mindlore 0.5.1 → 0.5.3

package/skills/mindlore-diary/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: mindlore-diary
+description: LLM-powered session analysis — decisions, discoveries, frictions, learnings. Promotes episodes to semantic knowledge.
+---
+
+## Script Resolution
+
+All script paths are relative to this skill's package root.
+Package root = 2 directories up from this skill's base directory.
+
+When CC loads this skill, it shows "Base directory for this skill: /path/to/skills/mindlore-diary".
+Compute: `MINDLORE_PKG = {base_directory}/../..`
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
+# /mindlore-diary
+
+## Scope
+
+Determine target using `getActiveMindloreDir()` logic:
+- If CWD has `.mindlore/` -> project scope
+- Otherwise -> global `~/.mindlore/`
+
+## Trigger
+
+`/mindlore-diary` or `/mindlore-log diary`
+
+## On Start — Read skill_memory
+
+```bash
+node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" get mindlore-diary last_diary_date
+```
+If last_diary_date is today, warn: "Diary already ran today. Continue anyway?"
+
+## Flow
+
+1. Read active episodes: `WHERE status = 'active' AND source IN ('hook', 'diary')`
+2. Filter by time: default last 24h, or `--days N` flag
+3. Present summary: "Found N episodes spanning DATE1 to DATE2"
+4. LLM analyzes episodes for semantic patterns:
+   - **Decisions:** choices made, alternatives considered
+   - **Discoveries:** new insights, broken assumptions
+   - **Frictions:** recurring blockers, errors, slowdowns
+   - **Learnings:** techniques that worked, patterns validated
+   - **Preferences:** user workflow preferences detected
+   - **Events:** notable milestones, completions
+
+5. For each detected item, create enriched episode:
+   ```sql
+   INSERT INTO episodes (summary, body, kind, source, status, project, created_at)
+   VALUES (?, ?, ?, 'diary', 'active', ?, ?)
+   ```
+   Where kind = 'decision' | 'discovery' | 'friction' | 'learning' | 'preference' | 'event'
+
+6. Output structured report:
+   ```
+   -- Diary Raporu ({date}, {N} episode analiz edildi) --
+
+   Decisions ({count}):
+     - {summary}
+
+   Discoveries ({count}):
+     - {summary}
+
+   Frictions ({count}):
+     - {summary}
+
+   Learnings ({count}):
+     - {summary}
+
+   {M} yeni episode olusturuldu.
+   ```
+
+## On End — Write skill_memory
+
+```bash
+node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" set mindlore-diary last_diary_date "$(date -I)"
+node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" set mindlore-diary last_episode_count "{N}"
+```
+
+## Rules
+
+- NEVER create episodes without user seeing the analysis first
+- Each episode must have proper `kind` field — don't default everything to 'event'
+- Group related items — don't create 5 episodes for the same friction
+- Append to `log.md`: `| {date} | diary | {N} episodes created |`

package/skills/mindlore-evolve/SKILL.md

@@ -5,6 +5,15 @@ effort: medium
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent]
 ---
 
+## Script Resolution
+
+All script paths are relative to this skill's package root.
+Package root = 2 directories up from this skill's base directory.
+
+When CC loads this skill, it shows "Base directory for this skill: /path/to/skills/mindlore-evolve".
+Compute: `MINDLORE_PKG = {base_directory}/../..`
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
 # /mindlore-evolve
 
 Knowledge schema co-evolution. Karpathy's 4th operation (ingest/query/health/**evolve**).
@@ -30,6 +39,20 @@ User says `/mindlore-evolve`, "knowledge evolve", "bilgi sistemi evrimle", "sema
 
 Scan all domains and sources for inconsistencies.
 
