@olegkoval/agent-skills 1.6.0 → 1.7.0

package/packages/photography/gallery/adapters/windsurf/rules/gallery.md

@@ -0,0 +1,227 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+description: "Create photo galleries with AI-assisted layout curation and sequencing."
+---
+
+
+# Gallery Workflow
+
+Composed skill that creates photo galleries by orchestrating atomic scripts and sub-agents.
+
+## Philosophy
+
+This skill applies principles from masters of photo sequencing and curation:
+
+- **Keith Smith** — Group/Series/Sequence taxonomy; the gallery as a unified experience
+- **Jörg Colberg** — Ruthless editing; visual rhythm; pacing
+- **John Szarkowski** — The Five Characteristics for image assessment
+
+> "The individual pages have to give up their independence in order to form a union." — Keith Smith
+
+For detailed principles, see `docs/photo-layout-principles.md`.
+
+## Usage
+
+`/gallery {folder} "{title}" {slug}`
+
+Example: `/gallery cabo-2025 "CABO 2025" cabo`
+
+**Important:** All paths are relative to the current project directory. The `{folder}` argument is a path within the project (e.g., `./photos/cabo-2025` or just `cabo-2025`). Do NOT search the filesystem for folders — assume the user's folder exists in the current working directory.
+
+## Gallery Modes
+
+Before starting, identify the gallery's organizational mode:
+
+| Mode | Definition | Implication |
+|------|------------|-------------|
+| **Series** | Chronological journey (default) | Respect timestamp order; adjust only within temporal clusters |
+| **Group** | Thematic collection | Order is flexible; optimize for visual rhythm |
+| **Sequence** | Strict order with meaning | Order is sacred; only adjust layout, not arrangement |
+
+Most travel/event galleries are **Series**.
+
+## Architecture
+
+```
+Atomic Scripts (reusable):
+├── init-gallery-manifest.ts    Create manifest from EXIF
+├── merge-gallery-batches.ts    Combine batch files
+├── validate-gallery-manifest.ts Fix common errors
+└── generate-gallery-files.ts   Generate .astro pages
+
+Sub-Agent Skill:
+└── review-image-batch          AI reviews images → batch-NN.json
+```
+
+## Workflow
+
+### Phase 1: Initialize
+
+```bash
+bun scripts/init-gallery-manifest.ts {folder} "{title}" {slug}
+```
+
+Creates:
+- `src/data/gallery-manifests/{folder}.json` (images array, empty blocks)
+- `/tmp/gallery-batches/{folder}/` (clean directory for batch files)
+
+### Phase 2: Batch Review
+
+Spawn sub-agents to review images. **Each writes to its own file** (parallel-safe).
+
+```
+For batchIndex in 0..ceil(imageCount/8):
+  Task(
+    subagent_type: "general-purpose",
+    description: "Review gallery batch {batchIndex}",
+    prompt: <see below>
+  )
+```
+
+**Sub-agent prompt template:**
+
+```
+Review batch {batchIndex} for {folder} gallery.
+
+Read:
+- Manifest: src/data/gallery-manifests/{folder}.json
+- Layout guide: {plugin_base_dir}/skills/review-image-batch/references/layout-guide.md
+  (The plugin base directory is provided in the skill invocation header)
+
+Images to review: indices {startImage} to {endImage}
+(Calculate: startImage = batchIndex * 8, endImage = min(startImage + 7, totalImages - 1))
+
+Workflow:
+1. Read manifest to get image filenames
+2. Read layout guide for rules
+3. View each image file with Read tool
+4. Create layout blocks using your visual judgment
+5. Write JSON to: /tmp/gallery-batches/{folder}/batch-{NN}.json
+   where NN = batchIndex padded to 2 digits (00, 01, 02...)
+6. Return TEXT SUMMARY ONLY
+
+Output file format:
+{
+  "batchIndex": {batchIndex},
+  "startImage": {startImage},
+  "endImage": {endImage},
+  "blocks": [
