity.md +229 -0
  58. package/methodology/basic level categorization determines optimal MOC granularity.md +51 -0
  59. package/methodology/batching by context similarity reduces switching costs in agent processing.md +43 -0
  60. package/methodology/behavioral anti-patterns matter more than tool selection.md +42 -0
  61. package/methodology/betweenness centrality identifies bridge notes connecting disparate knowledge domains.md +57 -0
  62. package/methodology/blueprints that teach construction outperform downloads that provide pre-built code for platform-dependent modules.md +42 -0
  63. package/methodology/bootstrapping principle enables self-improving systems.md +62 -0
  64. package/methodology/build automatic memory through cognitive offloading and session handoffs.md +285 -0
  65. package/methodology/capture the reaction to content not just the content itself.md +41 -0
  66. package/methodology/claims must be specific enough to be wrong.md +36 -0
  67. package/methodology/closure rituals create clean breaks that prevent attention residue bleed.md +44 -0
  68. package/methodology/cognitive offloading is the architectural foundation for vault design.md +46 -0
  69. package/methodology/cognitive outsourcing risk in agent-operated systems.md +55 -0
  70. package/methodology/coherence maintains consistency despite inconsistent inputs.md +96 -0
  71. package/methodology/coherent architecture emerges from wiki links spreading activation and small-world topology.md +48 -0
  72. package/methodology/community detection algorithms can inform when MOCs should split or merge.md +52 -0
  73. package/methodology/complete navigation requires four complementary types that no single mechanism provides.md +43 -0
  74. package/methodology/complex systems evolve from simple working systems.md +59 -0
  75. package/methodology/composable knowledge architecture builds systems from independent toggleable modules not monolithic templates.md +61 -0
  76. package/methodology/compose multi-domain systems through separate templates and shared graph.md +372 -0
  77. package/methodology/concept-orientation beats source-orientation for cross-domain connections.md +51 -0
  78. package/methodology/confidence thresholds gate automated action between the mechanical and judgment zones.md +50 -0
  79. package/methodology/configuration dimensions interact so choices in one create pressure on others.md +58 -0
  80. package/methodology/configuration paralysis emerges when derivation surfaces too many decisions.md +44 -0
  81. package/methodology/context files function as agent operating systems through self-referential self-extension.md +46 -0
  82. package/methodology/context phrase clarity determines how deep a navigation hierarchy can scale.md +46 -0
  83. package/methodology/continuous small-batch processing eliminates review dread.md +48 -0
  84. package/methodology/controlled disorder engineers serendipity through semantic rather than topical linking.md +51 -0
  85. package/methodology/creative writing uses worldbuilding consistency with character tracking.md +672 -0
  86. package/methodology/cross-links between MOC territories indicate creative leaps and integration depth.md +43 -0
  87. package/methodology/dangling links reveal which notes want to exist.md +62 -0
  88. package/methodology/data exit velocity measures how quickly content escapes vendor lock-in.md +74 -0
  89. package/methodology/decontextualization risk means atomicity may strip meaning that cannot be recovered.md +48 -0
  90. package/methodology/dense interlinked research claims enable derivation while sparse references only enable templating.md +47 -0
  91. package/methodology/dependency resolution through topological sort makes module composition transparent and verifiable.md +56 -0
  92. package/methodology/derivation generates knowledge systems from composable research claims not template customization.md +63 -0
  93. package/methodology/derivation-engine.md +27 -0
  94. package/methodology/derived systems follow a seed-evolve-reseed lifecycle.md +56 -0
  95. package/methodology/description quality for humans diverges from description quality for keyword search.md +73 -0
  96. package/methodology/descriptions are retrieval filters not summaries.md +112 -0
  97. package/methodology/design MOCs as attention management devices with lifecycle governance.md +318 -0
  98. package/methodology/design-dimensions.md +66 -0
  99. package/methodology/digital mutability enables note evolution that physical permanence forbids.md +54 -0
  100. package/methodology/discovery-retrieval.md +48 -0
  101. package/methodology/distinctiveness scoring treats description quality as measurable.md +69 -0
  102. package/methodology/does agent processing recover what fast capture loses.md +43 -0
  103. package/methodology/domain-compositions.md +37 -0
  104. package/methodology/dual-coding with visual elements could enhance agent traversal.md +55 -0
  105. package/methodology/each module must be describable in one sentence under 200 characters or it does too many things.md +45 -0
  106. package/methodology/each new note compounds value by creating traversal paths.md +55 -0
  107. package/methodology/eight configuration dimensions parameterize the space of possible knowledge systems.md +56 -0
  108. package/methodology/elaborative encoding is the quality gate for new notes.md +55 -0
  109. package/methodology/enforce schema with graduated strictness across capture processing and query zones.md +221 -0
  110. package/methodology/enforcing atomicity can create paralysis when ideas resist decomposition.md +43 -0
  111. package/methodology/engineering uses technical decision tracking with architectural memory.md +766 -0
