superlocalmemory 3.6.13 → 3.6.14

package/skills/slm-list-recent/SKILL.md

@@ -1,348 +0,0 @@
----
-name: slm-list-recent
-description: List most recent memories in chronological order. Use when the user wants to see what was recently saved, review recent conversations, check what they worked on today, or browse memory history. Shows memories sorted by creation time (newest first).
-version: "3.4.23"
-license: AGPL-3.0-or-later
-compatibility: "Requires SuperLocalMemory V2 installed at ~/.claude-memory/"
-attribution:
-  creator: Varun Pratap Bhardwaj
-  role: Solution Architect & Original Creator
-  project: SuperLocalMemory V2
----
-
-# SuperLocalMemory: List Recent
-
-List most recent memories in chronological order (newest first).
-
-## Usage
-
-```bash
-slm list [--limit N] [--project name] [--tags tag1,tag2] [--today|--week|--month]
-```
-
-## Examples
-
-### Example 1: Last 10 Memories (Default)
-```bash
-$ slm list
-```
-
-**Output:**
-```
-📝 Recent Memories (10 most recent)
-
-[ID: 1247] 5 minutes ago
-Fixed JWT token refresh bug - tokens were expiring too fast
-Tags: bug-fix, jwt, auth
-Project: myapp
-Importance: 8
-
-[ID: 1246] 2 hours ago
-React hooks best practices: useCallback for memoization
-Tags: react, performance, hooks
-Project: frontend-app
-Importance: 6
-
-[ID: 1245] 4 hours ago
-Database migration strategy: use Alembic for versioning
-Tags: database, postgresql, migration
-Project: myapp
-Importance: 7
-
-[ID: 1244] Yesterday 18:42
-Decided to use FastAPI over Flask for new microservice
-Tags: python, backend, api, decision
-Project: myapp
-Importance: 9
-
-[ID: 1243] Yesterday 15:30
-Code review feedback: add more error handling to API endpoints
-Tags: code-review, api, error-handling
-Project: myapp
-Importance: 6
-
-...
-```
-
-### Example 2: Last 5 Memories
-```bash
-$ slm list --limit 5
-```
-
-### Example 3: Today's Memories
-```bash
-$ slm list --today
-```
-
-**Shows only memories created today**
-
-### Example 4: This Week
-```bash
-$ slm list --week
-```
-
-**Shows memories from last 7 days**
-
-### Example 5: Filter by Project
-```bash
-$ slm list --project myapp --limit 20
-```
-
-**Shows 20 most recent memories from "myapp" project**
-
-### Example 6: Filter by Tags
-```bash
-$ slm list --tags security,auth --limit 15
-```
-
-**Shows 15 most recent memories tagged with security AND auth**
-
-## Arguments
-
-| Argument | Type | Required | Default | Description |
-|----------|------|----------|---------|-------------|
-| `--limit` | integer | No | 10 | Number of memories to show |
-| `--project` | string | No | All | Filter by project |
-| `--tags` | string | No | All | Filter by tags (comma-separated) |
-| `--today` | flag | No | - | Show only today's memories |
-| `--week` | flag | No | - | Show last 7 days |
-| `--month` | flag | No | - | Show last 30 days |
-
-## Sorting & Display
-
-### Chronological Order
-Memories are always shown **newest first** (reverse chronological).
-
-**Rationale:** Recent context is usually most relevant.
-
-### Timestamps
-- **"5 minutes ago"** - Within last hour
-- **"2 hours ago"** - Within last 24 hours
-- **"Yesterday 18:42"** - Yesterday with time
-- **"Feb 05 14:23"** - Older than yesterday
-
-### Content Preview
-- First 200 characters shown
-- Ellipsis (...) if truncated
-- Use `slm recall --id <ID>` for full content
-
-## Use Cases
-
-### 1. Daily Standup Prep
-```bash
-# What did I work on yesterday?
-slm list --yesterday
-```
-
-### 2. Resume Context
-```bash
-# What was I working on before lunch?
-slm list --today --limit 5
-```
-
-### 3. Weekly Review
-```bash
-# What decisions did I make this week?