+    { "layout": "WideImage", "images": ["DSCF1234.jpeg"], "props": {}, "notes": "..." }
+  ]
+}
+
+LAYOUT PHILOSOPHY:
+Apply visual judgment, not mechanical rules. A gallery needs rhythm and variety.
+
+Single-image (WideImage, OffsetImage, InsetImage, FullBleed):
+- Strong standalones, portraits, quiet moments
+
+Multi-image (TwoUp, ThreeUp):
+- Use when juxtaposition creates meaning beyond either image alone
+- Apply Lyons's test: Temporal? Spatial? Formal echo? Emotional pairing? Transformation?
+- A good TwoUp is BETTER than two mediocre WideImages
+- A true sequence (entering→through→emerging) deserves ThreeUp
+
+Spacer: Add breathing room after powerful images
+Chapter: Insert at location/theme changes
+```
+
+**Parallel execution:** Sub-agents can run in parallel since each writes to its own file.
+
+### Phase 3: Merge & Validate
+
+After all batches complete:
+
+```bash
+bun scripts/merge-gallery-batches.ts {folder}
+bun scripts/validate-gallery-manifest.ts src/data/gallery-manifests/{folder}.json
+```
+
+This combines all batch files and validates the result.
+
+### Phase 4: Global Arc Review (NEW)
+
+Before generating, review the merged manifest for overall coherence:
+
+1. **Count hero moments** — If >4 FullBleeds, demote some to WideImage
+2. **Check multi-image limits** — Max 2-3 TwoUp, 1-2 ThreeUp across entire gallery
+3. **Verify rhythm** — No consecutive high-weight blocks
+4. **Identify the climax** — One clear emotional peak, not many
+5. **Working backwards** — Does the final image provide satisfying closure?
+
+### Phase 5: Generate
+
+```bash
+bun scripts/generate-gallery-files.ts {folder}
+```
+
+Creates:
+- `src/data/{folder}.ts` (data file with chapters)
+- `src/pages/photographing/{slug}/index.astro`
+- Additional `.astro` files for each chapter (if multi-chapter)
+
+## Resume Protocol
+
+If interrupted, check `/tmp/gallery-batches/{folder}/` for existing batch files:
+
+```bash
+ls /tmp/gallery-batches/{folder}/
+```
+
+Only run missing batches, then merge.
+
+## Layout Philosophy
+
+A gallery needs **rhythm and variety** — loud moments, quiet moments, pairings that create meaning.
+
+| Layout | Purpose |
+|--------|---------|
+| WideImage | Strong standalone landscapes |
+| OffsetImage | Portraits, quiet moments, breathing room |
+| FullBleed | Hero shots, climactic moments |
+| InsetImage | Intimate details, visual whispers |
+| Spacer | Pacing, section breaks |
+| TwoUp | Images that speak to each other |
+| ThreeUp | True sequences (entering→through→emerging) |
+| SplitLayout | Asymmetric pairs, one frames the other |
+| Chapter | Location/theme breaks |
+
+### Lyons's Juxtaposition Test
+
+Pair images when juxtaposition creates meaning beyond either image alone:
+
+1. **Temporal** — Same moment, different angles
+2. **Spatial** — Same scene, complementary views
+3. **Formal echo** — Compositional rhyme (lines, shapes, colors)
+4. **Emotional** — Contrast or reinforcement
+5. **Transformation** — Together they say something neither says alone
+
+A strong TwoUp is better than two mediocre WideImages.
+
+## Output
+
+When complete:
+- Gallery URL: `/photographing/{slug}/`
+- Files:
+  - `src/data/gallery-manifests/{folder}.json`
+  - `src/data/{folder}.ts`
+  - `src/pages/photographing/{slug}/*.astro`
+
+## Composability
+
+Each piece is reusable:
+
+```bash
+# Just extract EXIF
+bun scripts/init-gallery-manifest.ts photos "Photos" photos
+
+# Just merge existing batches
+bun scripts/merge-gallery-batches.ts photos
+
+# Just regenerate pages from manifest
+bun scripts/generate-gallery-files.ts photos
+
+# Validate any manifest
+bun scripts/validate-gallery-manifest.ts src/data/gallery-manifests/photos.json
+```