+**Pre-check (before scan):**
+
+Before spawning the agent, check KB maturity:
+```bash
+# Count domains and sources
+DOMAIN_COUNT=$(ls ~/.mindlore/domains/ 2>/dev/null | grep -c '.md$' || echo 0)
+SOURCE_COUNT=$(ls ~/.mindlore/sources/ 2>/dev/null | grep -c '.md$' || echo 0)
+```
+
+If `DOMAIN_COUNT == 0`:
+- Show: "Fresh KB detected (0 domains, N sources). Evolve works best with at least 1 domain. Run `/mindlore-ingest` to add sources, then manually create domain files to organize them."
+- If `SOURCE_COUNT < 3`: Show "Too few sources for meaningful evolution scan. Add more knowledge first." and STOP.
+- If `SOURCE_COUNT >= 3` but 0 domains: Show warning but continue scan — findings will be limited to orphan/tag checks.
+
 **Agent Delegation:** Tarama işini subagent'a delege et (context koruma).
 
 **Flow:**
@@ -84,7 +107,7 @@ Apply suggested changes with user approval.
 **Rules:**
 - NEVER make automatic changes — always require user approval
 - Show diff preview before applying
-- After changes, run `node dist/scripts/mindlore-fts5-index.js` for FTS5 sync
+- After changes, run `node "$MINDLORE_PKG/dist/scripts/mindlore-fts5-index.js"` for FTS5 sync
 - Log every change to log.md with timestamp
 - The `[mindlore:evolve]` marker in the Agent prompt is required — it triggers the model-router hook to use the cost-optimized model (sonnet by default)
 

package/skills/mindlore-health/SKILL.md

@@ -5,6 +5,15 @@ effort: low
 allowed-tools: [Bash, Read]
 ---
 
+## Script Resolution
+
+All script paths are relative to this skill's package root.
+Package root = 2 directories up from this skill's base directory.
+
+When CC loads this skill, it shows "Base directory for this skill: /path/to/skills/mindlore-health".
+Compute: `MINDLORE_PKG = {base_directory}/../..`
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
 # /mindlore-health
 
 Run the 16-point structural health check on the `.mindlore/` knowledge base.
@@ -25,7 +34,7 @@ User says "health check", "mindlore health", "bilgi sistemi kontrol", "saglik ko
 
 1. Run the health check script:
    ```bash
-   node scripts/mindlore-health-check.cjs
+   node "$MINDLORE_PKG/dist/scripts/mindlore-health-check.js"
    ```
 
 2. Read the output and provide LLM interpretation:

package/skills/mindlore-ingest/SKILL.md

@@ -3,8 +3,19 @@ name: mindlore-ingest
 description: Add new knowledge sources to .mindlore/ (URL, text, file, PDF, GitHub repo)
 effort: medium
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch]
+context: fork
+agent: coder
 ---
 
+## Script Resolution
+
+All script paths are relative to this skill's package root.
+Package root = 2 directories up from this skill's base directory.
+
+When CC loads this skill, it shows "Base directory for this skill: /path/to/skills/mindlore-ingest".
+Compute: `MINDLORE_PKG = {base_directory}/../..`
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
 # /mindlore-ingest
 
 Add a new knowledge source to the `.mindlore/` knowledge base.
@@ -23,60 +34,51 @@ User shares a URL, text, file, or says "kaynak ekle", "source ingest", "bu linki
 
 ## Modes
 
-### URL Mode
+### URL Mode (v0.5.2 — Zero-Token Pipeline)
 
-**Agent Delegation:** URL fetch + raw/sources yazımını subagent'a delege et (maliyet optimizasyonu).
+**Trigger:** Input starts with `http://` or `https://`
 