-slm list --week --tags decision
-```
-
-### 4. Project Check-In
-```bash
-# Recent memories for current project
-slm list --project myapp --limit 20
-```
-
-### 5. Security Audit
-```bash
-# All security-related memories
-slm list --tags security --limit 100
-```
-
-## Advanced Usage
-
-### Pagination
-```bash
-# First page
-slm list --limit 10
-
-# Next page (note IDs, then use recall)
-slm recall --before-id 1237 --limit 10
-```
-
-### Export to File
-```bash
-# Save recent work to file
-slm list --week > this-week.txt
-
-# JSON export (for processing)
-slm list --format json --limit 100 > memories.json
-```
-
-### Pipe to Other Commands
-```bash
-# Count memories per project
-slm list --limit 1000 | grep "Project:" | sort | uniq -c
-
-# Find common tags
-slm list --limit 500 | grep "Tags:" | tr ',' '\n' | sort | uniq -c | sort -rn
-```
-
-### Combined with Other Skills
-```bash
-# 1. List recent memories
-slm list --today
-
-# 2. Notice interesting pattern
-
-# 3. Search for related memories
-slm recall "FastAPI performance"
-
-# 4. Add new related memory
-slm remember "FastAPI async endpoints improve throughput by 3x" --tags performance,fastapi
-```
-
-## Output Formats
-
-### Standard Format (Default)
-```
-[ID: 42] Timestamp
-Content preview...
-Tags: tag1, tag2
-Project: name
-Importance: 7
-```
-
-### Compact Format
-```bash
-slm list --format compact
-```
-```
-42 | 5m ago | Content preview... | myapp
-43 | 2h ago | Another memory... | default
-```
-
-### JSON Format
-```bash
-slm list --format json
-```
-```json
-{
-  "memories": [
-    {
-      "id": 42,
-      "content": "Full content here",
-      "tags": ["tag1", "tag2"],
-      "project": "myapp",
-      "importance": 7,
-      "created_at": "2026-02-07T14:23:00Z"
-    }
-  ],
-  "count": 10,
-  "total": 1247
-}
-```
-
-### CSV Format
-```bash
-slm list --format csv
-```
-```csv
-id,content,tags,project,importance,created_at
-42,"Content here","tag1,tag2",myapp,7,2026-02-07T14:23:00Z
-43,"Another memory","tag3",default,5,2026-02-07T12:15:00Z
-```
-
-## Performance
-
-| Memory Count | List Time | Notes |
-|--------------|-----------|-------|
-| 10 | ~50ms | Instant |
-| 100 | ~200ms | Fast |
-| 1,000 | ~500ms | Acceptable |
-| 10,000+ | ~1s | Use filters |
-
-**Optimization tips:**
-- Use `--limit` to reduce results
-- Use `--project` or `--tags` filters
-- Use time filters (`--today`, `--week`)
-
-## Troubleshooting
-
-### "No memories found"
-**Cause:** Empty database or filters too restrictive
-
-**Solution:**
-```bash
-# Check total memory count
-slm status | grep "Total Memories"
-
-# Remove filters
-slm list  # No filters
-
-# Try different project
-slm list --project default
-```
-
-### "List takes too long"
-**Cause:** Large database, no filters
-
-**Solution:**
-```bash
-# Use smaller limit
-slm list --limit 5
-
-# Add filters
-slm list --today --project myapp
-
-# Rebuild indexes
-slm build-graph
-```
-
-### "Timestamps wrong"
-**Cause:** System timezone changed
-
-**Solution:**
-```bash
-# Check system timezone
-date
-
-# Timestamps are stored in UTC, displayed in local time
-# No action needed usually
-```
-
-## Comparison with Search
-
-| Feature | `slm list` | `slm recall` |
-|---------|------------|--------------|
-| **Sorting** | Chronological | Relevance |
-| **Use case** | Browse recent | Find specific |
-| **Speed** | Fast | Slower |
-| **Filters** | Basic | Advanced |
-| **Scoring** | No | Yes (relevance) |
-
-**Rule of thumb:**
-- Use `list` when you want to see **what you worked on recently**
-- Use `recall` when you want to **find specific information**
-
-## Notes
-
-- **Read-only:** Never modifies data
-- **Real-time:** Shows latest state
-- **Cross-tool:** Same list from Cursor, ChatGPT, Claude, etc.
