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.
- package/.claude-plugin/marketplace.json +11 -0
- package/.claude-plugin/plugin.json +22 -0
- package/README.md +683 -0
- package/agents/knowledge-guide.md +49 -0
- package/bin/cli.mjs +66 -0
- package/generators/agents-md.md +240 -0
- package/generators/claude-md.md +379 -0
- package/generators/features/atomic-notes.md +124 -0
- package/generators/features/ethical-guardrails.md +58 -0
- package/generators/features/graph-analysis.md +188 -0
- package/generators/features/helper-functions.md +92 -0
- package/generators/features/maintenance.md +164 -0
- package/generators/features/methodology-knowledge.md +70 -0
- package/generators/features/mocs.md +144 -0
- package/generators/features/multi-domain.md +61 -0
- package/generators/features/personality.md +71 -0
- package/generators/features/processing-pipeline.md +428 -0
- package/generators/features/schema.md +149 -0
- package/generators/features/self-evolution.md +229 -0
- package/generators/features/self-space.md +78 -0
- package/generators/features/semantic-search.md +99 -0
- package/generators/features/session-rhythm.md +85 -0
- package/generators/features/templates.md +85 -0
- package/generators/features/wiki-links.md +88 -0
- package/generators/soul-md.md +121 -0
- package/hooks/hooks.json +45 -0
- package/hooks/scripts/auto-commit.sh +44 -0
- package/hooks/scripts/session-capture.sh +35 -0
- package/hooks/scripts/session-orient.sh +86 -0
- package/hooks/scripts/write-validate.sh +42 -0
- package/methodology/AI shifts knowledge systems from externalizing memory to externalizing attention.md +59 -0
- package/methodology/BM25 retrieval fails on full-length descriptions because query term dilution reduces match scores.md +39 -0
- package/methodology/IBIS framework maps claim-based architecture to structured argumentation.md +58 -0
- package/methodology/LLM attention degrades as context fills.md +49 -0
- package/methodology/MOC construction forces synthesis that automated generation from metadata cannot replicate.md +49 -0
- package/methodology/MOC maintenance investment compounds because orientation savings multiply across every future session.md +41 -0
- package/methodology/MOCs are attention management devices not just organizational tools.md +51 -0
- package/methodology/PKM failure follows a predictable cycle.md +50 -0
- package/methodology/ThreadMode to DocumentMode transformation is the core value creation step.md +52 -0
- package/methodology/WIP limits force processing over accumulation.md +53 -0
- package/methodology/Zeigarnik effect validates capture-first philosophy because open loops drain attention.md +42 -0
- package/methodology/academic research uses structured extraction with cross-source synthesis.md +566 -0
- package/methodology/adapt the four-phase processing pipeline to domain-specific throughput needs.md +197 -0
- package/methodology/agent notes externalize navigation intuition that search cannot discover and traversal cannot reconstruct.md +48 -0
- package/methodology/agent self-memory should be architecturally separate from user knowledge systems.md +48 -0
- package/methodology/agent session boundaries create natural automation checkpoints that human-operated systems lack.md +56 -0
- package/methodology/agent-cognition.md +107 -0
- package/methodology/agents are simultaneously methodology executors and subjects creating a unique trust asymmetry.md +66 -0
- package/methodology/aspect-oriented programming solved the same cross-cutting concern problem that hooks solve.md +39 -0
- package/methodology/associative ontologies beat hierarchical taxonomies because heterarchy adapts while hierarchy brittles.md +53 -0
- package/methodology/attention residue may have a minimum granularity that cannot be subdivided.md +46 -0
- package/methodology/auto-commit hooks eliminate prospective memory failures by converting remember-to-act into guaranteed execution.md +47 -0
- package/methodology/automated detection is always safe because it only reads state while automated remediation risks content corruption.md +42 -0
- package/methodology/automation should be retired when its false positive rate exceeds its true positive rate or it catches zero issues.md +56 -0
- package/methodology/backlinks implicitly define notes by revealing usage context.md +35 -0
- package/methodology/backward maintenance asks what would be different if written today.md +62 -0
- package/methodology/balance onboarding enforcement and questions to prevent premature complexity.md +229 -0
- package/methodology/basic level categorization determines optimal MOC granularity.md +51 -0
- package/methodology/batching by context similarity reduces switching costs in agent processing.md +43 -0
- package/methodology/behavioral anti-patterns matter more than tool selection.md +42 -0
- package/methodology/betweenness centrality identifies bridge notes connecting disparate knowledge domains.md +57 -0
- package/methodology/blueprints that teach construction outperform downloads that provide pre-built code for platform-dependent modules.md +42 -0
- package/methodology/bootstrapping principle enables self-improving systems.md +62 -0
- package/methodology/build automatic memory through cognitive offloading and session handoffs.md +285 -0
- package/methodology/capture the reaction to content not just the content itself.md +41 -0
- package/methodology/claims must be specific enough to be wrong.md +36 -0
- package/methodology/closure rituals create clean breaks that prevent attention residue bleed.md +44 -0
- package/methodology/cognitive offloading is the architectural foundation for vault design.md +46 -0
- package/methodology/cognitive outsourcing risk in agent-operated systems.md +55 -0
- package/methodology/coherence maintains consistency despite inconsistent inputs.md +96 -0
- package/methodology/coherent architecture emerges from wiki links spreading activation and small-world topology.md +48 -0
- package/methodology/community detection algorithms can inform when MOCs should split or merge.md +52 -0
- package/methodology/complete navigation requires four complementary types that no single mechanism provides.md +43 -0
- package/methodology/complex systems evolve from simple working systems.md +59 -0
- package/methodology/composable knowledge architecture builds systems from independent toggleable modules not monolithic templates.md +61 -0
- package/methodology/compose multi-domain systems through separate templates and shared graph.md +372 -0
- package/methodology/concept-orientation beats source-orientation for cross-domain connections.md +51 -0
- package/methodology/confidence thresholds gate automated action between the mechanical and judgment zones.md +50 -0
- package/methodology/configuration dimensions interact so choices in one create pressure on others.md +58 -0
- package/methodology/configuration paralysis emerges when derivation surfaces too many decisions.md +44 -0
- package/methodology/context files function as agent operating systems through self-referential self-extension.md +46 -0
- package/methodology/context phrase clarity determines how deep a navigation hierarchy can scale.md +46 -0
- package/methodology/continuous small-batch processing eliminates review dread.md +48 -0
- package/methodology/controlled disorder engineers serendipity through semantic rather than topical linking.md +51 -0
- package/methodology/creative writing uses worldbuilding consistency with character tracking.md +672 -0
- package/methodology/cross-links between MOC territories indicate creative leaps and integration depth.md +43 -0
- package/methodology/dangling links reveal which notes want to exist.md +62 -0