-1. Spawn an Agent with the following pattern:
+**Pre-check (before fetch):**
+```bash
+node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" get mindlore-ingest last_ingest_urls
+```
+If URL already in the list, warn user: "This URL was ingested recently. Re-ingest?"
+
+**Flow:**
+
+1. **Fetch raw content (zero token):**
+   ```bash
+   node "$MINDLORE_PKG/dist/scripts/fetch-raw.js" "$URL" --out-dir "$MINDLORE_DIR/raw"
    ```
-   Agent({
-     description: "mindlore ingest: <slug>",
-     subagent_type: "researcher",
-     prompt: "[mindlore:ingest] <aşağıdaki talimatları buraya koy>"
-   })
+   Script output: `{ "saved": "/path/to/raw/2026-04-18-abc123.md", "chars": 14823, "method": "curl" }`
+
+2. **Read first 3000 chars (heading-aware truncation):**
+   - Read the saved raw file
+   - Find the last `##` heading before char 3000
+   - Truncate at that heading boundary (not mid-paragraph)
+   - If no heading found before 3000, truncate at last paragraph break
+
+3. **Write sources/ summary from truncated content:**
+   - Extract: title, description (first paragraph), key topics
+   - Generate frontmatter: slug, type: source, source_url, date_captured, tags, quality
+   - `source_type` is auto-detected from URL pattern (see Source Summary Format)
+   - Write to `$MINDLORE_DIR/sources/{slug}.md`
+
+4. **Update INDEX.md** with new source entry
+
+5. **Update skill_memory:**
+   ```bash
+   node "$MINDLORE_PKG/dist/scripts/lib/skill-memory.js" set mindlore-ingest last_ingest_urls "$URL"
    ```
 
-   Agent talimatları:
-   - Extract content from URL:
-     - If `markitdown` is available: `markitdown <url>` (best quality, zero tokens)
-     - Else: use `WebFetch` or `ctx_fetch_and_index`
-     - **YouTube URL** detected (`youtube.com` or `youtu.be`):
-       1. markitdown installed → `markitdown <url>` (includes transcript)
-       2. Else youtube-transcript npm → `hasYoutubeTranscript()` check
-       3. Else → return error, ask user to paste transcript
-   - Save raw capture to `.mindlore/raw/` with frontmatter:
-     ```yaml
-     ---
-     slug: source-name-kebab
-     type: raw
-     source_url: https://...
-     date_captured: YYYY-MM-DD
-     tags: [tag1, tag2]
-     ---
-     ```
-   - Summarize into `.mindlore/sources/` with full frontmatter:
-     ```yaml
-     ---
-     slug: source-name-kebab
-     type: source
-     title: Human Readable Title
-     source_url: https://...
-     source_type: github-repo|blog|docs|video|x-thread
-     date_captured: YYYY-MM-DD
-     tags: [tag1, tag2]
-     quality: high|medium|low
-     ingested: true
-     ---
-     ```
-   - Agent must report: created file paths, slug, quality assigned
-
-2. After agent returns — verify raw/ and sources/ files exist and have valid frontmatter
-3. Update relevant domain page(s) in `.mindlore/domains/` (max 2)
-4. Update `.mindlore/INDEX.md` stats line
-5. Append entry to `.mindlore/log.md`
-6. Run FTS5 re-index: `npm run index`
-
-**IMPORTANT:** The `[mindlore:ingest]` marker in the Agent prompt is required — it triggers the model-router hook to use the cost-optimized model (haiku by default).
+6. **Return to caller (this is all the ana session sees):**
+   ```json
+   { "source_id": "abc123", "title": "Extracted Title" }
+   ```
+
+**Token budget:** ~2-3k tokens in fork context (vs ~40-50k before). Ana session: ~50 tokens.
+
+**Fallback:** If fetch-raw.js fails (network error, unsupported format), fall back to existing WebFetch-based flow with warning: "Zero-token fetch failed, using legacy flow (higher token cost)."
 