-- **Privacy:** All local, no external calls
-
-## Related Commands
-
-- `slm remember` - Save a new memory
-- `slm recall` - Search memories by relevance
-- `slm status` - Check memory count and stats
-- `slm switch-profile` - View different profile's memories
-
----
-
-**Created by:** [Varun Pratap Bhardwaj](https://github.com/varun369) (Solution Architect)
-**Project:** SuperLocalMemory V2
-**License:** MIT (see [LICENSE](../../LICENSE))
-**Repository:** https://github.com/varun369/SuperLocalMemoryV2
-
-*Open source doesn't mean removing credit. Attribution must be preserved per MIT License terms.*

package/skills/slm-optimize/README.md

@@ -1,55 +0,0 @@
-# slm-optimize — Context Optimizer Skill
-
-Automatically compresses large tool outputs and caches repeated reads, reducing
-context window usage without a proxy and without losing the full 1M window.
-
-## Prerequisites
-
-- SuperLocalMemory v3.6.11+
-- `slm mcp` daemon running
-- `slm_compress` visible in `tools/list` (verify with your IDE's MCP tool inspector)
-
-## Install (Claude Code)
-
-```bash
-cp skills/slm-optimize/SKILL.md ~/.claude/skills/slm-optimize/SKILL.md
-```
-
-## Activate
-
-**Option A — On demand:**
-Invoke via the `Skill` tool: `Skill("slm-optimize")`
-
-**Option B — Auto-activate:**
-Add to your project or global `CLAUDE.md`:
-```markdown
-## Context Management
-Use the `slm-optimize` skill to compress large outputs and cache repeated reads.
-Invoke at session start if context > 50k tokens.
-```
-
-## Verify
-
-After activation, run `slm_optimize_stats()` from Claude Code. If it returns `ok:True`,
-all 5 optimize tools are reachable and the skill is working.
-
-## What it does
-
-| Feature | How |
-|---|---|
-| Compresses large tool outputs | `slm_compress` → compressed text + optional `ccr_id` |
-| Caches repeated file reads | `slm_cache_set` / `slm_cache_get` keyed by file path |
-| Caches repeated bash/search | Same KV tools, keyed by command |
-| Recovers exact originals | `slm_retrieve(ccr_id)` when byte-identical content needed |
-| Session stats | `slm_optimize_stats()` |
-
-## What it does NOT do
-
-- **Full-turn caching**: impossible without a proxy (`ANTHROPIC_BASE_URL`).
-  Use Surface A (proxy mode) for that.
-- **Guarantee savings**: results depend on content type and daemon compress config.
-
-## For Cursor, Antigravity, Codex
-
-Same SKILL.md works — all IDEs that support MCP tool calls can use the 5 tools.
-The skill itself is pure Markdown with no IDE-specific code.

package/skills/slm-optimize/SKILL.md

@@ -1,139 +0,0 @@
----
-name: slm-optimize
-description: >
-  Context optimizer for Claude Code + SLM. Compresses large outputs via
-  slm_compress (reversible CCR), caches repeated reads via slm_cache_set/get,
-  recovers originals via slm_retrieve. Works on any Claude plan, no proxy,
-  full context window preserved.
-  Requires SuperLocalMemory v3.6.11+ with optimize MCP tools enabled.
-version: "3.6.11"
-license: AGPL-3.0-or-later
-triggers:
-  - "slm-optimize"
-  - "compress context"
-  - "optimize context"
-  - "reduce tokens"
----
-
-# slm-optimize: Context Optimizer for Claude Code
-
-Reduces context window usage through compression and caching.
-No proxy required. Full 1M window preserved.
-
-**What this skill does NOT do:**
-- Cache the primary Claude conversation turn (impossible without a proxy).
-- Guarantee any specific savings percentage — results depend on content type and daemon config.
-
----
-
-## When This Skill Is Active
-
-Apply these rules automatically throughout the session once this skill is loaded.
-
----
-
-## Decision Rules
-
-### RULE 1 — Session start: compress CLAUDE.md if large
-
-At the start of any session where this skill is loaded:
-1. Read `CLAUDE.md` (or project CLAUDE.md).
-2. If `len(content) > 3000` characters: call `slm_compress(content=<text>, mode="normalize", reversible=False)`.
