stevehansen
UserLong-term memory for AI coding agents — local-first, privacy-absolute, works everywhere.
Categories
Indexed Skills (12)
canon
Prime on Eidet's Canon before changing it — the propose/review/approve loop over Term (P1) and Domain (P2) pages, CanonDraft in its own canondrafts/* collection, CanonService's damper matrix and claim-before-mint protocol, ICanonMintPort as the sole write edge into canon:* memories, fingerprints, rejection cooldowns, and the canon:* guard that keeps curated pages out of dedup/consolidation. Use when the task touches a Canon draft or page, a draft source, the Web UI Canon panel, or /api/eidet/canon/*. Not for parked open work (see looseends), not for the live Portal view (see portal).
enrichment
Prime on Eidet's optional LLM layer before changing it — EnrichmentService, IEnrichmentPort and its Ollama/OpenAI-compatible/Fallback/Null/InMemory adapters, the primary-plus-fallbacks backend chain, bearer auth and the thinking switch, prompt kinds, the health cache, CoT sanitizing, the store-time EnrichmentWorker subscription, and the generated Summary/OneLiner/ForesightHint/Entities fields plus drift-review and reflection proposals. Use when the task touches enrichment config or reload, an Ollama/LM Studio/vLLM backend or a network model cluster, a prompt, a parser for model output, or "why is Summary null". Not for the stages that schedule these calls (see maintenance), not for the zero-LLM store gates (see writepath).
intake
Prime on Eidet's intake pipeline before changing it — IntakeService's four verbs (whole-repo, docs-folder, git-history, Claude-Code-memory), the IIntakeExtractor/IIntakeSink contract, the per-candidate write gate, content-addressed dedup, the git commit gate and watermark. Use when the task touches an intake extractor, seeding memories from CLAUDE.md/README/manifests, git-history mining, Claude Code memory import, or a skip reason in an intake result. Not for pack import (see sharing), not for the /memories file store (see memorytool), not for turning seeds into insights (see maintenance).
looseends
Prime on Eidet's Loose Ends before changing them — parked open work in its own looseends/* collection, LooseEndService's park/resolve verbs, resolution kinds (Done/Dropped/Promoted/Superseded), the claim-before-promote race protection, IPromotionPort, priority clamping, and the wake-up slice plus recall ride-along. Use when the task touches eidet_park/eidet_resolve, LooseEnd, promotion to a memory or an external issue, or open-work surfacing at session start. Not for memories or forget (see memory), not for pending knowledge awaiting review (see canon).
maintenance
Prime on Eidet's maintenance pipeline before changing it — the MaintenanceOrchestrator stage order, IMaintenanceStage/MaintenanceContext contract, TTL expiry, observation retention, dedup, FadeMem importance decay, ROI decay, budget eviction, deprecation, consolidation, the ACE-style Reflector, drift review, and the nightly forget-integrity audit. Use when the task touches a maintenance stage, ConsolidationEngine, DedupEngine, ReflectionEngine, RecallConsistencyGuard, FadeMemCurve, RetentionScore, or a nightly/scheduled corpus rewrite. Not for the LLM backend those stages call (see enrichment), not for one-off ingestion (see intake), not for the read path (see recall).
memory
Prime on Eidet's Memory core before touching it — the MemoryEntry aggregate, its deterministic id (which doubles as a content commitment), validity intervals, supersession chains, forget/redact/edit verbs, and the Valence and FunctionalStage dimensions. Use when the task touches MemoryEntry, memory ids, MemoryType, Valence, Validity, provenance fields, supersession, version chains, forget, redact, links, or echo/fizzle feedback. Not for the gates that accept or reject a write (see writepath), not for ranking or context packing (see recall), not for scheduled rewrites (see maintenance).
memorytool
Prime on Eidet's memory_20250818 backend before changing it — MemoryToolTranslator's six commands (view/create/str_replace/insert/delete/rename), MemoryPath validation, byte-exact path-keyed blobs in memoryfiles/*, the size cap and SecretPolicy, the reserved /memories/.recall subtree, and the opt-in one-way IMemoryBridge into the semantic store. Use when the task touches Claude memory-tool commands, /memories paths, MemoryFile storage, or POST /api/eidet/memory-tool. Not for semantic memories (see memory), not for seeding from repo files (see intake).
portal
Prime on Eidet's Portal before changing it — the per-repo generated HTML state view behind GET /api/eidet/portal, PortalRenderer's one-fetch section loop, the IPortalSection contract and its five v1 sections (Identity, Architecture, Procedures, Heuristics, Health), PortalMarkup citation anchors and escaping, and the augment=off liveness model. Use when the task touches a Portal section, portal rendering or citations, or the Web UI's portal view. Not for the approve-a-page curation loop (see canon), not for ranked agent-facing retrieval (see recall).
quality
Prime on Eidet's quality and benchmarking surfaces before changing them — QualityService's check battery and QualityReport behind /api/eidet/quality, the deterministic retrieval scorecard (BenchmarkRunner's fused-vs-flat-baseline arms, RetrievalMetrics, AmaCapability headings, the CI-asserted docs/benchmark.md), and the SWE Context Bench harness in tools/Eidet.Bench with its LeaderboardGuard. Use when the task touches a quality check, a retrieval metric, the gold dataset, eidet bench, or a benchmark number. Not for the ranking pipeline itself (see recall), not for the integrity auditor (see writepath).
recall
Prime on Eidet's read path before changing it — hybrid lexical+vector+abstraction fusion, UCB exploration, dual-clock FadeMem recency, per-repo alpha learning, graph-neighbour and cue-anchor expansion, trust/ROI/quarantine de-boosts, per-type budgets, the generation-token recall cache, and L0/L1 context assembly. Use when the task touches RecallScoring, Fuse, RecallCache, RecallOptions/MemoryQuery, GetContextAsync, the wake-up budget, stage or valence recall filters, Memories_Search, or "why did this memory (not) come back". Not for the write-time gates or the trust model itself (see writepath), not for the MemoryEntry shape (see memory), not for retrieval benchmarking (see quality).
sharing
Prime on Eidet's layers and packs before changing them — MemoryLayer types and the Local/Shared/Base priority ladder, LayerService mounting and applicability, the immutable LayerScope handed to recall, MarkdownPackFormat's YAML+markdown round-trip and its import provenance clamp, LayerSyncService and ILayerSource, and the AGENTS.md export. Use when the task touches pack export/import, mounting or unmounting a layer, cross-repo scope, the .eidet markdown format, or ExportService. Not for seeding from a repo's own files (see intake), not for backup/restore or remote sync.
writepath
Prime on Eidet's write path and integrity model before changing it — the always-on secret scanner, the signal/self-talk gate, WriteValidator entry construction, duplicate and conflict gates, quarantine, the poison log, derived MemoryTrust, provenance tiers, content commitments, and the IntegrityAuditor. Use when the task touches WriteValidator, SecretScanRule, ConflictGate, MemoryTrust, MemoryCommitment, ProvenanceRules, QuarantineInfo, IPoisonLog, IntegrityCheck, or any STRIDE tampering/poisoning finding. Not for the MemoryEntry shape or lifecycle verbs (see memory), not for recall ranking (see recall), not for scheduled rewrites (see maintenance).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.