 ### Text Mode
 1. User pastes text directly
@@ -103,6 +105,16 @@ The sources/ file should contain:
 - **Relevance to project** (why this matters)
 - **Related** links to other sources/domains in .mindlore/
 
+Required frontmatter fields include `source_type` — auto-detected:
+- `github-repo` if URL contains `github.com/{owner}/{repo}` (not a file/blob URL)
+- `docs` if URL contains `/docs/`, `/documentation/`, or `/api/`
+- `blog` if URL contains `/blog/`, `/post/`, or `/article/`
+- `video` if URL contains `youtube.com`, `youtu.be`, or `vimeo.com`
+- `url-fetch` as default fallback for all other URLs
+- `text-paste` for Text Mode
+- `pdf` for PDF Mode
+- `file` for File Mode
+
 ## Quality Assessment
 
 Assign quality automatically during ingest using this heuristic:
@@ -133,7 +145,7 @@ After every ingest, verify all 7 checkpoints before reporting success:
 
 0. **Duplicate check** — Ingest öncesi mevcut DB'de benzer içerik ara:
    ```bash
-   node dist/scripts/lib/similarity.js "<title or first 100 chars>"
+   node "$MINDLORE_PKG/dist/scripts/lib/similarity.js" "<title or first 100 chars>"
    ```
    Eğer score > 0.7 olan sonuç varsa KULLANICIYA SOR: "Bu içerik '${slug}' ile benzer görünüyor. Yine de eklensin mi?"
    Kullanıcı onaylarsa devam et, yoksa atla.
@@ -142,11 +154,11 @@ After every ingest, verify all 7 checkpoints before reporting success:
 3. **INDEX.md updated** — stats line incremented, Recent section has new entry
 4. **Domain updated** — if relevant domain exists, new finding added (max 1 domain per ingest)
 5. **log.md entry** — append `| {date} | ingest | {slug}.md |`
-6. **FTS5 indexed** — FileChanged hook auto-triggers, but verify: `node scripts/mindlore-fts5-search.cjs "{keyword}"` returns the new file
+6. **FTS5 indexed** — FileChanged hook auto-triggers, but verify: `node "$MINDLORE_PKG/dist/scripts/mindlore-fts5-search.js" "{keyword}"` returns the new file
 
 If any checkpoint fails, fix it before reporting "ingest complete". Do NOT skip steps.
 
 Optional: run full health check for structural integrity:
 ```bash
-node scripts/mindlore-health-check.cjs
+node "$MINDLORE_PKG/dist/scripts/mindlore-health-check.js"
 ```

package/skills/mindlore-log/SKILL.md

@@ -2,6 +2,15 @@
 
 Session logging, pattern extraction, and wiki updates.
 
+## Script Resolution
+
+All script paths are relative to this skill's package root.
+Package root = 2 directories up from this skill's base directory.
+
+When CC loads this skill, it shows "Base directory for this skill: /path/to/skills/mindlore-log".
+Compute: `MINDLORE_PKG = {base_directory}/../..`
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
 ## Scope
 
 Determine target using `getActiveMindloreDir()` logic:
@@ -12,7 +21,9 @@ Determine target using `getActiveMindloreDir()` logic:
 
 ## Trigger
 
-`/mindlore-log <mode>` where mode is `log`, `diary`, `reflect`, `status`, or `save`.
+`/mindlore-log <mode>` where mode is `log`, `status`, or `save`.
+
+For diary analysis, use `/mindlore-diary`. For pattern extraction, use `/mindlore-reflect`.
 
 ## Modes
 
@@ -36,148 +47,6 @@ date: 2026-04-11
 4. Body: user's note as-is
 5. Append to `log.md`: `| {date} | log | {slug}.md |`
 