package/packages/software-development/add-to-my-skills/SKILL.md

@@ -2,7 +2,8 @@
 name: add-to-my-skills
 description: Copy a newly created skill from another repo into this catalog, refresh the README and generated manifests, then commit and push the change. Use when the user wants to bring a skill they built elsewhere into this repository.
 license: MIT
-compatibility: Codex, Claude Code, Cursor, and other Agent Skills compatible tools. Requires a writable git repository and access to the source skill repo.
+allowed-tools: Bash, Read, Write, Edit
+compatibility: Codex, Claude Code, Cursor, GitHub Copilot, Windsurf, Kiro, and other Agent Skills compatible tools. Requires a writable git repository and access to the source skill repo.
 metadata:
   author: Oleg Koval
   tags:

package/packages/software-development/add-to-my-skills/adapters/claude/skills/add-to-my-skills/SKILL.md

@@ -4,7 +4,8 @@
 name: add-to-my-skills
 description: Copy a newly created skill from another repo into this catalog, refresh the README and generated manifests, then commit and push the change. Use when the user wants to bring a skill they built elsewhere into this repository.
 license: MIT
-compatibility: Codex, Claude Code, Cursor, and other Agent Skills compatible tools. Requires a writable git repository and access to the source skill repo.
+allowed-tools: Bash, Read, Write, Edit
+compatibility: Codex, Claude Code, Cursor, GitHub Copilot, Windsurf, Kiro, and other Agent Skills compatible tools. Requires a writable git repository and access to the source skill repo.
 metadata:
   author: Oleg Koval
   tags:

package/packages/software-development/add-to-my-skills/adapters/cursor/skills/add-to-my-skills/SKILL.md

@@ -4,7 +4,8 @@
 name: add-to-my-skills
 description: Copy a newly created skill from another repo into this catalog, refresh the README and generated manifests, then commit and push the change. Use when the user wants to bring a skill they built elsewhere into this repository.
 license: MIT
-compatibility: Codex, Claude Code, Cursor, and other Agent Skills compatible tools. Requires a writable git repository and access to the source skill repo.
+allowed-tools: Bash, Read, Write, Edit
+compatibility: Codex, Claude Code, Cursor, GitHub Copilot, Windsurf, Kiro, and other Agent Skills compatible tools. Requires a writable git repository and access to the source skill repo.
 metadata:
   author: Oleg Koval
   tags:

package/packages/software-development/add-to-my-skills/adapters/kiro/steering/add-to-my-skills.md

@@ -0,0 +1,78 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+inclusion: manual
+description: "Copy a newly created skill into this catalog, refresh manifests, and publish the change."
+---
+
+
+# Add to My Skills
+
+Use this skill when a skill was created in another repository and needs to be copied into this catalog as a first-class package.
+
+## Outcome
+
+Bring the source skill into `packages/software-development/`, register it in the catalog, refresh generated docs and adapters, and publish the change with a git commit and push.
+
+## When to Use
+
+- The user created a new `SKILL.md` in another repo and wants it added here
+- The user wants this catalog to become the canonical home for that skill
+- The user wants the README, generated manifests, commit, and push handled in one pass
+
+## Clarify Before Acting
+
+If any of these are unclear, ask up to 3 questions in one batch before editing:
+
+- Source repo or source skill path
+- Final skill name if it should differ from the source
+- Destination branch or remote if the push target is unclear
+
+Default assumptions when not specified:
+
+- Copy the source skill as a new canonical package in `packages/software-development/<skill-name>/`
+- Keep the source skill name unless the user asks to rename it
+- Use this repository as the destination
+- Commit with a conventional commit message and push to the current branch's upstream
+
+## Workflow
+
+1. Inspect the source skill:
+   - locate the source `SKILL.md`
+   - copy any supporting `references/`, `scripts/`, or `assets/` files that the skill needs
+   - note any repo-specific assumptions that need to be rewritten for this catalog
+2. Choose the package location:
+   - default to `packages/software-development/<skill-name>/`
+   - ensure the package directory name matches the `name` frontmatter value
+3. Create or update the canonical package:
+   - write `SKILL.md` first
+   - keep the frontmatter accurate and concise
+   - make the workflow explicit, actionable, and self-contained
+4. Register the package in the repository inventory:
+   - add the package to `catalog/skills.json`
+   - add it to the appropriate collection file if it belongs in a bundle
+   - update `README.md` so the package list, counts, and usage examples stay current
+5. Refresh generated outputs:
+   - run `./scripts/build-adapters.sh`
+   - run `./scripts/validate-catalog.sh`
+6. Verify the new package actually exists:
+   - confirm `packages/software-development/<skill-name>/SKILL.md`
+   - confirm generated adapter files and prompt files were created
+7. Commit and push:
+   - inspect `git status`
+   - commit the change with a conventional message
+   - push to the current upstream branch
+
+## Git Safety
+
+- Never overwrite unrelated changes
+- Never force push unless the user explicitly asks
+- Never commit secrets copied from the source repo
+- If the source skill is incomplete or ambiguous, stop and ask for clarification instead of guessing
+
+## Verification
+
+- `./scripts/build-adapters.sh` completes successfully
+- `./scripts/validate-catalog.sh` passes
+- `git status` shows only the intended package, catalog, README, and generated files
+- `git push` succeeds to the expected remote

package/packages/software-development/add-to-my-skills/adapters/windsurf/rules/add-to-my-skills.md

@@ -0,0 +1,77 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+description: "Copy a newly created skill into this catalog, refresh manifests, and publish the change."
+---
+
+
+# Add to My Skills
+
+Use this skill when a skill was created in another repository and needs to be copied into this catalog as a first-class package.
+
+## Outcome
+
+Bring the source skill into `packages/software-development/`, register it in the catalog, refresh generated docs and adapters, and publish the change with a git commit and push.
+
+## When to Use
+
+- The user created a new `SKILL.md` in another repo and wants it added here
+- The user wants this catalog to become the canonical home for that skill
+- The user wants the README, generated manifests, commit, and push handled in one pass
+
+## Clarify Before Acting
+
+If any of these are unclear, ask up to 3 questions in one batch before editing:
+
+- Source repo or source skill path
+- Final skill name if it should differ from the source
+- Destination branch or remote if the push target is unclear
+
+Default assumptions when not specified:
+
+- Copy the source skill as a new canonical package in `packages/software-development/<skill-name>/`
+- Keep the source skill name unless the user asks to rename it
+- Use this repository as the destination
+- Commit with a conventional commit message and push to the current branch's upstream
+
+## Workflow
+
+1. Inspect the source skill:
+   - locate the source `SKILL.md`
+   - copy any supporting `references/`, `scripts/`, or `assets/` files that the skill needs
+   - note any repo-specific assumptions that need to be rewritten for this catalog
+2. Choose the package location:
+   - default to `packages/software-development/<skill-name>/`
+   - ensure the package directory name matches the `name` frontmatter value
+3. Create or update the canonical package:
+   - write `SKILL.md` first
+   - keep the frontmatter accurate and concise
+   - make the workflow explicit, actionable, and self-contained
+4. Register the package in the repository inventory:
+   - add the package to `catalog/skills.json`
+   - add it to the appropriate collection file if it belongs in a bundle
+   - update `README.md` so the package list, counts, and usage examples stay current
+5. Refresh generated outputs:
+   - run `./scripts/build-adapters.sh`
+   - run `./scripts/validate-catalog.sh`
+6. Verify the new package actually exists:
+   - confirm `packages/software-development/<skill-name>/SKILL.md`
+   - confirm generated adapter files and prompt files were created
+7. Commit and push:
+   - inspect `git status`
+   - commit the change with a conventional message
+   - push to the current upstream branch
+
+## Git Safety
+
+- Never overwrite unrelated changes
+- Never force push unless the user explicitly asks
+- Never commit secrets copied from the source repo
+- If the source skill is incomplete or ambiguous, stop and ask for clarification instead of guessing
+
+## Verification
+
+- `./scripts/build-adapters.sh` completes successfully
+- `./scripts/validate-catalog.sh` passes
+- `git status` shows only the intended package, catalog, README, and generated files
+- `git push` succeeds to the expected remote

package/packages/software-development/ai-tools-setup/adapters/kiro/steering/ai-tools-setup.md