-3. Replace the in-context CLAUDE.md block with the compressed version.
-4. **Do not modify the actual file** — compress only the in-context representation.
-
-### RULE 2 — Large tool output: compress before processing
-
-After any tool call that returns > 2000 characters:
-1. Call `slm_compress(content=<output>, mode="auto", reversible=True)`.
-2. Work from `compressed` in the response.
-3. If `lossy=True`, store the returned `ccr_id` — call `slm_retrieve` only if you need the exact original for verification, diffing, or code parsing.
-
-**Never compress** (see RULE 6 for the complete exclusion list).
-
-### RULE 3 — Repeated file reads: KV cache
-
-Before calling `Read(file_path)` for a file you have already read this session:
-1. `slm_cache_get(key=f"file:{file_path}")`.
-2. If `hit=True` → use `value` directly. Skip the `Read` call.
-3. If `hit=False` → call `Read`, then `slm_cache_set(key=f"file:{file_path}", value=<content>, ttl_seconds=1800)`.
-
-If you edit a file via Edit/Write, immediately update or invalidate the cache entry.
-
-### RULE 4 — Repeated bash/search results: KV cache
-
-For any Bash or WebSearch call whose result you expect to reuse:
-1. `slm_cache_set(key=f"bash:{command[:64]}", value=<output>, ttl_seconds=600)`.
-2. On the next identical call: `slm_cache_get` first.
-
-Use `ttl_seconds=3600` for web search results (more expensive to re-run).
-
-### RULE 5 — Retrieve original via slm_retrieve
-
-If you compressed content with `lossy=True` and need the exact original:
-1. Call `slm_retrieve(ccr_id=<ccr_id from prior compress response>)`.
-2. Check `size_bytes` before retrieving if context is nearly full.
-3. Do not retrieve unless you actually need byte-identical content.
-
-### RULE 6 — What NOT to compress or cache
-
-- **Code being sent to Edit/Write**: never compress — the editor needs exact bytes.
-- **JSON or structured data you will parse**: compression can alter whitespace and break parsers.
-- **Secrets, API keys, credentials, tokens**: never store via `slm_cache_set`.
-- **CCR IDs**: never cache via `slm_cache_set` — treat as ephemeral session values.
-- **Very short outputs (< 500 chars)**: compression overhead exceeds the gain.
-
-### RULE 7 — Stats and awareness
-
-If the user asks "how much context have you saved?" or "what is the optimization status?":
-1. Call `slm_optimize_stats()`.
-2. Report `cache_kv_hits`, `compress_runs`, and `tokens_saved_compress` clearly.
-3. Note that proxy stats are daemon-persisted; KV stats are this session only.
-
-### RULE 8 — Fail-open behavior
-
-If any `slm_compress`, `slm_retrieve`, `slm_cache_set`, `slm_cache_get`, or
-`slm_optimize_stats` call returns `ok:False`:
-- Continue with the original (uncompressed/uncached) content.
-- Do not retry. Do not surface the error unless the user asks about optimization.
-- Optimization is always advisory — it must never block any primary task.
-
----
-
-## Examples
-
-### Compress a large file read
-
-```
-# Instead of working with 8000-char file output directly:
-result = slm_compress(content=<file_content>, mode="auto", reversible=True)
-# Work from result["compressed"]; keep result["ccr_id"] if lossy=True
-```
-
-### Cache a repeated grep result
-
-```
-cached = slm_cache_get(key="bash:grep -rn MyClass src/")
-if not cached["hit"]:
-    output = Bash("grep -rn MyClass src/")
-    slm_cache_set(key="bash:grep -rn MyClass src/", value=output, ttl_seconds=600)
-```
-
-### Recover original when needed
-
-```
-original = slm_retrieve(ccr_id=<ccr_id>)
-# original["content"] is byte-identical to what was compressed
-```
-
----
-
-## Stats and Troubleshooting
-
-Run `slm_optimize_stats()` to see current session counters.
-
-If tools return `ok:False`, the daemon may be down or the optimize module may not be
-configured. Continue with normal tool calls — this skill degrades gracefully.
-
-Verify tools are available: check that `slm_compress` appears in your MCP `tools/list`.
-Requires SuperLocalMemory v3.6.11+ with `slm mcp` running.