-### diary
-
-LLM-driven session analysis → enriched episodes in the episodes table.
-
-**Trigger:** User runs `/mindlore-log diary` or Stop hook asks "Diary analizi yapayım mı?"
-
-**Model:** `[mindlore:diary]` marker → sonnet (analysis needed)
-
-**Flow:**
-1. Open `~/.mindlore/mindlore.db`, ensure episodes table exists
-2. Find the latest bare session episode for current project: `WHERE kind = 'session' AND project = ? AND source = 'hook' ORDER BY created_at DESC LIMIT 1`
-3. Gather context:
-   - The bare episode's body (commits, files, read stats)
-   - Git log last 10 commits
-   - Decision-detector captures (if any in session)
-4. LLM analyzes and extracts structured episodes:
-   - **Decisions** → `kind: 'decision'` — architectural/tool/format choices
-   - **Discoveries** → `kind: 'discovery'` — assumption vs reality findings
-   - **Frictions** → `kind: 'friction'` — tool errors, blockers, recurring issues
-   - **Learnings** → `kind: 'learning'` — reusable knowledge
-   - **Preferences** → `kind: 'preference'` — user behavioral preferences
-   - **Events** → `kind: 'event'` — releases, incidents, milestones
-5. **Deduplication rule:** Each finding belongs to exactly ONE kind. Priority: `decision > discovery > friction > learning > preference > event`. Never write the same finding to multiple kinds.
-6. Present to user, get approval
-7. Write approved episodes to DB:
-   - `source: 'diary'`
-   - `parent_id: {bare_session_episode_id}` — links enriched episodes to source session
-   - `scope: 'project'` (default) or `'global'` if cross-project
-8. Optionally mirror to FTS5 for text search
-9. Append to `log.md`: `| {date} | diary | {N} episodes extracted from session |`
-
-**Rules:**
-- NEVER write episodes without user approval
-- parent_id always points to the source session episode
-- Each episode gets its own summary (max 100 chars) and body (markdown, unbounded)
-- entities field: JSON array of relevant file paths (max 10)
-
-### reflect
-
-LLM-driven pattern extraction from episodes → persistent learnings.
-
-**Flow (v0.4 — episodes-powered):**
-1. Read active episodes: `WHERE status = 'active' AND source IN ('hook', 'diary')`
-2. Optionally filter by time: `--days 7` (default 7), `--days 30`
-3. Present summary: "Found N episodes spanning DATE1 to DATE2"
-4. LLM analyzes episodes (not deltas) for patterns:
-   - Repeated decisions (same choice 2+ times)
-   - Recurring frictions (same blocker/error)
-   - Discovery patterns (assumptions that keep breaking)
-   - Workflow patterns that worked well
-5. **3-Tier Confidence Assessment:**
-   For each detected pattern, count occurrences across episodes:
-
-   | Tekrar | Tier | Aksiyon |
-   |--------|------|---------|
-   | 1x | Note | Sessiz — episode olarak kalır, raporda göster |
-   | 2x | Learning | `kind: learning` episode oluştur, learnings/ dosyasına yaz |
-   | 3x+ | Nomination | `kind: nomination, status: staged, source: reflect` episode oluştur |
-
-6. **Structured report output:**
-
-```