@@ -0,0 +1,263 @@
+<!-- Generated by scripts/build-adapters.sh. Do not edit directly. -->
+
+---
+inclusion: manual
+description: "Install, repair, and measure the RTK+ICM+Vox AI development toolkit. Fixes missing hooks and MCP config, and shows a weekly effectiveness digest of token savings and memory health."
+---
+
+
+# AI Tools Setup — RTK + ICM + Vox
+
+Install, repair, and measure the RTK+ICM+Vox toolkit for Claude Code.
+
+## What This Skill Does
+
+| Mode | When to use |
+|------|-------------|
+| **Setup** | First install on a new machine |
+| **Repair** | Something broke — hooks missing, MCP not loading |
+| **Digest** | Weekly check: token savings, memory health, voice stats |
+
+## Tools in the Bundle
+
+| Tool | Version | Purpose |
+|------|---------|---------|
+| **RTK** | latest | Compresses CLI output by ~89% before it reaches the model |
+| **ICM** | latest | Persistent SQLite memory across sessions (knowledge graph + hybrid search) |
+| **Vox** | latest | Spoken task notifications via local TTS — zero API calls |
+
+---
+
+## Step 1: Detect Current State
+
+Run this to see what is installed and what is missing:
+
+```bash
+echo "=== Binary check ===" && \
+  (rtk --version 2>/dev/null && echo "RTK: ok") || echo "RTK: MISSING" && \
+  (icm --version 2>/dev/null && echo "ICM: ok") || echo "ICM: MISSING" && \
+  (vox --version 2>/dev/null && echo "Vox: ok") || echo "Vox: MISSING"
+
+echo "=== RTK hook ===" && \
+  grep -c '"rtk hook claude"' ~/.claude/settings.json 2>/dev/null \
+    && echo "RTK hook: ok" || echo "RTK hook: MISSING"
+
+echo "=== ICM hooks ===" && \
+  grep -c '"icm hook' ~/.claude/settings.json 2>/dev/null \
+    && echo "ICM hooks: ok" || echo "ICM hooks: MISSING"
+
+echo "=== ICM MCP ===" && \
+  python3 -c "import json; d=json.load(open(open('$HOME/.claude.json').name)); print('ICM MCP: ok' if 'icm' in d.get('mcpServers',{}) else 'ICM MCP: MISSING')" 2>/dev/null || echo "ICM MCP: MISSING"
+
+echo "=== Vox MCP ===" && \
+  python3 -c "import json; d=json.load(open(open('$HOME/.claude.json').name)); print('Vox MCP: ok' if 'vox' in d.get('mcpServers',{}) else 'Vox MCP: MISSING')" 2>/dev/null || echo "Vox MCP: MISSING"
+
+echo "=== ICM CLAUDE.md ===" && \
+  grep -c 'icm:start' ~/.claude/CLAUDE.md 2>/dev/null \
+    && echo "ICM CLAUDE.md: ok" || echo "ICM CLAUDE.md: MISSING"
+```
+
+Read the output and determine which of the following repair steps are needed.
+
+---
+
+## Step 2: Install Missing Binaries
+
+Only run for tools that showed MISSING above.
+
+**RTK:**
+```bash
+brew install rtk
+rtk --version
+```
+
+**ICM:**
+```bash
+brew install rtk-ai/tap/icm
+icm --version
+```
+
+**Vox:**
+```bash
+brew install rtk-ai/tap/vox
+vox --version
+```
+
+---
+
+## Step 3: Repair Hooks
+
+### RTK hook missing
+
+Add the `PreToolUse` RTK hook to `~/.claude/settings.json`. Read the file first, then add inside the existing `"hooks"` block (or create one):
+
+```json
+"PreToolUse": [
+  {
+    "matcher": "Bash",
+    "hooks": [{ "type": "command", "command": "rtk hook claude" }]
+  }
+]
+```
+
+Then verify: `grep -c '"rtk hook claude"' ~/.claude/settings.json`
+
+### ICM hooks missing
+
+Run:
+```bash
+icm init --mode hook
+```
+
+This adds `PreToolUse`, `PostToolUse`, `PreCompact`, `UserPromptSubmit`, `SessionStart`, `SessionEnd` hooks automatically.
+
+### Vox Stop hook missing
+
+Run:
+```bash
+vox init --mode cli
+```
+
+---
+
+## Step 4: Repair MCP Servers
+
+### ICM MCP missing
+
+```bash
+icm init --mode mcp
+```
+
+### Vox MCP missing
+
+```bash
+vox init --mode mcp
+```
+
+Verify both by checking `~/.claude.json`:
+```bash
+python3 -c "import json; d=json.load(open('$HOME/.claude.json')); print(list(d.get('mcpServers',{}).keys()))"
+```
+
+---
+
+## Step 5: Repair CLAUDE.md Instructions
+
+If ICM instructions are missing from `~/.claude/CLAUDE.md`:
+
+```bash
+icm init --mode cli
+```
+
+Then move the block from wherever `icm init` placed it into `~/.claude/CLAUDE.md` (the global file), and remove it from any project-local files.
+
+---
+
+## Step 6: Effectiveness Digest
+
+Run this report to see how the toolkit is performing. Good to run weekly.
+
+```bash
+echo "=============================="
+echo "  AI TOOLS EFFECTIVENESS"
+echo "=============================="
+echo ""
+echo "--- RTK: Token Savings ---"
+rtk gain 2>/dev/null || echo "No data yet (run some commands first)"
+echo ""
+echo "--- ICM: Memory Health ---"
+icm health 2>/dev/null || echo "No memories yet"
+echo ""
+echo "--- ICM: Topics ---"
+icm topics 2>/dev/null || echo "No topics yet"
+echo ""
+echo "--- Vox: Usage ---"
+vox stats 2>/dev/null || echo "No stats yet"
+echo ""
+echo "=============================="
+```
+
+### What healthy output looks like
+
+- **RTK**: `Tokens saved: 5M+ (85%+)` across `500+ commands` — if savings are low, run `rtk discover` to find uncovered commands
+- **ICM**: Topics like `decisions-*`, `errors-resolved`, `preferences` with recent timestamps — if empty, start storing manually with `icm store`
+- **Vox**: Non-zero speak count means the Stop hook fired
+
+---
+
+## Step 7 (Optional): Schedule a Weekly Digest
+
+To get a weekly automated report without having to remember to run this skill:
+
+```bash
+# Create a weekly digest script
+cat > ~/ai-tools-digest.sh << 'EOF'
+#!/bin/bash
+echo "=== Weekly AI Tools Digest — $(date) ===" | tee -a ~/ai-tools-digest.log
+echo "" | tee -a ~/ai-tools-digest.log
+rtk gain 2>/dev/null | tee -a ~/ai-tools-digest.log
+echo "" | tee -a ~/ai-tools-digest.log
+icm health 2>/dev/null | tee -a ~/ai-tools-digest.log
+echo "" | tee -a ~/ai-tools-digest.log
+icm topics 2>/dev/null | tee -a ~/ai-tools-digest.log
+# Speak the summary if Vox is available
+vox "Weekly digest complete. Check your log." 2>/dev/null || true
+EOF
+chmod +x ~/ai-tools-digest.sh
+```
+
+Then set up a weekly launchd job (macOS):
+
+```bash
+cat > ~/Library/LaunchAgents/com.oleg.ai-tools-digest.plist << 'EOF'
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+  <key>Label</key>
+  <string>com.oleg.ai-tools-digest</string>
+  <key>ProgramArguments</key>
+  <array>
+    <string>/bin/bash</string>
+    <string>/Users/oleg.koval/ai-tools-digest.sh</string>
+  </array>
+  <key>StartCalendarInterval</key>
+  <dict>
+    <key>Weekday</key>
+    <integer>1</integer>
+    <key>Hour</key>
+    <integer>9</integer>
+    <key>Minute</key>
+    <integer>0</integer>
+  </dict>
+  <key>StandardOutPath</key>
+  <string>/tmp/ai-tools-digest.log</string>
+  <key>StandardErrorPath</key>
+  <string>/tmp/ai-tools-digest.err</string>
+</dict>
+</plist>
+EOF
+
+launchctl load ~/Library/LaunchAgents/com.oleg.ai-tools-digest.plist
+echo "Weekly digest scheduled for Mondays at 9am"
+```
+
+To view the digest log anytime: `cat ~/ai-tools-digest.log`
+
+To unload: `launchctl unload ~/Library/LaunchAgents/com.oleg.ai-tools-digest.plist`
+
+---
+
+## Quick Reference
+
+| Command | What it does |
+|---------|-------------|
+| `rtk gain` | Total tokens saved to date |
+| `rtk discover` | Find commands not yet covered by RTK |
+| `icm topics` | List all memory topic buckets |
+| `icm health` | Memory hygiene — stale, redundant, decay stats |
+| `icm recall "query"` | Search memories semantically |
+| `icm store -t topic -c "content" -i high` | Store a memory manually |
+| `vox "text"` | Speak text immediately |
+| `vox stats` | Usage stats for the Vox backend |
+| `cat ~/ai-tools-digest.log` | View scheduled digest history |