- package/methodology/data exit velocity measures how quickly content escapes vendor lock-in.md +74 -0
- package/methodology/decontextualization risk means atomicity may strip meaning that cannot be recovered.md +48 -0
- package/methodology/dense interlinked research claims enable derivation while sparse references only enable templating.md +47 -0
- package/methodology/dependency resolution through topological sort makes module composition transparent and verifiable.md +56 -0
- package/methodology/derivation generates knowledge systems from composable research claims not template customization.md +63 -0
- package/methodology/derivation-engine.md +27 -0
- package/methodology/derived systems follow a seed-evolve-reseed lifecycle.md +56 -0
- package/methodology/description quality for humans diverges from description quality for keyword search.md +73 -0
- package/methodology/descriptions are retrieval filters not summaries.md +112 -0
- package/methodology/design MOCs as attention management devices with lifecycle governance.md +318 -0
- package/methodology/design-dimensions.md +66 -0
- package/methodology/digital mutability enables note evolution that physical permanence forbids.md +54 -0
- package/methodology/discovery-retrieval.md +48 -0
- package/methodology/distinctiveness scoring treats description quality as measurable.md +69 -0
- package/methodology/does agent processing recover what fast capture loses.md +43 -0
- package/methodology/domain-compositions.md +37 -0
- package/methodology/dual-coding with visual elements could enhance agent traversal.md +55 -0
- package/methodology/each module must be describable in one sentence under 200 characters or it does too many things.md +45 -0
- package/methodology/each new note compounds value by creating traversal paths.md +55 -0
- package/methodology/eight configuration dimensions parameterize the space of possible knowledge systems.md +56 -0
- package/methodology/elaborative encoding is the quality gate for new notes.md +55 -0
- package/methodology/enforce schema with graduated strictness across capture processing and query zones.md +221 -0
- package/methodology/enforcing atomicity can create paralysis when ideas resist decomposition.md +43 -0
- package/methodology/engineering uses technical decision tracking with architectural memory.md +766 -0
- package/methodology/every knowledge domain shares a four-phase processing skeleton that diverges only in the process step.md +53 -0
- package/methodology/evolution observations provide actionable signals for system adaptation.md +67 -0
- package/methodology/external memory shapes cognition more than base model.md +60 -0
- package/methodology/faceted classification treats notes as multi-dimensional objects rather than folder contents.md +65 -0
- package/methodology/failure-modes.md +27 -0
- package/methodology/false universalism applies same processing logic regardless of domain.md +49 -0
- package/methodology/federated wiki pattern enables multi-agent divergence as feature not bug.md +59 -0
- package/methodology/flat files break at retrieval scale.md +75 -0
- package/methodology/forced engagement produces weak connections.md +48 -0
- package/methodology/four abstraction layers separate platform-agnostic from platform-dependent knowledge system features.md +47 -0
- package/methodology/fresh context per task preserves quality better than chaining phases.md +44 -0
- package/methodology/friction reveals architecture.md +63 -0
- package/methodology/friction-driven module adoption prevents configuration debt by adding complexity only at pain points.md +48 -0
- package/methodology/gardening cycle implements tend prune fertilize operations.md +41 -0
- package/methodology/generation effect gate blocks processing without transformation.md +40 -0
- package/methodology/goal-driven memory orchestration enables autonomous domain learning through directed compute allocation.md +41 -0
- package/methodology/good descriptions layer heuristic then mechanism then implication.md +57 -0
- package/methodology/graph-structure.md +65 -0
- package/methodology/guided notes might outperform post-hoc structuring for high-volume capture.md +37 -0
- package/methodology/health wellness uses symptom-trigger correlation with multi-dimensional tracking.md +819 -0
- package/methodology/hook composition creates emergent methodology from independent single-concern components.md +47 -0
- package/methodology/hook enforcement guarantees quality while instruction enforcement merely suggests it.md +51 -0
- package/methodology/hook-driven learning loops create self-improving methodology through observation accumulation.md +62 -0
- package/methodology/hooks are the agent habit system that replaces the missing basal ganglia.md +40 -0
- package/methodology/hooks cannot replace genuine cognitive engagement yet more automation is always tempting.md +87 -0
- package/methodology/hooks enable context window efficiency by delegating deterministic checks to external processes.md +47 -0
- package/methodology/idempotent maintenance operations are safe to automate because running them twice produces the same result as running them once.md +44 -0
- package/methodology/implement condition-based maintenance triggers for derived systems.md +255 -0
- package/methodology/implicit dependencies create distributed monoliths that fail silently across configurations.md +58 -0
- package/methodology/implicit knowledge emerges from traversal.md +55 -0
- package/methodology/incremental formalization happens through repeated touching of old notes.md +60 -0
- package/methodology/incremental reading enables cross-source connection finding.md +39 -0
- package/methodology/index.md +32 -0
- package/methodology/inline links carry richer relationship data than metadata fields.md +91 -0
- package/methodology/insight accretion differs from productivity in knowledge systems.md +41 -0
- package/methodology/intermediate packets enable assembly over creation.md +52 -0
- package/methodology/intermediate representation pattern enables reliable vault operations beyond regex.md +62 -0
- package/methodology/justification chains enable forward backward and evolution reasoning about configuration decisions.md +46 -0
- package/methodology/knowledge system architecture is parameterized by platform capabilities not fixed by methodology.md +51 -0
- package/methodology/knowledge systems become communication partners through complexity and memory humans cannot sustain.md +47 -0
- package/methodology/knowledge systems share universal operations and structural components across all methodology traditions.md +46 -0
- package/methodology/legal case management uses precedent chains with regulatory change propagation.md +892 -0
- package/methodology/live index via periodic regeneration keeps discovery current.md +58 -0
- package/methodology/local-first file formats are inherently agent-native.md +69 -0
- package/methodology/logic column pattern separates reasoning from procedure.md +35 -0
- package/methodology/maintenance operations are more universal than creative pipelines because structural health is domain-invariant.md +47 -0
- package/methodology/maintenance scheduling frequency should match consequence speed not detection capability.md +50 -0
- package/methodology/maintenance targeting should prioritize mechanism and theory notes.md +26 -0
- package/methodology/maintenance-patterns.md +72 -0
- package/methodology/markdown plus YAML plus ripgrep implements a queryable graph database without infrastructure.md +55 -0
- package/methodology/maturity field enables agent context prioritization.md +33 -0