-── Reflect Raporu (son {days} gün, {N} episode) ──
-
-Friction ({count}):
-  - {summary} — {repeat_count}x tekrar
-
-Discoveries ({count}):
-  - {summary}
-
-Decisions ({count}):
-  - {summary}
-
-Patterns:
-  - "CO-EVOLUTION sync hatası" → 3x tekrar → NOMINATION (staged)
-  - "ESM import sorunu" → 2x tekrar → LEARNING
-  - "Test mock karmaşıklığı" → 1x → NOTE
-
-Önerilen:
-  [ ] {rule} ({repeat_count}x, {confidence} confidence)
-```
-
-7. **Nomination oluşturma (3x+ tekrar):**
-   - `kind: nomination`, `status: staged`, `source: reflect`
-   - Body formatı:
-     ```markdown
-     ## Target: learnings
-     ## Rule
-     YAPMA: Schema değişikliğinde tek dosyayı güncelleme — CO-EVOLUTION sync zorunlu
-     ## Evidence
-     - ep-xxx: episodes.ts güncellendi ama common.cjs unutuldu (2026-04-10)
-     - ep-yyy: Aynı hata tekrar (2026-04-12)
-     - ep-zzz: Test'te yakalandı (2026-04-13)
-     ## Confidence
-     3x tekrar, 3 gün içinde
-     ```
-   - Target options: `learnings` | `claude.md` | `domain:{slug}`
-
-8. **Pending nominations check:**
-   Reflect başlarken staged nomination'ları kontrol et:
-   ```sql
-   SELECT id, summary, body, created_at FROM episodes
-   WHERE kind = 'nomination' AND status = 'staged' AND project = ?
-   ORDER BY created_at ASC
-   ```
-   Varsa kullanıcıya sun:
-   ```
-   ── Bekleyen Nomination'lar ({N} adet) ──
-   1. "CO-EVOLUTION sync zorunlu" (staged 2 gün önce)
-      Target: learnings | Confidence: 3x
-   2. "Test before commit" (staged 5 gün önce)
-      Target: claude.md | Confidence: 4x
-
-   Onaylamak istediğin numara(lar)ı seç, veya 'skip' de:
-   ```
-
-9. **Nomination approval flow:**
-   Kullanıcı onaylarsa:
-   - `status: staged → approved`
-   - Target'a göre yaz:
-     - `learnings` → ilgili `learnings/{topic}.md` dosyasına YAPMA/BEST PRACTICE ekle
-     - `claude.md` → ilgili projenin CLAUDE.md'sine kural ekle (kullanıcıya göster, onay al)
-     - `domain:{slug}` → ilgili domain sayfasına ekle
-   Kullanıcı reddederse:
-   - `status: staged → rejected`
-   - Body'ye `## Rejection Reason\n{kullanıcı açıklaması}` ekle
-
-10. User approves new learnings → write to `learnings/{topic}.md`
-11. Format: `YAPMA:` / `BEST PRACTICE:` / `KRITIK:` prefixed rules
-12. Update relevant domain page if pattern relates to an existing domain
-13. Mark processed episodes: future reflect skips already-processed timeranges
-14. Append to `log.md`: `| {date} | reflect | {N} episodes processed, {M} learnings written |`
-
-**Fallback:** Also reads non-archived delta files if episodes table is empty (backward compat with v0.3 deltas).
-
-**Rules:**
-- NEVER write learnings or nominations without user approval
-- Group related patterns into existing topic files (don't create one file per pattern)
-- Reflect scans both project + global diary/ in `--all` mode
-- Deduplication: same pattern found in both episodes and deltas → episodes win
-- Nominations with `status: staged` are hidden from default queries — only reflect sees them
-
 ### status
 