  112. package/methodology/every knowledge domain shares a four-phase processing skeleton that diverges only in the process step.md +53 -0
  113. package/methodology/evolution observations provide actionable signals for system adaptation.md +67 -0
  114. package/methodology/external memory shapes cognition more than base model.md +60 -0
  115. package/methodology/faceted classification treats notes as multi-dimensional objects rather than folder contents.md +65 -0
  116. package/methodology/failure-modes.md +27 -0
  117. package/methodology/false universalism applies same processing logic regardless of domain.md +49 -0
  118. package/methodology/federated wiki pattern enables multi-agent divergence as feature not bug.md +59 -0
  119. package/methodology/flat files break at retrieval scale.md +75 -0
  120. package/methodology/forced engagement produces weak connections.md +48 -0
  121. package/methodology/four abstraction layers separate platform-agnostic from platform-dependent knowledge system features.md +47 -0
  122. package/methodology/fresh context per task preserves quality better than chaining phases.md +44 -0
  123. package/methodology/friction reveals architecture.md +63 -0
  124. package/methodology/friction-driven module adoption prevents configuration debt by adding complexity only at pain points.md +48 -0
  125. package/methodology/gardening cycle implements tend prune fertilize operations.md +41 -0
  126. package/methodology/generation effect gate blocks processing without transformation.md +40 -0
  127. package/methodology/goal-driven memory orchestration enables autonomous domain learning through directed compute allocation.md +41 -0
  128. package/methodology/good descriptions layer heuristic then mechanism then implication.md +57 -0
  129. package/methodology/graph-structure.md +65 -0
  130. package/methodology/guided notes might outperform post-hoc structuring for high-volume capture.md +37 -0
  131. package/methodology/health wellness uses symptom-trigger correlation with multi-dimensional tracking.md +819 -0
  132. package/methodology/hook composition creates emergent methodology from independent single-concern components.md +47 -0
  133. package/methodology/hook enforcement guarantees quality while instruction enforcement merely suggests it.md +51 -0
  134. package/methodology/hook-driven learning loops create self-improving methodology through observation accumulation.md +62 -0
  135. package/methodology/hooks are the agent habit system that replaces the missing basal ganglia.md +40 -0
  136. package/methodology/hooks cannot replace genuine cognitive engagement yet more automation is always tempting.md +87 -0
  137. package/methodology/hooks enable context window efficiency by delegating deterministic checks to external processes.md +47 -0
  138. package/methodology/idempotent maintenance operations are safe to automate because running them twice produces the same result as running them once.md +44 -0
  139. package/methodology/implement condition-based maintenance triggers for derived systems.md +255 -0
  140. package/methodology/implicit dependencies create distributed monoliths that fail silently across configurations.md +58 -0
  141. package/methodology/implicit knowledge emerges from traversal.md +55 -0
  142. package/methodology/incremental formalization happens through repeated touching of old notes.md +60 -0
  143. package/methodology/incremental reading enables cross-source connection finding.md +39 -0
  144. package/methodology/index.md +32 -0
  145. package/methodology/inline links carry richer relationship data than metadata fields.md +91 -0
  146. package/methodology/insight accretion differs from productivity in knowledge systems.md +41 -0
  147. package/methodology/intermediate packets enable assembly over creation.md +52 -0
  148. package/methodology/intermediate representation pattern enables reliable vault operations beyond regex.md +62 -0
  149. package/methodology/justification chains enable forward backward and evolution reasoning about configuration decisions.md +46 -0
  150. package/methodology/knowledge system architecture is parameterized by platform capabilities not fixed by methodology.md +51 -0
  151. package/methodology/knowledge systems become communication partners through complexity and memory humans cannot sustain.md +47 -0
  152. package/methodology/knowledge systems share universal operations and structural components across all methodology traditions.md +46 -0
  153. package/methodology/legal case management uses precedent chains with regulatory change propagation.md +892 -0
  154. package/methodology/live index via periodic regeneration keeps discovery current.md +58 -0
  155. package/methodology/local-first file formats are inherently agent-native.md +69 -0
  156. package/methodology/logic column pattern separates reasoning from procedure.md +35 -0
  157. package/methodology/maintenance operations are more universal than creative pipelines because structural health is domain-invariant.md +47 -0
  158. package/methodology/maintenance scheduling frequency should match consequence speed not detection capability.md +50 -0
  159. package/methodology/maintenance targeting should prioritize mechanism and theory notes.md +26 -0
  160. package/methodology/maintenance-patterns.md +72 -0
  161. package/methodology/markdown plus YAML plus ripgrep implements a queryable graph database without infrastructure.md +55 -0
  162. package/methodology/maturity field enables agent context prioritization.md +33 -0
  163. package/methodology/memory-architecture.md +27 -0
  164. package/methodology/metacognitive confidence can diverge from retrieval capability.md +42 -0
  165. package/methodology/metadata reduces entropy enabling precision over recall.md +91 -0
  166. package/methodology/methodology development should follow the trajectory from documentation to skill to hook as understanding hardens.md +80 -0
  167. package/methodology/methodology traditions are named points in a shared configuration space not competing paradigms.md +64 -0
  168. package/methodology/mnemonic medium embeds verification into navigation.md +46 -0
  169. package/methodology/module communication through shared YAML fields creates loose coupling without direct dependencies.md +44 -0
  170. package/methodology/module deactivation must account for structural artifacts that survive the toggle.md +49 -0
  171. package/methodology/multi-domain systems compose through separate templates and shared graph.md +61 -0
  172. package/methodology/multi-domain-composition.md +27 -0
  173. package/methodology/narrow folksonomy optimizes for single-operator retrieval unlike broad consensus tagging.md +53 -0
  174. package/methodology/navigation infrastructure passes through distinct scaling regimes that require qualitative strategy shifts.md +48 -0
  175. package/methodology/navigational vertigo emerges in pure association systems without local hierarchy.md +54 -0
  176. package/methodology/note titles should function as APIs enabling sentence transclusion.md +51 -0
  177. package/methodology/note-design.md +57 -0
  178. package/methodology/notes are skills /342/200/224 curated knowledge injected when relevant.md" +62 -0
  179. package/methodology/notes function as cognitive anchors that stabilize attention during complex tasks.md +41 -0
  180. package/methodology/novel domains derive by mapping knowledge type to closest reference domain then adapting.md +50 -0
  181. package/methodology/nudge theory explains graduated hook enforcement as choice architecture for agents.md +59 -0
  182. package/methodology/observation and tension logs function as dead-letter queues for failed automation.md +51 -0
  183. package/methodology/operational memory and knowledge memory serve different functions in agent architecture.md +48 -0
  184. package/methodology/operational wisdom requires contextual observation.md +52 -0
  185. package/methodology/orchestrated vault creation transforms arscontexta from tool to autonomous knowledge factory.md +40 -0
  186. package/methodology/organic emergence versus active curation creates a fundamental vault governance tension.md +68 -0
  187. package/methodology/orphan notes are seeds not failures.md +38 -0
  188. package/methodology/over-automation corrupts quality when hooks encode judgment rather than verification.md +62 -0
  189. package/methodology/people relationships uses Dunbar-layered graphs with interaction tracking.md +659 -0
  190. package/methodology/personal assistant uses life area management with review automation.md +610 -0
  191. package/methodology/platform adapter translation is semantic not mechanical because hook event meanings differ.md +40 -0
  192. package/methodology/platform capability tiers determine which knowledge system features can be implemented.md +48 -0
  193. package/methodology/platform fragmentation means identical conceptual operations require different implementations across agent environments.md +44 -0
  194. package/methodology/premature complexity is the most common derivation failure mode.md +45 -0
  195. package/methodology/prevent domain-specific failure modes through the vulnerability matrix.md +336 -0
  196. package/methodology/processing effort should follow retrieval demand.md +57 -0
  197. package/methodology/processing-workflows.md +75 -0
  198. package/methodology/product management uses feedback pipelines with experiment tracking.md +789 -0
  199. package/methodology/productivity porn risk in meta-system building.md +30 -0
  200. package/methodology/programmable notes could enable property-triggered workflows.md +64 -0
  201. package/methodology/progressive disclosure means reading right not reading less.md +69 -0
  202. package/methodology/progressive schema validates only what active modules require not the full system schema.md +49 -0
  203. package/methodology/project management uses decision tracking with stakeholder context.md +776 -0
  204. package/methodology/propositional link semantics transform wiki links from associative to reasoned.md +87 -0
  205. package/methodology/prospective memory requires externalization.md +53 -0
  206. package/methodology/provenance tracks where beliefs come from.md +62 -0
  207. package/methodology/queries evolve during search so agents should checkpoint.md +35 -0
  208. package/methodology/question-answer metadata enables inverted search patterns.md +39 -0
  209. package/methodology/random note resurfacing prevents write-only memory.md +33 -0
  210. package/methodology/reconciliation loops that compare desired state to actual state enable drift correction without continuous monitoring.md +59 -0
  211. package/methodology/reflection synthesizes existing notes into new insight.md +100 -0
  212. package/methodology/retrieval utility should drive design over capture completeness.md +69 -0
  213. package/methodology/retrieval verification loop tests description quality at scale.md +81 -0
  214. package/methodology/role field makes graph structure explicit.md +94 -0
  215. package/methodology/scaffolding enables divergence that fine-tuning cannot.md +67 -0
  216. package/methodology/schema enforcement via validation agents enables soft consistency.md +60 -0
  217. package/methodology/schema evolution follows observe-then-formalize not design-then-enforce.md +65 -0
  218. package/methodology/schema field names are the only domain specific element in the universal note pattern.md +46 -0
  219. package/methodology/schema fields should use domain-native vocabulary not abstract terminology.md +47 -0
  220. package/methodology/schema templates reduce cognitive overhead at capture time.md +55 -0
  221. package/methodology/schema validation hooks externalize inhibitory control that degrades under cognitive load.md +48 -0
  222. package/methodology/schema-enforcement.md +27 -0
  223. package/methodology/self-extension requires context files to contain platform operations knowledge not just methodology.md +47 -0
  224. package/methodology/sense-making vs storage does compression lose essential nuance.md +73 -0
  225. package/methodology/session boundary hooks implement cognitive bookends for orientation and reflection.md +60 -0
  226. package/methodology/session handoff creates continuity without persistent memory.md +43 -0
  227. package/methodology/session outputs are packets for future selves.md +43 -0
  228. package/methodology/session transcript mining enables experiential validation that structural tests cannot provide.md +38 -0
  229. package/methodology/skill context budgets constrain knowledge system complexity on agent platforms.md +52 -0
  230. package/methodology/skills encode methodology so manual execution bypasses quality gates.md +50 -0
  231. package/methodology/small-world topology requires hubs and dense local links.md +99 -0
  232. package/methodology/source attribution enables tracing claims to foundations.md +38 -0
  233. package/methodology/spaced repetition scheduling could optimize vault maintenance.md +44 -0
  234. package/methodology/spreading activation models how agents should traverse.md +79 -0
  235. package/methodology/stale navigation actively misleads because agents trust curated maps completely.md +43 -0
  236. package/methodology/stigmergy coordinates agents through environmental traces without direct communication.md +62 -0
  237. package/methodology/storage versus thinking distinction determines which tool patterns apply.md +56 -0
  238. package/methodology/structure enables navigation without reading everything.md +52 -0
  239. package/methodology/structure without processing provides no value.md +56 -0
  240. package/methodology/student learning uses prerequisite graphs with spaced retrieval.md +770 -0
  241. package/methodology/summary coherence tests composability before filing.md +37 -0
  242. package/methodology/tag rot applies to wiki links because titles serve as both identifier and display text.md +50 -0
  243. package/methodology/temporal media must convert to spatial text for agent traversal.md +43 -0
  244. package/methodology/temporal processing priority creates age-based inbox urgency.md +45 -0
  245. package/methodology/temporal separation of capture and processing preserves context freshness.md +39 -0
  246. package/methodology/ten universal primitives form the kernel of every viable agent knowledge system.md +162 -0
  247. package/methodology/testing effect could enable agent knowledge verification.md +38 -0
  248. package/methodology/the AgentSkills standard embodies progressive disclosure at the skill level.md +40 -0
  249. package/methodology/the derivation engine improves recursively as deployed systems generate observations.md +49 -0
  250. package/methodology/the determinism boundary separates hook methodology from skill methodology.md +46 -0
  251. package/methodology/the fix-versus-report decision depends on determinism reversibility and accumulated trust.md +45 -0
  252. package/methodology/the generation effect requires active transformation not just storage.md +57 -0
  253. package/methodology/the no wrong patches guarantee ensures any valid module combination produces a valid system.md +58 -0
  254. package/methodology/the system is the argument.md +46 -0
  255. package/methodology/the vault constitutes identity for agents.md +86 -0
  256. package/methodology/the vault methodology transfers because it encodes cognitive science not domain specifics.md +47 -0
  257. package/methodology/therapy journal uses warm personality with pattern detection for emotional processing.md +584 -0
  258. package/methodology/three capture schools converge through agent-mediated synthesis.md +55 -0
  259. package/methodology/three concurrent maintenance loops operate at different timescales to catch different classes of problems.md +56 -0
  260. package/methodology/throughput matters more than accumulation.md +58 -0
  261. package/methodology/title as claim enables traversal as reasoning.md +50 -0
  262. package/methodology/topological organization beats temporal for knowledge work.md +52 -0
  263. package/methodology/trading uses conviction tracking with thesis-outcome correlation.md +699 -0
  264. package/methodology/trails transform ephemeral navigation into persistent artifacts.md +39 -0
  265. package/methodology/transform universal vocabulary to domain-native language through six levels.md +259 -0
  266. package/methodology/type field enables structured queries without folder hierarchies.md +53 -0
  267. package/methodology/use-case presets dissolve the tension between composability and simplicity.md +44 -0
  268. package/methodology/vault conventions may impose hidden rigidity on thinking.md +44 -0
  269. package/methodology/verbatim risk applies to agents too.md +31 -0
  270. package/methodology/vibe notetaking is the emerging industry consensus for AI-native self-organization.md +56 -0
  271. package/methodology/vivid memories need verification.md +45 -0
  272. package/methodology/vocabulary-transformation.md +27 -0
  273. package/methodology/voice capture is the highest-bandwidth channel for agent-delegated knowledge systems.md +45 -0
  274. package/methodology/wiki links are the digital evolution of analog indexing.md +73 -0
  275. package/methodology/wiki links as social contract transforms agents into stewards of incomplete references.md +52 -0
  276. package/methodology/wiki links create navigation paths that shape retrieval.md +63 -0
  277. package/methodology/wiki links implement GraphRAG without the infrastructure.md +101 -0
  278. package/methodology/writing for audience blocks authentic creation.md +22 -0
  279. package/methodology/you operate a system that takes notes.md +79 -0
  280. package/openclaw/SKILL.md +110 -0
  281. package/package.json +45 -0
  282. package/platforms/README.md +51 -0
  283. package/platforms/claude-code/generator.md +61 -0
  284. package/platforms/claude-code/hooks/README.md +186 -0
  285. package/platforms/claude-code/hooks/auto-commit.sh.template +38 -0
  286. package/platforms/claude-code/hooks/session-capture.sh.template +72 -0
  287. package/platforms/claude-code/hooks/session-orient.sh.template +189 -0
  288. package/platforms/claude-code/hooks/write-validate.sh.template +106 -0
  289. package/platforms/openclaw/generator.md +82 -0
  290. package/platforms/openclaw/hooks/README.md +89 -0
  291. package/platforms/openclaw/hooks/bootstrap.ts.template +224 -0
  292. package/platforms/openclaw/hooks/command-new.ts.template +165 -0
  293. package/platforms/openclaw/hooks/heartbeat.ts.template +214 -0
  294. package/platforms/shared/features/README.md +70 -0
  295. package/platforms/shared/skill-blocks/graph.md +145 -0
  296. package/platforms/shared/skill-blocks/learn.md +119 -0
  297. package/platforms/shared/skill-blocks/next.md +131 -0
  298. package/platforms/shared/skill-blocks/pipeline.md +326 -0
  299. package/platforms/shared/skill-blocks/ralph.md +616 -0
  300. package/platforms/shared/skill-blocks/reduce.md +1142 -0
  301. package/platforms/shared/skill-blocks/refactor.md +129 -0
  302. package/platforms/shared/skill-blocks/reflect.md +780 -0
  303. package/platforms/shared/skill-blocks/remember.md +524 -0
  304. package/platforms/shared/skill-blocks/rethink.md +574 -0
  305. package/platforms/shared/skill-blocks/reweave.md +680 -0
  306. package/platforms/shared/skill-blocks/seed.md +320 -0
  307. package/platforms/shared/skill-blocks/stats.md +145 -0
  308. package/platforms/shared/skill-blocks/tasks.md +171 -0
  309. package/platforms/shared/skill-blocks/validate.md +323 -0
  310. package/platforms/shared/skill-blocks/verify.md +562 -0
  311. package/platforms/shared/templates/README.md +35 -0
  312. package/presets/experimental/categories.yaml +1 -0
  313. package/presets/experimental/preset.yaml +38 -0
  314. package/presets/experimental/starter/README.md +7 -0
  315. package/presets/experimental/vocabulary.yaml +7 -0
  316. package/presets/personal/categories.yaml +7 -0
  317. package/presets/personal/preset.yaml +41 -0
  318. package/presets/personal/starter/goals.md +21 -0
  319. package/presets/personal/starter/index.md +17 -0
  320. package/presets/personal/starter/life-areas.md +21 -0
  321. package/presets/personal/starter/people.md +21 -0
  322. package/presets/personal/vocabulary.yaml +32 -0
  323. package/presets/research/categories.yaml +8 -0
  324. package/presets/research/preset.yaml +41 -0
  325. package/presets/research/starter/index.md +17 -0
  326. package/presets/research/starter/methods.md +21 -0
  327. package/presets/research/starter/open-questions.md +21 -0
  328. package/presets/research/vocabulary.yaml +33 -0
  329. package/reference/AUDIT-REPORT.md +238 -0
  330. package/reference/claim-map.md +172 -0
  331. package/reference/components.md +327 -0
  332. package/reference/conversation-patterns.md +542 -0
  333. package/reference/derivation-validation.md +649 -0
  334. package/reference/dimension-claim-map.md +134 -0
  335. package/reference/evolution-lifecycle.md +297 -0
  336. package/reference/failure-modes.md +235 -0
  337. package/reference/interaction-constraints.md +204 -0
  338. package/reference/kernel.yaml +242 -0
  339. package/reference/methodology.md +283 -0
  340. package/reference/open-questions.md +279 -0
  341. package/reference/personality-layer.md +302 -0
  342. package/reference/self-space.md +299 -0
  343. package/reference/semantic-vs-keyword.md +288 -0
  344. package/reference/session-lifecycle.md +298 -0
  345. package/reference/templates/base-note.md +16 -0
  346. package/reference/templates/companion-note.md +70 -0
  347. package/reference/templates/creative-note.md +16 -0
  348. package/reference/templates/learning-note.md +16 -0
  349. package/reference/templates/life-note.md +16 -0
  350. package/reference/templates/moc.md +26 -0
  351. package/reference/templates/relationship-note.md +17 -0
  352. package/reference/templates/research-note.md +19 -0
  353. package/reference/templates/session-log.md +24 -0
  354. package/reference/templates/therapy-note.md +16 -0
  355. package/reference/test-fixtures/edge-case-constraints.md +148 -0
  356. package/reference/test-fixtures/multi-domain.md +164 -0
  357. package/reference/test-fixtures/novel-domain-gaming.md +138 -0
  358. package/reference/test-fixtures/research-minimal.md +102 -0
  359. package/reference/test-fixtures/therapy-full.md +155 -0
  360. package/reference/testing-milestones.md +1087 -0
  361. package/reference/three-spaces.md +363 -0
  362. package/reference/tradition-presets.md +203 -0
  363. package/reference/use-case-presets.md +341 -0
  364. package/reference/validate-kernel.sh +432 -0
  365. package/reference/vocabulary-transforms.md +85 -0
  366. package/scripts/sync-thinking.sh +147 -0
  367. package/skill-sources/graph/SKILL.md +567 -0
  368. package/skill-sources/graph/skill.json +17 -0
  369. package/skill-sources/learn/SKILL.md +254 -0
  370. package/skill-sources/learn/skill.json +17 -0
  371. package/skill-sources/next/SKILL.md +407 -0
  372. package/skill-sources/next/skill.json +17 -0
  373. package/skill-sources/pipeline/SKILL.md +314 -0
  374. package/skill-sources/pipeline/skill.json +17 -0
  375. package/skill-sources/ralph/SKILL.md +604 -0
  376. package/skill-sources/ralph/skill.json +17 -0
  377. package/skill-sources/reduce/SKILL.md +1113 -0
  378. package/skill-sources/reduce/skill.json +17 -0
  379. package/skill-sources/refactor/SKILL.md +448 -0
  380. package/skill-sources/refactor/skill.json +17 -0
  381. package/skill-sources/reflect/SKILL.md +747 -0
  382. package/skill-sources/reflect/skill.json +17 -0
  383. package/skill-sources/remember/SKILL.md +534 -0
  384. package/skill-sources/remember/skill.json +17 -0
  385. package/skill-sources/rethink/SKILL.md +658 -0
  386. package/skill-sources/rethink/skill.json +17 -0
  387. package/skill-sources/reweave/SKILL.md +657 -0
  388. package/skill-sources/reweave/skill.json +17 -0
  389. package/skill-sources/seed/SKILL.md +303 -0
  390. package/skill-sources/seed/skill.json +17 -0
  391. package/skill-sources/stats/SKILL.md +371 -0
  392. package/skill-sources/stats/skill.json +17 -0
  393. package/skill-sources/tasks/SKILL.md +402 -0
  394. package/skill-sources/tasks/skill.json +17 -0
  395. package/skill-sources/validate/SKILL.md +310 -0
  396. package/skill-sources/validate/skill.json +17 -0
  397. package/skill-sources/verify/SKILL.md +532 -0
  398. package/skill-sources/verify/skill.json +17 -0
  399. package/skills/add-domain/SKILL.md +441 -0
  400. package/skills/add-domain/skill.json +17 -0
  401. package/skills/architect/SKILL.md +568 -0
  402. package/skills/architect/skill.json +17 -0
  403. package/skills/ask/SKILL.md +388 -0
  404. package/skills/ask/skill.json +17 -0
  405. package/skills/health/SKILL.md +760 -0
  406. package/skills/health/skill.json +17 -0
  407. package/skills/help/SKILL.md +348 -0
  408. package/skills/help/skill.json +17 -0
  409. package/skills/recommend/SKILL.md +553 -0
  410. package/skills/recommend/skill.json +17 -0
  411. package/skills/reseed/SKILL.md +385 -0
  412. package/skills/reseed/skill.json +17 -0
  413. package/skills/setup/SKILL.md +1688 -0
  414. package/skills/setup/skill.json +17 -0
  415. package/skills/tutorial/SKILL.md +496 -0
  416. package/skills/tutorial/skill.json +17 -0
  417. package/skills/upgrade/SKILL.md +395 -0
  418. package/skills/upgrade/skill.json +17 -0
@@ -0,0 +1,310 @@
1
+ ---
2
+ name: validate
3
+ description: Schema validation for notes. Checks against domain-specific templates. Validates required fields, enum values, description quality, and link health. Non-blocking — warns but doesn't prevent capture. Triggers on "/validate", "/validate [note]", "check schema", "validate note", "validate all".
4
+ user-invocable: true
5
+ allowed-tools: Read, Grep, Glob
6
+ context: fork
7
+ model: sonnet
8
+ ---
9
+
10
+ ## Runtime Configuration (Step 0 — before any processing)
11
+
12
+ Read these files to configure domain-specific behavior:
13
+
14
+ 1. **`ops/derivation-manifest.md`** — vocabulary mapping, platform hints
15
+ - Use `vocabulary.notes` for the notes folder name
16
+ - Use `vocabulary.note` / `vocabulary.note_plural` for note type references
17
+ - Use `vocabulary.topic_map` for MOC references
18
+ - Use `vocabulary.templates` for the templates folder path
19
+
20
+ 2. **`ops/config.yaml`** — processing depth
21
+ - `processing.depth`: deep | standard | quick
22
+
23
+ If these files don't exist, use universal defaults.
24
+
25
+ **Processing depth adaptation:**
26
+
27
+ | Depth | Validation Behavior |
28
+ |-------|---------------------|
29
+ | deep | Full schema validation. All checks enabled including composability analysis and cross-reference verification |
30
+ | standard | Full validation — all checks enabled |
31
+ | quick | Basic schema validation only — required fields, YAML validity, enum values |
32
+
33
+ ## EXECUTE NOW
34
+
35
+ **Target: $ARGUMENTS**
36
+
37
+ Parse immediately:
38
+ - If target contains a note name: validate that specific note
39
+ - If target contains `--handoff`: output RALPH HANDOFF block at end
40
+ - If target is "all" or "notes": validate all notes in {DOMAIN:notes}/ directory
41
+ - If target is empty: ask which note to validate
42
+
43
+ **Execute these steps:**
44
+
45
+ ### Step 1: Locate Template
46
+
47
+ Determine which template applies to the target note:
48
+
49
+ 1. Check the note's location — notes in {DOMAIN:notes}/ use the standard note template
50
+ 2. Check the `type` field in frontmatter — specialized types may have dedicated templates
51
+ 3. Look for a templates directory (check `ops/templates/` or domain-specific path from derivation manifest)
52
+ 4. If the template has a `_schema` block, read it — this is the authoritative schema definition
53
+
54
+ If no template is found, use the default schema checks below.
55
+
56
+ ### Step 2: Read Target Note
57
+
58
+ Read the target note's full YAML frontmatter. Parse:
59
+ - All YAML fields and their values
60
+ - The body content (for link scanning)
61
+ - The footer section (for Topics and Relevant Notes)
62
+
63
+ ### Step 3: Run Schema Checks
64
+
65
+ Run ALL validation checks. Each check produces PASS, WARN, or FAIL.
66
+
67
+ **START NOW.**
68
+
69
+ ---
70
+
71
+ ## Schema Checks
72
+
73
+ ### Required Fields (FAIL if missing)
74
+
75
+ | Check | Rule | How to Verify |
76
+ |-------|------|---------------|
77
+ | `description` | Must exist and be non-empty | Check YAML frontmatter for `description:` field with non-empty value |
78
+ | Topics | Must link to at least one {DOMAIN:topic map} | Check for `topics:` in YAML or `Topics:` section in footer. Must contain at least one wiki link |
79
+
80
+ A missing required field is a hard failure. The note cannot pass validation without these.
81
+
82
+ ### Description Quality (WARN if weak)
83
+
84
+ | Check | Rule | How to Verify |
85
+ |-------|------|---------------|
86
+ | Length | Should be ~50-200 characters | Count characters in description value |
87
+ | New information | Must add context beyond the title | Compare description text against filename/title — if semantically equivalent, WARN |
88
+ | No trailing period | Convention: descriptions don't end with periods | Check last character |
89
+ | Single sentence | Should be one coherent statement | Check for sentence-ending punctuation mid-description |
90
+
91
+ **How to check "adds new info":** Read the title (filename without .md). Read the description. If the description merely restates the title using different words, it fails this check. A good description adds one of:
92
+ - **Mechanism** — how or why the claim works
93
+ - **Scope** — what boundaries the claim has
94
+ - **Implication** — what follows from the claim
95
+ - **Context** — where the claim applies
96
+
97
+ **Examples:**
98
+
99
+ Bad (restates title):
100
+ - Title: `vector proximity measures surface overlap not deep connection`
101
+ - Description: "Semantic similarity captures surface-level overlap rather than genuine conceptual relationships"
102
+
103
+ Good (adds mechanism):
104
+ - Title: `vector proximity measures surface overlap not deep connection`
105
+ - Description: "Two notes about the same concept with different vocabulary score high, while genuinely related ideas across domains score low"
106
+
107
+ ### YAML Validity (FAIL if broken)
108
+
109
+ | Check | Rule | How to Verify |
110
+ |-------|------|---------------|
111
+ | Frontmatter delimiters | Must start with `---` on line 1 and close with `---` | Read first line and scan for closing delimiter |
112
+ | Valid YAML | Must parse without errors | Check for common YAML errors: unquoted colons in values, mismatched quotes, bad indentation |
113
+ | No duplicate keys | Each YAML key appears only once | Scan for repeated field names |
114
+ | No unknown fields | Fields not in the template schema | Compare against `_schema.required` and `_schema.optional` if available — unknown fields get WARN |
115
+
116
+ ### Domain-Specific Enum Checks (WARN if invalid)
117
+
118
+ If the note has fields with enumerated values, check them against the template's `_schema.enums` block:
119
+
120
+ | Field | Expected | Severity |
121
+ |-------|----------|----------|
122
+ | `type` | Values from template enum (e.g., claim, methodology, tension, problem, learning) | WARN |
123
+ | `status` | Values from template enum (e.g., preliminary, open, dissolved) | WARN |
124
+ | `classification` | Values from template enum (e.g., open, closed) | WARN |
125
+ | Custom domain fields | Values from template enum | WARN |
126
+
127
+ If a field has a value not in the enum list, report the invalid value and list the valid options.
128
+
129
+ ### Link Health (WARN per broken link)
130
+
131
+ | Check | Rule | How to Verify |
132
+ |-------|------|---------------|
133
+ | Body wiki-links | Each `[[link]]` should point to an existing file | Extract all `[[...]]` patterns from body, check each against file tree |
134
+ | Topics links | {DOMAIN:topic map} referenced in Topics must exist | Verify each topic wiki link resolves |
135
+ | Relevant notes links | Each note in `relevant_notes` must exist | Verify each wiki link in relevant_notes resolves |
136
+ | Backtick exclusion | Wiki links inside backticks are examples, not real links | Skip `[[...]]` patterns inside single or triple backtick blocks |
137
+
138
+ **How to verify link resolution:** For each `[[link text]]`, check if a file named `link text.md` exists anywhere in the vault. Wiki links resolve by filename, not path.
139
+
140
+ ### Relevant Notes Format (WARN if incorrect)
141
+
142
+ | Check | Rule | Severity |
143
+ |-------|------|----------|
144
+ | Format | Array with context: `["[[note]] -- relationship"]` | WARN |
145
+ | Context phrase present | Each entry should include `--` or `—` followed by relationship description | WARN |
146
+ | Relationship type | Standard types: extends, foundation, contradicts, enables, example | INFO |
147
+ | No bare links | `["[[note]]"]` without context is a bare link — useless for navigation | WARN |
148
+
149
+ ### Composability (WARN if fails)
150
+
151
+ | Check | Rule | How to Verify |
152
+ |-------|------|---------------|
153
+ | Title test | Can you complete "This note argues that [title]"? | Read the title as a sentence fragment — does it make a claim? |
154
+ | Specificity | Is the claim specific enough to disagree with? | Could someone reasonably argue the opposite? |
155
+ | Prose fitness | Would `since [[title]]` read naturally in another note? | Check if the title works as an inline wiki link |
156
+
157
+ **Topic labels vs claims:**
158
+ - "knowledge management" — topic label, not a claim, FAILS composability
159
+ - "knowledge management requires curation not accumulation" — claim, PASSES composability
160
+
161
+ ## Batch Mode
162
+
163
+ When validating all notes (target is "all" or "notes"):
164
+
165
+ 1. Discover all .md files in {DOMAIN:notes}/ directory
166
+ 2. Optionally include additional directories (e.g., self/memory/) if they exist
167
+ 3. Run all schema checks on each note
168
+ 4. Produce summary report:
169
+ - Total notes checked
170
+ - PASS / WARN / FAIL counts
171
+ - Top issues grouped by check type
172
+ - Notes needing immediate attention (FAIL items)
173
+ - Pattern analysis: are certain check types failing systematically?
174
+
175
+ **Batch output format:**
176
+
177
+ ```
178
+ ## Validation Summary
179
+
180
+ Checked: N notes
181
+ - PASS: M (X%)
182
+ - WARN: K (Y%)
183
+ - FAIL: J (Z%)
184
+
185
+ ### FAIL Items (immediate attention)
186
+ | Note | Check | Detail |
187
+ |------|-------|--------|
188
+ | [[note]] | description | Missing |
189
+ | [[note]] | topics | No topics footer |
190
+
191
+ ### Top WARN Patterns
192
+ - Description restates title: N notes
193
+ - Missing context phrases in relevant_notes: N notes
194
+ - Enum value not in template: N notes
195
+
196
+ ### Notes Needing Attention
197
+ 1. [[note]] — 2 FAIL, 1 WARN
198
+ 2. [[note]] — 1 FAIL, 3 WARN
199
+ ```
200
+
201
+ ## Output Format (Single Note)
202
+
203
+ ```
204
+ === VALIDATION: [[note title]] ===
205
+
206
+ PASS:
207
+ - description: present, 147 chars, adds mechanism beyond title
208
+ - topics: ["[[topic-name]]"] — exists
209
+ - yaml: well-formed, valid delimiters
210
+ - composability: title works as prose ("This note argues that [title]")
211
+
212
+ WARN:
213
+ - relevant_notes: bare link without context phrase for [[note-x]]
214
+ - type: "observation" not in template enum (valid: claim, methodology, tension, problem, learning)
215
+
216
+ FAIL:
217
+ - (none)
218
+
219
+ Overall: PASS (2 warnings)
220
+ ===
221
+ ```
222
+
223
+ If WARN or FAIL items exist, include:
224
+
225
+ ```
226
+ ### Suggested Fixes
227
+ - **relevant_notes**: Add context phrase — e.g., `["[[note-x]] -- extends this by adding..."]`
228
+ - **type**: Change to valid enum value or propose adding "observation" to template
229
+ ```
230
+
231
+ ## Handoff Mode (--handoff flag)
232
+
233
+ When invoked with `--handoff`, output this structured format at the END:
234
+
235
+ ```
236
+ === RALPH HANDOFF: validate ===
237
+ Target: [[note title]]
238
+
239
+ Work Done:
240
+ - Validated against [template name] schema
241
+ - Checks run: N
242
+ - Status: PASS | WARN | FAIL
243
+
244
+ Findings:
245
+ - PASS: [list]
246
+ - WARN: [list or "none"]
247
+ - FAIL: [list or "none"]
248
+
249
+ Files Modified:
250
+ - [task file path] (Validate section updated, if applicable)
251
+
252
+ Learnings:
253
+ - [Friction]: [description] | NONE
254
+ - [Surprise]: [description] | NONE
255
+ - [Methodology]: [description] | NONE
256
+ - [Process gap]: [description] | NONE
257
+
258
+ Queue Updates:
259
+ - Mark: validate done for this task
260
+ === END HANDOFF ===
261
+ ```
262
+
263
+ ## Task File Update
264
+
265
+ When a task file is in context (pipeline execution), update the `## Validate` section:
266
+
267
+ ```markdown
268
+ ## Validate
269
+ **Validated:** [UTC timestamp]
270
+
271
+ Schema check against [template name]:
272
+ - description: PASS (147 chars, adds mechanism beyond title)
273
+ - topics: PASS (["[[topic-name]]"])
274
+ - yaml: PASS (well-formed)
275
+ - type: not specified (optional)
276
+ - relevant_notes: WARN (bare link for [[note-x]])
277
+ - composability: PASS
278
+
279
+ Overall: PASS (1 warning)
280
+ ```
281
+
282
+ ## Severity Levels
283
+
284
+ | Level | Meaning | Action |
285
+ |-------|---------|--------|
286
+ | PASS | Meets requirement fully | None needed |
287
+ | WARN | Optional issue or soft violation | Consider fixing, not blocking |
288
+ | FAIL | Required field missing or invalid format | Must fix before verification passes |
289
+ | INFO | Informational observation | No action needed |
290
+
291
+ **FAIL blocks pipeline completion.** A note with any FAIL-level issue should NOT be marked done in the queue. It stays at `current_phase: "verify"` (or "validate" if run standalone) for re-validation after fixes.
292
+
293
+ **WARN does not block.** Warnings are quality signals, not gates. A note can proceed through the pipeline with warnings.
294
+
295
+ ## Critical Constraints
296
+
297
+ **never:**
298
+ - block note creation based on validation failures (validation is a quality check, not a gate)
299
+ - auto-fix issues without reporting them first
300
+ - skip checks because the note "looks fine"
301
+ - report PASS without actually running the check
302
+ - ignore `_schema` blocks in templates when they exist
303
+
304
+ **always:**
305
+ - check ALL schema requirements, not a subset
306
+ - report specific field values in FAIL/WARN messages (not just "description is weak")
307
+ - suggest concrete fixes for every WARN and FAIL
308
+ - use template `_schema` as the authoritative source when available
309
+ - fall back to default checks gracefully when no template exists
310
+ - log patterns when running batch validation (recurring issues signal systematic problems)
@@ -0,0 +1,17 @@
1
+ {
2
+ "name": "knowledge-validate",
3
+ "description": "Schema validation for notes. Checks against domain-specific templates. Validates required fields, enum values, description quality, and link health. Non-blocking -- warns but doesn't prevent capture.",
4
+ "version": "0.4.0",
5
+ "author": "arscontexta",
6
+ "tags": ["knowledge-management", "processing", "pipeline"],
7
+ "entry": "SKILL.md",
8
+ "platform_hints": {
9
+ "claude-code": {
10
+ "context": "fork",
11
+ "model": "sonnet"
12
+ },
13
+ "openclaw": {
14
+ "type": "external"
15
+ }
16
+ }
17
+ }