- package/methodology/memory-architecture.md +27 -0
- package/methodology/metacognitive confidence can diverge from retrieval capability.md +42 -0
- package/methodology/metadata reduces entropy enabling precision over recall.md +91 -0
- package/methodology/methodology development should follow the trajectory from documentation to skill to hook as understanding hardens.md +80 -0
- package/methodology/methodology traditions are named points in a shared configuration space not competing paradigms.md +64 -0
- package/methodology/mnemonic medium embeds verification into navigation.md +46 -0
- package/methodology/module communication through shared YAML fields creates loose coupling without direct dependencies.md +44 -0
- package/methodology/module deactivation must account for structural artifacts that survive the toggle.md +49 -0
- package/methodology/multi-domain systems compose through separate templates and shared graph.md +61 -0
- package/methodology/multi-domain-composition.md +27 -0
- package/methodology/narrow folksonomy optimizes for single-operator retrieval unlike broad consensus tagging.md +53 -0
- package/methodology/navigation infrastructure passes through distinct scaling regimes that require qualitative strategy shifts.md +48 -0
- package/methodology/navigational vertigo emerges in pure association systems without local hierarchy.md +54 -0
- package/methodology/note titles should function as APIs enabling sentence transclusion.md +51 -0
- package/methodology/note-design.md +57 -0
- package/methodology/notes are skills /342/200/224 curated knowledge injected when relevant.md" +62 -0
- package/methodology/notes function as cognitive anchors that stabilize attention during complex tasks.md +41 -0
- package/methodology/novel domains derive by mapping knowledge type to closest reference domain then adapting.md +50 -0
- package/methodology/nudge theory explains graduated hook enforcement as choice architecture for agents.md +59 -0
- package/methodology/observation and tension logs function as dead-letter queues for failed automation.md +51 -0
- package/methodology/operational memory and knowledge memory serve different functions in agent architecture.md +48 -0
- package/methodology/operational wisdom requires contextual observation.md +52 -0
- package/methodology/orchestrated vault creation transforms arscontexta from tool to autonomous knowledge factory.md +40 -0
- package/methodology/organic emergence versus active curation creates a fundamental vault governance tension.md +68 -0
- package/methodology/orphan notes are seeds not failures.md +38 -0
- package/methodology/over-automation corrupts quality when hooks encode judgment rather than verification.md +62 -0
- package/methodology/people relationships uses Dunbar-layered graphs with interaction tracking.md +659 -0
- package/methodology/personal assistant uses life area management with review automation.md +610 -0
- package/methodology/platform adapter translation is semantic not mechanical because hook event meanings differ.md +40 -0
- package/methodology/platform capability tiers determine which knowledge system features can be implemented.md +48 -0
- package/methodology/platform fragmentation means identical conceptual operations require different implementations across agent environments.md +44 -0
- package/methodology/premature complexity is the most common derivation failure mode.md +45 -0
- package/methodology/prevent domain-specific failure modes through the vulnerability matrix.md +336 -0
- package/methodology/processing effort should follow retrieval demand.md +57 -0
- package/methodology/processing-workflows.md +75 -0
- package/methodology/product management uses feedback pipelines with experiment tracking.md +789 -0
- package/methodology/productivity porn risk in meta-system building.md +30 -0
- package/methodology/programmable notes could enable property-triggered workflows.md +64 -0
- package/methodology/progressive disclosure means reading right not reading less.md +69 -0
- package/methodology/progressive schema validates only what active modules require not the full system schema.md +49 -0
- package/methodology/project management uses decision tracking with stakeholder context.md +776 -0
- package/methodology/propositional link semantics transform wiki links from associative to reasoned.md +87 -0
- package/methodology/prospective memory requires externalization.md +53 -0
- package/methodology/provenance tracks where beliefs come from.md +62 -0
- package/methodology/queries evolve during search so agents should checkpoint.md +35 -0
- package/methodology/question-answer metadata enables inverted search patterns.md +39 -0
- package/methodology/random note resurfacing prevents write-only memory.md +33 -0
- package/methodology/reconciliation loops that compare desired state to actual state enable drift correction without continuous monitoring.md +59 -0
- package/methodology/reflection synthesizes existing notes into new insight.md +100 -0
- package/methodology/retrieval utility should drive design over capture completeness.md +69 -0
- package/methodology/retrieval verification loop tests description quality at scale.md +81 -0
- package/methodology/role field makes graph structure explicit.md +94 -0
- package/methodology/scaffolding enables divergence that fine-tuning cannot.md +67 -0
- package/methodology/schema enforcement via validation agents enables soft consistency.md +60 -0
- package/methodology/schema evolution follows observe-then-formalize not design-then-enforce.md +65 -0
- package/methodology/schema field names are the only domain specific element in the universal note pattern.md +46 -0
- package/methodology/schema fields should use domain-native vocabulary not abstract terminology.md +47 -0
- package/methodology/schema templates reduce cognitive overhead at capture time.md +55 -0
- package/methodology/schema validation hooks externalize inhibitory control that degrades under cognitive load.md +48 -0
- package/methodology/schema-enforcement.md +27 -0
- package/methodology/self-extension requires context files to contain platform operations knowledge not just methodology.md +47 -0
- package/methodology/sense-making vs storage does compression lose essential nuance.md +73 -0
- package/methodology/session boundary hooks implement cognitive bookends for orientation and reflection.md +60 -0
- package/methodology/session handoff creates continuity without persistent memory.md +43 -0
- package/methodology/session outputs are packets for future selves.md +43 -0
- package/methodology/session transcript mining enables experiential validation that structural tests cannot provide.md +38 -0
- package/methodology/skill context budgets constrain knowledge system complexity on agent platforms.md +52 -0
- package/methodology/skills encode methodology so manual execution bypasses quality gates.md +50 -0
- package/methodology/small-world topology requires hubs and dense local links.md +99 -0
- package/methodology/source attribution enables tracing claims to foundations.md +38 -0
- package/methodology/spaced repetition scheduling could optimize vault maintenance.md +44 -0
- package/methodology/spreading activation models how agents should traverse.md +79 -0
- package/methodology/stale navigation actively misleads because agents trust curated maps completely.md +43 -0
- package/methodology/stigmergy coordinates agents through environmental traces without direct communication.md +62 -0
- package/methodology/storage versus thinking distinction determines which tool patterns apply.md +56 -0
- package/methodology/structure enables navigation without reading everything.md +52 -0
- package/methodology/structure without processing provides no value.md +56 -0
- package/methodology/student learning uses prerequisite graphs with spaced retrieval.md +770 -0
- package/methodology/summary coherence tests composability before filing.md +37 -0
- package/methodology/tag rot applies to wiki links because titles serve as both identifier and display text.md +50 -0
- package/methodology/temporal media must convert to spatial text for agent traversal.md +43 -0
- package/methodology/temporal processing priority creates age-based inbox urgency.md +45 -0
- package/methodology/temporal separation of capture and processing preserves context freshness.md +39 -0
- package/methodology/ten universal primitives form the kernel of every viable agent knowledge system.md +162 -0
- package/methodology/testing effect could enable agent knowledge verification.md +38 -0
- package/methodology/the AgentSkills standard embodies progressive disclosure at the skill level.md +40 -0
- package/methodology/the derivation engine improves recursively as deployed systems generate observations.md +49 -0
- package/methodology/the determinism boundary separates hook methodology from skill methodology.md +46 -0
- package/methodology/the fix-versus-report decision depends on determinism reversibility and accumulated trust.md +45 -0
- package/methodology/the generation effect requires active transformation not just storage.md +57 -0
- package/methodology/the no wrong patches guarantee ensures any valid module combination produces a valid system.md +58 -0
- package/methodology/the system is the argument.md +46 -0
- package/methodology/the vault constitutes identity for agents.md +86 -0
- package/methodology/the vault methodology transfers because it encodes cognitive science not domain specifics.md +47 -0
- package/methodology/therapy journal uses warm personality with pattern detection for emotional processing.md +584 -0
- package/methodology/three capture schools converge through agent-mediated synthesis.md +55 -0
- package/methodology/three concurrent maintenance loops operate at different timescales to catch different classes of problems.md +56 -0
- package/methodology/throughput matters more than accumulation.md +58 -0
- package/methodology/title as claim enables traversal as reasoning.md +50 -0
- package/methodology/topological organization beats temporal for knowledge work.md +52 -0
- package/methodology/trading uses conviction tracking with thesis-outcome correlation.md +699 -0
- package/methodology/trails transform ephemeral navigation into persistent artifacts.md +39 -0
- package/methodology/transform universal vocabulary to domain-native language through six levels.md +259 -0
- package/methodology/type field enables structured queries without folder hierarchies.md +53 -0
- package/methodology/use-case presets dissolve the tension between composability and simplicity.md +44 -0
- package/methodology/vault conventions may impose hidden rigidity on thinking.md +44 -0
- package/methodology/verbatim risk applies to agents too.md +31 -0
- package/methodology/vibe notetaking is the emerging industry consensus for AI-native self-organization.md +56 -0
- package/methodology/vivid memories need verification.md +45 -0
- package/methodology/vocabulary-transformation.md +27 -0
- package/methodology/voice capture is the highest-bandwidth channel for agent-delegated knowledge systems.md +45 -0
- package/methodology/wiki links are the digital evolution of analog indexing.md +73 -0
- package/methodology/wiki links as social contract transforms agents into stewards of incomplete references.md +52 -0
- package/methodology/wiki links create navigation paths that shape retrieval.md +63 -0
- package/methodology/wiki links implement GraphRAG without the infrastructure.md +101 -0
- package/methodology/writing for audience blocks authentic creation.md +22 -0
- package/methodology/you operate a system that takes notes.md +79 -0
- package/openclaw/SKILL.md +110 -0
- package/package.json +45 -0
- package/platforms/README.md +51 -0
- package/platforms/claude-code/generator.md +61 -0
- package/platforms/claude-code/hooks/README.md +186 -0
- package/platforms/claude-code/hooks/auto-commit.sh.template +38 -0
- package/platforms/claude-code/hooks/session-capture.sh.template +72 -0
- package/platforms/claude-code/hooks/session-orient.sh.template +189 -0
- package/platforms/claude-code/hooks/write-validate.sh.template +106 -0
- package/platforms/openclaw/generator.md +82 -0
- package/platforms/openclaw/hooks/README.md +89 -0
- package/platforms/openclaw/hooks/bootstrap.ts.template +224 -0
- package/platforms/openclaw/hooks/command-new.ts.template +165 -0
- package/platforms/openclaw/hooks/heartbeat.ts.template +214 -0
- package/platforms/shared/features/README.md +70 -0
- package/platforms/shared/skill-blocks/graph.md +145 -0
- package/platforms/shared/skill-blocks/learn.md +119 -0
- package/platforms/shared/skill-blocks/next.md +131 -0
- package/platforms/shared/skill-blocks/pipeline.md +326 -0
- package/platforms/shared/skill-blocks/ralph.md +616 -0
- package/platforms/shared/skill-blocks/reduce.md +1142 -0
- package/platforms/shared/skill-blocks/refactor.md +129 -0
- package/platforms/shared/skill-blocks/reflect.md +780 -0
- package/platforms/shared/skill-blocks/remember.md +524 -0
- package/platforms/shared/skill-blocks/rethink.md +574 -0
- package/platforms/shared/skill-blocks/reweave.md +680 -0
- package/platforms/shared/skill-blocks/seed.md +320 -0
- package/platforms/shared/skill-blocks/stats.md +145 -0
- package/platforms/shared/skill-blocks/tasks.md +171 -0
- package/platforms/shared/skill-blocks/validate.md +323 -0
- package/platforms/shared/skill-blocks/verify.md +562 -0
- package/platforms/shared/templates/README.md +35 -0
- package/presets/experimental/categories.yaml +1 -0
- package/presets/experimental/preset.yaml +38 -0
- package/presets/experimental/starter/README.md +7 -0
- package/presets/experimental/vocabulary.yaml +7 -0
- package/presets/personal/categories.yaml +7 -0
- package/presets/personal/preset.yaml +41 -0
- package/presets/personal/starter/goals.md +21 -0
- package/presets/personal/starter/index.md +17 -0
- package/presets/personal/starter/life-areas.md +21 -0
- package/presets/personal/starter/people.md +21 -0
- package/presets/personal/vocabulary.yaml +32 -0
- package/presets/research/categories.yaml +8 -0
- package/presets/research/preset.yaml +41 -0
- package/presets/research/starter/index.md +17 -0
- package/presets/research/starter/methods.md +21 -0
- package/presets/research/starter/open-questions.md +21 -0
- package/presets/research/vocabulary.yaml +33 -0
- package/reference/AUDIT-REPORT.md +238 -0
- package/reference/claim-map.md +172 -0
- package/reference/components.md +327 -0
- package/reference/conversation-patterns.md +542 -0
- package/reference/derivation-validation.md +649 -0
- package/reference/dimension-claim-map.md +134 -0
- package/reference/evolution-lifecycle.md +297 -0
- package/reference/failure-modes.md +235 -0
- package/reference/interaction-constraints.md +204 -0
- package/reference/kernel.yaml +242 -0
- package/reference/methodology.md +283 -0
- package/reference/open-questions.md +279 -0
- package/reference/personality-layer.md +302 -0
- package/reference/self-space.md +299 -0
- package/reference/semantic-vs-keyword.md +288 -0
- package/reference/session-lifecycle.md +298 -0
- package/reference/templates/base-note.md +16 -0
- package/reference/templates/companion-note.md +70 -0
- package/reference/templates/creative-note.md +16 -0
- package/reference/templates/learning-note.md +16 -0
- package/reference/templates/life-note.md +16 -0
- package/reference/templates/moc.md +26 -0
- package/reference/templates/relationship-note.md +17 -0
- package/reference/templates/research-note.md +19 -0
- package/reference/templates/session-log.md +24 -0
- package/reference/templates/therapy-note.md +16 -0
- package/reference/test-fixtures/edge-case-constraints.md +148 -0
- package/reference/test-fixtures/multi-domain.md +164 -0
- package/reference/test-fixtures/novel-domain-gaming.md +138 -0
- package/reference/test-fixtures/research-minimal.md +102 -0
- package/reference/test-fixtures/therapy-full.md +155 -0
- package/reference/testing-milestones.md +1087 -0
- package/reference/three-spaces.md +363 -0
- package/reference/tradition-presets.md +203 -0
- package/reference/use-case-presets.md +341 -0
- package/reference/validate-kernel.sh +432 -0
- package/reference/vocabulary-transforms.md +85 -0
- package/scripts/sync-thinking.sh +147 -0
- package/skill-sources/graph/SKILL.md +567 -0
- package/skill-sources/graph/skill.json +17 -0
- package/skill-sources/learn/SKILL.md +254 -0
- package/skill-sources/learn/skill.json +17 -0
- package/skill-sources/next/SKILL.md +407 -0
- package/skill-sources/next/skill.json +17 -0
- package/skill-sources/pipeline/SKILL.md +314 -0
- package/skill-sources/pipeline/skill.json +17 -0
- package/skill-sources/ralph/SKILL.md +604 -0
- package/skill-sources/ralph/skill.json +17 -0
- package/skill-sources/reduce/SKILL.md +1113 -0
- package/skill-sources/reduce/skill.json +17 -0
- package/skill-sources/refactor/SKILL.md +448 -0
- package/skill-sources/refactor/skill.json +17 -0
- package/skill-sources/reflect/SKILL.md +747 -0
- package/skill-sources/reflect/skill.json +17 -0
- package/skill-sources/remember/SKILL.md +534 -0
- package/skill-sources/remember/skill.json +17 -0
- package/skill-sources/rethink/SKILL.md +658 -0
- package/skill-sources/rethink/skill.json +17 -0
- package/skill-sources/reweave/SKILL.md +657 -0
- package/skill-sources/reweave/skill.json +17 -0
- package/skill-sources/seed/SKILL.md +303 -0
- package/skill-sources/seed/skill.json +17 -0
- package/skill-sources/stats/SKILL.md +371 -0
- package/skill-sources/stats/skill.json +17 -0
- package/skill-sources/tasks/SKILL.md +402 -0
- package/skill-sources/tasks/skill.json +17 -0
- package/skill-sources/validate/SKILL.md +310 -0
- package/skill-sources/validate/skill.json +17 -0
- package/skill-sources/verify/SKILL.md +532 -0
- package/skill-sources/verify/skill.json +17 -0
- package/skills/add-domain/SKILL.md +441 -0
- package/skills/add-domain/skill.json +17 -0
- package/skills/architect/SKILL.md +568 -0
- package/skills/architect/skill.json +17 -0
- package/skills/ask/SKILL.md +388 -0
- package/skills/ask/skill.json +17 -0
- package/skills/health/SKILL.md +760 -0
- package/skills/health/skill.json +17 -0
- package/skills/help/SKILL.md +348 -0
- package/skills/help/skill.json +17 -0
- package/skills/recommend/SKILL.md +553 -0
- package/skills/recommend/skill.json +17 -0
- package/skills/reseed/SKILL.md +385 -0
- package/skills/reseed/skill.json +17 -0
- package/skills/setup/SKILL.md +1688 -0
- package/skills/setup/skill.json +17 -0
- package/skills/tutorial/SKILL.md +496 -0
- package/skills/tutorial/skill.json +17 -0
- package/skills/upgrade/SKILL.md +395 -0
- package/skills/upgrade/skill.json +17 -0
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "knowledge-reduce",
|
|
3
|
+
"description": "Extract atomic insights from raw material. Domain-aware -- detects whether insight is relationship, learning, pattern, preference, decision, etc. Works on inbox items, daily logs, or any raw source.",
|
|
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": "opus"
|
|
12
|
+
},
|
|
13
|
+
"openclaw": {
|
|
14
|
+
"type": "external"
|
|
15
|
+
}
|
|
16
|
+
}
|
|
17
|
+
}
|
|
@@ -0,0 +1,448 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: refactor
|
|
3
|
+
description: Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval. Triggers on "/refactor", "restructure vault".
|
|
4
|
+
version: "1.0"
|
|
5
|
+
generated_from: "arscontexta-v1.6"
|
|
6
|
+
user-invocable: true
|
|
7
|
+
context: fork
|
|
8
|
+
model: opus
|
|
9
|
+
allowed-tools: Read, Write, Edit, Grep, Glob, Bash
|
|
10
|
+
argument-hint: "[dimension|--dry-run] — focus on specific dimension or preview without approval prompt"
|
|
11
|
+
---
|
|
12
|
+
|
|
13
|
+
## Runtime Configuration (Step 0 — before any processing)
|
|
14
|
+
|
|
15
|
+
Read these files to configure domain-specific behavior:
|
|
16
|
+
|
|
17
|
+
1. **`ops/derivation-manifest.md`** — vocabulary mapping, dimension positions, platform hints
|
|
18
|
+
- Use `vocabulary.notes` for the notes folder name
|
|
19
|
+
- Use `vocabulary.note` / `vocabulary.note_plural` for note type references
|
|
20
|
+
- Use `vocabulary.topic_map` / `vocabulary.topic_map_plural` for MOC references
|
|
21
|
+
- Use `vocabulary.inbox` for the inbox folder name
|
|
22
|
+
|
|
23
|
+
2. **`ops/config.yaml`** — current live configuration (the "after" state)
|
|
24
|
+
|
|
25
|
+
3. **`ops/derivation.md`** — original derivation record (the "before" state)
|
|
26
|
+
|
|
27
|
+
If these files don't exist, report error: "Cannot refactor without both ops/config.yaml and ops/derivation.md. These files establish the baseline and current configuration."
|
|
28
|
+
|
|
29
|
+
---
|
|
30
|
+
|
|
31
|
+
## EXECUTE NOW
|
|
32
|
+
|
|
33
|
+
**INVARIANT: /refactor never executes without approval.** The plan is always shown first.
|
|
34
|
+
|
|
35
|
+
**Target: $ARGUMENTS**
|
|
36
|
+
|
|
37
|
+
Parse immediately:
|
|
38
|
+
- If target is empty: detect ALL config changes and plan restructuring
|
|
39
|
+
- If target names a specific dimension (e.g., "granularity", "organization"): focus on that dimension only
|
|
40
|
+
- If target is `--dry-run`: show plan without asking for approval
|
|
41
|
+
|
|
42
|
+
**Execute these phases:**
|
|
43
|
+
|
|
44
|
+
1. Detect changes between config.yaml and derivation.md
|
|
45
|
+
2. Plan restructuring for each changed dimension
|
|
46
|
+
3. Show the plan with affected artifacts and risk assessment
|
|
47
|
+
4. Execute on approval (unless --dry-run)
|
|
48
|
+
5. Validate post-restructuring
|
|
49
|
+
|
|
50
|
+
**START NOW.** Reference below defines the workflow.
|
|
51
|
+
|
|
52
|
+
---
|
|
53
|
+
|
|
54
|
+
## Philosophy
|
|
55
|
+
|
|
56
|
+
**Configuration changes cascade.**
|
|
57
|
+
|
|
58
|
+
Changing a dimension is not just editing a value in config.yaml. Each dimension affects multiple artifacts — skills, templates, context file sections, hooks, MOC structure. Changing organization from "flat" to "hierarchical" means restructuring the notes directory, updating MOC templates, adjusting navigation references in the context file, and regenerating skills that reference folder structure.
|
|
59
|
+
|
|
60
|
+
/refactor makes these cascades visible and manages them. Without it, dimension changes create drift: config says one thing, artifacts say another. With it, every change is planned, approved, and validated.
|
|
61
|
+
|
|
62
|
+
**The relationship to /architect:** /architect RECOMMENDS changes. /refactor IMPLEMENTS them. /architect analyzes health and friction to propose dimension shifts. When those proposals are approved, /refactor ensures every affected artifact is updated consistently.
|
|
63
|
+
|
|
64
|
+
---
|
|
65
|
+
|
|
66
|
+
## Phase 1: Detect Changes
|
|
67
|
+
|
|
68
|
+
Compare each dimension in `ops/config.yaml` against the same dimension in `ops/derivation.md`:
|
|
69
|
+
|
|
70
|
+
**Step 1: Read both files**
|
|
71
|
+
|
|
72
|
+
Read `ops/config.yaml` and `ops/derivation.md` fully. Extract the position for each of the 8 dimensions from both.
|
|
73
|
+
|
|
74
|
+
**Step 2: Build comparison table**
|
|
75
|
+
|
|
76
|
+
| Dimension | Derivation Value | Config Value | Changed? | Drift Type |
|
|
77
|
+
|-----------|-----------------|--------------|----------|------------|
|
|
78
|
+
| granularity | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
79
|
+
| organization | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
80
|
+
| linking | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
81
|
+
| processing | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
82
|
+
| navigation | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
83
|
+
| maintenance | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
84
|
+
| schema | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
85
|
+
| automation | [val] | [val] | [yes/no] | [aligned/misaligned] |
|
|
86
|
+
|
|
87
|
+
**Step 3: Check feature flags**
|
|
88
|
+
|
|
89
|
+
Also compare feature flags between derivation and config:
|
|
90
|
+
|
|
91
|
+
| Feature | Derivation | Config | Changed? |
|
|
92
|
+
|---------|-----------|--------|----------|
|
|
93
|
+
| semantic_search | [on/off] | [on/off] | [yes/no] |
|
|
94
|
+
| processing_pipeline | [on/off] | [on/off] | [yes/no] |
|
|
95
|
+
| self_space | [on/off] | [on/off] | [yes/no] |
|
|
96
|
+
| session_capture | [on/off] | [on/off] | [yes/no] |
|
|
97
|
+
| parallel_workers | [on/off] | [on/off] | [yes/no] |
|
|
98
|
+
|
|
99
|
+
**Step 4: Early exit if no changes**
|
|
100
|
+
|
|
101
|
+
If no changes detected:
|
|
102
|
+
```
|
|
103
|
+
--=={ refactor }==--
|
|
104
|
+
|
|
105
|
+
No configuration drift detected between config.yaml and derivation.md.
|
|
106
|
+
All dimensions and features match the original derivation.
|
|
107
|
+
|
|
108
|
+
If you want to explore changes, run /architect for recommendations
|
|
109
|
+
or edit ops/config.yaml directly, then run /refactor again.
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
---
|
|
113
|
+
|
|
114
|
+
## Phase 2: Plan Restructuring
|
|
115
|
+
|
|
116
|
+
For each changed dimension, determine ALL affected artifacts. This is the cascade analysis.
|
|
117
|
+
|
|
118
|
+
### Dimension-to-Artifact Mapping
|
|
119
|
+
|
|
120
|
+
| Change | Affected Artifacts | What Changes |
|
|
121
|
+
|--------|-------------------|-------------|
|
|
122
|
+
| **Granularity shift** | Note templates, extraction depth in /reduce, processing skills, context file "Note Design" section | Template body length guidance, extraction granularity settings, composability test thresholds |
|
|
123
|
+
| **Organization shift** | Folder structure, MOC hierarchy, context file "Folder Architecture" section, hub MOC | Directory layout, MOC tier count, navigation references |
|
|
124
|
+
| **Linking shift** | Semantic search config, /reflect connection density expectations, context file "Connection Finding" section | Search tool availability, link threshold values, discovery layer instructions |
|
|
125
|
+
| **Processing shift** | /reduce depth settings, /reflect pass count, pipeline skills, context file "Processing Pipeline" section, config.yaml processing.depth | Extraction thoroughness, connection evaluation depth, chaining mode |
|
|
126
|
+
| **Navigation shift** | MOC tier structure, hub MOC, context file "MOC" section, note Topics footers | Number of MOC tiers, hub content, navigation instructions |
|
|
127
|
+
| **Maintenance shift** | /health threshold values, condition-based trigger settings, context file maintenance instructions | Check frequency conditions, stale note thresholds, reweave trigger conditions |
|
|
128
|
+
| **Schema shift** | Templates (_schema blocks), validation rules, /validate skill, query scripts, context file "YAML" section | Required fields, enum values, validation patterns |
|
|
129
|
+
| **Automation shift** | Hooks (session orient, write validation, inbox processing), skill activation, config.yaml automation section | Which hooks are active, automation level references |
|
|
130
|
+
|
|
131
|
+
### Artifact Analysis Format
|
|
132
|
+
|
|
133
|
+
For each affected artifact, specify:
|
|
134
|
+
|
|
135
|
+
```
|
|
136
|
+
Artifact: [file path]
|
|
137
|
+
Section: [specific section within the file, if applicable]
|
|
138
|
+
Current: [what it says now — quote relevant content]
|
|
139
|
+
Proposed: [what it should say after refactoring]
|
|
140
|
+
Risk: [low | medium | high]
|
|
141
|
+
Reversible: [yes | no — with explanation]
|
|
142
|
+
Content impact: [does this affect existing notes? how many?]
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
### Content Impact Assessment
|
|
146
|
+
|
|
147
|
+
Some changes affect only infrastructure (skills, templates, context file). Others affect existing content (notes, MOCs):
|
|
148
|
+
|
|
149
|
+
| Change Type | Content Impact | Action Required |
|
|
150
|
+
|-------------|---------------|----------------|
|
|
151
|
+
| Template field addition | New notes get field, old notes don't | Add field to old notes (schema migration) |
|
|
152
|
+
| Template field removal | Old notes have unused field | Remove field from old notes (optional) |
|
|
153
|
+
| Folder restructure | Notes must move | Move files, update all wiki links |
|
|
154
|
+
| MOC tier change | MOC hierarchy restructured | Merge/split MOCs, update Topics footers |
|
|
155
|
+
| Enum value change | Old notes have invalid values | Update values in affected notes |
|
|
156
|
+
|
|
157
|
+
For content-impacting changes:
|
|
158
|
+
- Count affected notes: `grep -rl '[old value]' {vocabulary.notes}/*.md | wc -l`
|
|
159
|
+
- List specific files that need updating
|
|
160
|
+
- Estimate time for content migration
|
|
161
|
+
|
|
162
|
+
### Interaction Constraint Check
|
|
163
|
+
|
|
164
|
+
Read `${CLAUDE_PLUGIN_ROOT}/reference/interaction-constraints.md` and check:
|
|
165
|
+
|
|
166
|
+
1. **Hard blocks:** Would the new configuration create a combination that WILL fail?
|
|
167
|
+
- Example: atomic granularity + 2-tier navigation at high volume
|
|
168
|
+
- If a hard block is detected: WARN the user and recommend against the change
|
|
169
|
+
|
|
170
|
+
2. **Soft warns:** What friction points does the new configuration create?
|
|
171
|
+
- Example: dense schema + convention-level automation (manual schema enforcement is tedious)
|
|
172
|
+
- If soft warns exist: note them in the plan with compensating mechanisms
|
|
173
|
+
|
|
174
|
+
3. **Cascade effects:** Does changing dimension X create pressure on dimension Y?
|
|
175
|
+
- If cascade detected: include Y in the restructuring plan even if Y did not change in config
|
|
176
|
+
|
|
177
|
+
---
|
|
178
|
+
|
|
179
|
+
## Phase 3: Show Plan
|
|
180
|
+
|
|
181
|
+
Present the complete restructuring plan:
|
|
182
|
+
|
|
183
|
+
```
|
|
184
|
+
--=={ refactor }==--
|
|
185
|
+
|
|
186
|
+
Detected [N] dimension changes:
|
|
187
|
+
|
|
188
|
+
[dimension]: [old] -> [new]
|
|
189
|
+
Affects:
|
|
190
|
+
- [artifact 1]: [specific change]
|
|
191
|
+
- [artifact 2]: [specific change]
|
|
192
|
+
Content impact: [N] existing {vocabulary.note_plural} need [what]
|
|
193
|
+
Risk: [low/medium/high]
|
|
194
|
+
|
|
195
|
+
[dimension]: [old] -> [new]
|
|
196
|
+
Affects:
|
|
197
|
+
- [artifact 1]: [specific change]
|
|
198
|
+
- [artifact 2]: [specific change]
|
|
199
|
+
Content impact: none
|
|
200
|
+
Risk: [low/medium/high]
|
|
201
|
+
|
|
202
|
+
Interaction constraints:
|
|
203
|
+
- [Hard block | Soft warn | Clean]: [description]
|
|
204
|
+
|
|
205
|
+
Unchanged (preserved as-is):
|
|
206
|
+
- [list artifacts not affected by changes]
|
|
207
|
+
|
|
208
|
+
Estimated implementation time: ~[N] minutes
|
|
209
|
+
Validation: Will run kernel validation after restructuring.
|
|
210
|
+
```
|
|
211
|
+
|
|
212
|
+
**If `--dry-run`:** Stop here. Do not ask for approval.
|
|
213
|
+
|
|
214
|
+
**Otherwise:** Ask: "Proceed with restructuring? (yes / no / adjust)"
|
|
215
|
+
|
|
216
|
+
**Handle responses:**
|
|
217
|
+
|
|
218
|
+
| Response | Action |
|
|
219
|
+
|----------|--------|
|
|
220
|
+
| "yes" | Execute Phase 4 |
|
|
221
|
+
| "no" | Exit without changes |
|
|
222
|
+
| "adjust" | Ask what to change, revise plan, re-present |
|
|
223
|
+
|
|
224
|
+
---
|
|
225
|
+
|
|
226
|
+
## Phase 4: Execute on Approval
|
|
227
|
+
|
|
228
|
+
Execute changes in strict order to prevent intermediate inconsistency:
|
|
229
|
+
|
|
230
|
+
### 4a. Archive Current State
|
|
231
|
+
|
|
232
|
+
Before making changes, record the current state for rollback reference:
|
|
233
|
+
|
|
234
|
+
```bash
|
|
235
|
+
# Log what is about to change
|
|
236
|
+
DATE=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
|
|
237
|
+
echo "## $DATE: /refactor — [dimensions changed]" >> ops/changelog.md
|
|
238
|
+
echo "" >> ops/changelog.md
|
|
239
|
+
echo "Changes planned:" >> ops/changelog.md
|
|
240
|
+
echo "[list of changes]" >> ops/changelog.md
|
|
241
|
+
```
|
|
242
|
+
|
|
243
|
+
### 4b. Regenerate Affected Skills
|
|
244
|
+
|
|
245
|
+
For each skill affected by the dimension changes:
|
|
246
|
+
|
|
247
|
+
1. Read the current skill from the generated skills directory
|
|
248
|
+
2. Consult `${CLAUDE_PLUGIN_ROOT}/reference/` for the latest skill generation approach
|
|
249
|
+
3. Apply vocabulary transformation from derivation-manifest
|
|
250
|
+
4. Apply processing depth settings from the new config
|
|
251
|
+
5. Write the regenerated skill
|
|
252
|
+
|
|
253
|
+
**Skills most commonly affected by dimension changes:**
|
|
254
|
+
|
|
255
|
+
| Dimension Change | Skills to Regenerate |
|
|
256
|
+
|-----------------|---------------------|
|
|
257
|
+
| Granularity | /reduce, /verify, /validate |
|
|
258
|
+
| Processing | /reduce, /reflect, /reweave, /verify, /ralph, /pipeline |
|
|
259
|
+
| Linking | /reflect, /reweave |
|
|
260
|
+
| Navigation | /reflect (MOC update logic) |
|
|
261
|
+
| Schema | /validate, /verify |
|
|
262
|
+
| Automation | /ralph, /pipeline (chaining mode) |
|
|
263
|
+
| Maintenance | /health |
|
|
264
|
+
|
|
265
|
+
### 4c. Update Context File
|
|
266
|
+
|
|
267
|
+
Edit only the sections affected by changed dimensions. Do NOT rewrite the entire context file.
|
|
268
|
+
|
|
269
|
+
For each affected section:
|
|
270
|
+
1. Locate the section by heading
|
|
271
|
+
2. Read current content
|
|
272
|
+
3. Generate updated content reflecting new dimension positions
|
|
273
|
+
4. Replace the section using Edit tool
|
|
274
|
+
5. Verify surrounding sections are unchanged
|
|
275
|
+
|
|
276
|
+
### 4d. Update Templates
|
|
277
|
+
|
|
278
|
+
For schema changes:
|
|
279
|
+
1. Read affected templates from ops/templates/ (or templates/)
|
|
280
|
+
2. Update `_schema` blocks with new required fields, enum values, constraints
|
|
281
|
+
3. Write updated templates
|
|
282
|
+
|
|
283
|
+
### 4e. Update Hooks
|
|
284
|
+
|
|
285
|
+
If automation level changed:
|
|
286
|
+
1. Read current hooks from the hooks directory
|
|
287
|
+
2. Update trigger conditions, threshold values, or active/inactive state
|
|
288
|
+
3. Write updated hooks
|
|
289
|
+
|
|
290
|
+
### 4f. Update Derivation Records
|
|
291
|
+
|
|
292
|
+
After all changes are applied:
|
|
293
|
+
|
|
294
|
+
1. Update `ops/derivation.md` with:
|
|
295
|
+
- New dimension positions
|
|
296
|
+
- Rationale for each change
|
|
297
|
+
- Date of change
|
|
298
|
+
- Reference to /architect recommendation (if applicable)
|
|
299
|
+
|
|
300
|
+
2. Update `ops/derivation-manifest.md` to sync machine-readable config
|
|
301
|
+
|
|
302
|
+
3. Update `ops/config.yaml` to confirm it matches derivation (should already match since config triggered the refactor)
|
|
303
|
+
|
|
304
|
+
### 4g. Content Migration (if needed)
|
|
305
|
+
|
|
306
|
+
If Phase 2 identified content-impacting changes:
|
|
307
|
+
|
|
308
|
+
1. **Schema migration:** Add/remove/rename fields across notes
|
|
309
|
+
```bash
|
|
310
|
+
# Example: add a new required field to all notes
|
|
311
|
+
for f in {vocabulary.notes}/*.md; do
|
|
312
|
+
grep -q '^new_field:' "$f" || sed -i '' '/^description:/a\
|
|
313
|
+
new_field: [default value]' "$f"
|
|
314
|
+
done
|
|
315
|
+
```
|
|
316
|
+
|
|
317
|
+
2. **Folder migration:** Move files to new locations
|
|
318
|
+
```bash
|
|
319
|
+
# Use git mv to preserve history
|
|
320
|
+
git mv "old/path/file.md" "new/path/file.md"
|
|
321
|
+
```
|
|
322
|
+
|
|
323
|
+
3. **Link updates:** Update all wiki links affected by renames
|
|
324
|
+
```bash
|
|
325
|
+
# Use rename script if available
|
|
326
|
+
ops/scripts/rename-note.sh "old name" "new name"
|
|
327
|
+
```
|
|
328
|
+
|
|
329
|
+
4. **MOC restructuring:** Merge/split MOCs as needed
|
|
330
|
+
- For splits: create sub-MOCs, move Core Ideas, update parent
|
|
331
|
+
- For merges: combine Core Ideas, remove redundant MOC, update notes' Topics footers
|
|
332
|
+
|
|
333
|
+
---
|
|
334
|
+
|
|
335
|
+
## Phase 5: Validate
|
|
336
|
+
|
|
337
|
+
Run kernel validation to confirm nothing broke:
|
|
338
|
+
|
|
339
|
+
### Validation Checks
|
|
340
|
+
|
|
341
|
+
| Check | How | Pass Criterion |
|
|
342
|
+
|-------|-----|----------------|
|
|
343
|
+
| Wiki link resolution | Scan for all `[[X]]` and verify X.md exists | Zero dangling links |
|
|
344
|
+
| Schema compliance | Check all notes against template _schema blocks | All required fields present, enum values valid |
|
|
345
|
+
| MOC hierarchy | Verify hub links to domain MOCs, domains link to topics | All tiers connected |
|
|
346
|
+
| Session orient | Simulate session start — can the context file be loaded? | No file-not-found errors |
|
|
347
|
+
| Three-space boundaries | Check notes vs ops vs self boundaries | No content in wrong space |
|
|
348
|
+
| Vocabulary consistency | Check that skills and context file use updated vocabulary | No stale universal terms |
|
|
349
|
+
| Skill integrity | Verify regenerated skills have valid frontmatter and structure | All skills parseable |
|
|
350
|
+
|
|
351
|
+
### Validation Report
|
|
352
|
+
|
|
353
|
+
```
|
|
354
|
+
--=={ refactor complete }==--
|
|
355
|
+
|
|
356
|
+
Restructuring applied:
|
|
357
|
+
[dimension]: [old] -> [new] — [N] artifacts updated
|
|
358
|
+
[dimension]: [old] -> [new] — [N] artifacts updated
|
|
359
|
+
|
|
360
|
+
Content migration:
|
|
361
|
+
[N] {vocabulary.note_plural} updated with new schema fields
|
|
362
|
+
[N] wiki links updated
|
|
363
|
+
[N] {vocabulary.topic_map_plural} restructured
|
|
364
|
+
|
|
365
|
+
Kernel validation: [N]/[N] checks PASS
|
|
366
|
+
[Any warnings or issues]
|
|
367
|
+
|
|
368
|
+
Derivation updated: ops/derivation.md
|
|
369
|
+
Changelog updated: ops/changelog.md
|
|
370
|
+
```
|
|
371
|
+
|
|
372
|
+
If any validation checks fail:
|
|
373
|
+
```
|
|
374
|
+
WARNING: [N] validation checks failed:
|
|
375
|
+
- [check name]: [specific failure]
|
|
376
|
+
|
|
377
|
+
Recommended action: [specific fix]
|
|
378
|
+
Rollback guidance: [how to revert if needed]
|
|
379
|
+
```
|
|
380
|
+
|
|
381
|
+
---
|
|
382
|
+
|
|
383
|
+
## Edge Cases
|
|
384
|
+
|
|
385
|
+
### No ops/config.yaml or No ops/derivation.md
|
|
386
|
+
|
|
387
|
+
Cannot refactor without both files. Report error and suggest creating them:
|
|
388
|
+
```
|
|
389
|
+
Cannot run /refactor: [missing file] not found.
|
|
390
|
+
- ops/config.yaml is the live configuration
|
|
391
|
+
- ops/derivation.md is the original design baseline
|
|
392
|
+
Both are required to detect dimension shifts.
|
|
393
|
+
|
|
394
|
+
Run /setup to create a new system, or manually create the missing file.
|
|
395
|
+
```
|
|
396
|
+
|
|
397
|
+
### Single Dimension Focus
|
|
398
|
+
|
|
399
|
+
If $ARGUMENTS names a specific dimension:
|
|
400
|
+
1. Only check that dimension for changes
|
|
401
|
+
2. Still check interaction constraints (other dimensions may be affected by cascade)
|
|
402
|
+
3. Only restructure artifacts affected by that dimension
|
|
403
|
+
|
|
404
|
+
### No Changes Detected
|
|
405
|
+
|
|
406
|
+
Report clean state and exit (see Phase 1 early exit).
|
|
407
|
+
|
|
408
|
+
### Hard Block Detected
|
|
409
|
+
|
|
410
|
+
If an interaction constraint hard block is detected:
|
|
411
|
+
```
|
|
412
|
+
HARD BLOCK: The proposed configuration [dimension X = val, dimension Y = val]
|
|
413
|
+
creates a combination that will fail because [reason from interaction-constraints.md].
|
|
414
|
+
|
|
415
|
+
Recommended: Either change [dimension X] back to [safe value] or also change
|
|
416
|
+
[dimension Y] to [compensating value].
|
|
417
|
+
|
|
418
|
+
Cannot proceed with current configuration. Adjust and re-run /refactor.
|
|
419
|
+
```
|
|
420
|
+
|
|
421
|
+
Do NOT proceed with restructuring when a hard block is active.
|
|
422
|
+
|
|
423
|
+
### Large Content Migration (100+ notes)
|
|
424
|
+
|
|
425
|
+
For large migrations:
|
|
426
|
+
1. Show the count and estimated time
|
|
427
|
+
2. Offer batch processing: "This affects 150 notes. Process all at once or in batches of 50?"
|
|
428
|
+
3. For batch processing, validate after each batch before continuing
|
|
429
|
+
|
|
430
|
+
### Feature Flag Changes
|
|
431
|
+
|
|
432
|
+
Feature flag changes (semantic_search, self_space, etc.) may require:
|
|
433
|
+
- Creating new directories (self/ for self_space on)
|
|
434
|
+
- Installing tools (qmd for semantic_search on)
|
|
435
|
+
- Removing hooks (for automation off)
|
|
436
|
+
|
|
437
|
+
Handle each feature flag change specifically:
|
|
438
|
+
|
|
439
|
+
| Flag | On -> Off | Off -> On |
|
|
440
|
+
|------|-----------|-----------|
|
|
441
|
+
| semantic_search | Remove search references from skills, update context file | Add search config, update skills with search integration |
|
|
442
|
+
| self_space | Archive self/ contents, remove self/ references | Create self/ structure, generate identity files |
|
|
443
|
+
| session_capture | INVARIANT — cannot disable | Already on (invariant) |
|
|
444
|
+
| parallel_workers | Update /ralph to serial-only mode | Verify tmux available, update /ralph for parallel mode |
|
|
445
|
+
|
|
446
|
+
### No ops/derivation-manifest.md
|
|
447
|
+
|
|
448
|
+
Use universal vocabulary. Refactoring still works but vocabulary transformation is skipped.
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "knowledge-refactor",
|
|
3
|
+
"description": "Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval.",
|
|
4
|
+
"version": "0.4.0",
|
|
5
|
+
"author": "arscontexta",
|
|
6
|
+
"tags": ["knowledge-management", "maintenance", "infrastructure"],
|
|
7
|
+
"entry": "SKILL.md",
|
|
8
|
+
"platform_hints": {
|
|
9
|
+
"claude-code": {
|
|
10
|
+
"context": "fork",
|
|
11
|
+
"model": "opus"
|
|
12
|
+
},
|
|
13
|
+
"openclaw": {
|
|
14
|
+
"type": "external"
|
|
15
|
+
}
|
|
16
|
+
}
|
|
17
|
+
}
|