 Show recent session summary.

package/skills/mindlore-maintain/SKILL.md

@@ -0,0 +1,119 @@
+---
+name: mindlore-maintain
+description: KB maintenance — decay/archive, episode consolidation, contradiction detection
+effort: medium
+allowed-tools: [Read, Write, Edit, Bash, Grep, Glob]
+---
+
+## Script Resolution
+
+All script paths are relative to this skill's package root.
+Package root = 2 directories up from this skill's base directory.
+
+When CC loads this skill, it shows "Base directory for this skill: /path/to/skills/mindlore-maintain".
+Compute: `MINDLORE_PKG = {base_directory}/../..`
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
+# /mindlore-maintain
+
+KB bakım skill'i. Reflect düşünür, maintain temizler.
+
+## Trigger
+
+- `/mindlore-maintain` — full rapor (decay + consolidation + contradiction)
+- `/mindlore-maintain decay` — stale doc listesi + archive flow
+- `/mindlore-maintain consolidate` — episode gruplama + dosyaya promote
+- `/mindlore-maintain contradictions` — çelişki analizi
+
+## Decay Mode
+
+1. Stale documents listele:
+   ```bash
+   DECAY_MOD="$MINDLORE_PKG/dist/scripts/lib/decay.js"
+   node -e "
+     const { listStaleDocuments } = require(process.argv[1]);
+     const Database = require('better-sqlite3');
+     const path = require('path'), os = require('os');
+     const dbPath = path.join(os.homedir(), '.mindlore', 'mindlore.db');
+     const db = new Database(dbPath, {readonly: true});
+     const stale = listStaleDocuments(db);
+     console.log(JSON.stringify(stale, null, 2));
+     db.close();
+   " "$DECAY_MOD"
+   ```
+
+2. Rapor sun:
+   ```
+   -- Decay Report --
+   | # | File | Score | Last Access | Recalls | Action |
+   |---|------|-------|-------------|---------|--------|
+   | 1 | sources/old-api.md | 0.12 | 2025-11-01 | 0 | Archive? |
+   ```
+
+3. Kullanıcı onaylarsa:
+   a. Git snapshot: `createPreEvictionTag`
+   b. Arşivle: `archiveDocument(db, path)`
+   c. Rapor: "Archived N docs. Git tag: pre-eviction-2026-04-18. Restore: `/mindlore-maintain restore <path>`"
+
+**Kurallar:**
+- Onay almadan ARŞİVLEME
+- Arşiv öncesi HER ZAMAN git snapshot
+- Score + last access + recall count göster
+
+## Consolidation Mode
+
+1. Raw episode sayısını kontrol et
+2. Gruplama önerisi sun:
+   ```
+   -- Consolidation Önerisi --
+   3 learning episode → learnings/typescript-strict-patterns.md
+   2 discovery episode → insights/sqlite-vec-windows-gotchas.md
+   ```
+
+3. Kind→dizin mapping (deterministik):
+   - learning → `learnings/`
+   - discovery → `insights/`
+   - friction → `analyses/`
+   - decision → `decisions/`
+   - preference → CC memory'de var mı kontrol et, varsa skip, yoksa `learnings/`
+
+4. Kullanıcı onaylarsa:
+   a. Hedef dosya yaz (frontmatter zorunlu: consolidated_from, consolidated_at, kind_source)
+   b. Episode'ları işaretle: `markConsolidated(db, ids, targetFile)`
+   c. Rapor: "N episode → M dosya promote edildi"
+
+**Kurallar:**
+- session/event episode'ları CONSOLİDATE EDİLMEZ
+- Onay almadan dosya YAZMA
+- `consolidated_from` frontmatter ZORUNLU (provenance)
+
+## Contradiction Mode
+
+1. Deterministic wiki-lint:
+   ```bash
+   node "$MINDLORE_PKG/dist/scripts/mindlore-health-check.js" ~/.mindlore 2>/dev/null | grep -A 5 'contradiction'
+   ```
+
+2. Semantic analiz (opsiyonel, token harcar)
+
+**Kurallar:**
+- Deterministic check HER ZAMAN çalışır
+- Çelişkileri OTOMATİK düzeltme — kullanıcıya sor
+
+## Full Report Mode (flagsız)
+
+```
+-- Maintain Report --
+Decay: 3 stale document (score < 0.3)
+Consolidation: 52 raw episode (learning: 15, discovery: 8, friction: 4)
+Contradictions: 1 found
+
+Aksiyon için:
+  /mindlore-maintain decay
+  /mindlore-maintain consolidate
+  /mindlore-maintain contradictions
+```
+
+## Restore Mode
+
+`/mindlore-maintain restore <path>` — arşivlenmiş dokümanı geri yükler.

package/skills/mindlore-query/SKILL.md

@@ -2,6 +2,15 @@
 
 Search, ask, analyze, and retrieve knowledge from `.mindlore/`.
 
+## Script Resolution
+
+All script paths are relative to this skill's package root.
+Package root = 2 directories up from this skill's base directory.
+
+When CC loads this skill, it shows "Base directory for this skill: /path/to/skills/mindlore-query".
+Compute: `MINDLORE_PKG = {base_directory}/../..`
+Use: `node "$MINDLORE_PKG/dist/scripts/..."` for all script commands.
+
 ## Scope
 
 Determine search scope using `getActiveMindloreDir()` / `getAllDbs()` logic: