/Upgrade

name: Upgrade
version: 1.1.26
description: "Improve LifeOS from what the best practitioners are shipping around AI harnesses — Anthropic first (changelogs, docs, releases), then trusted creators, trending repos, and the system's own reflections — extracting concrete techniques and filtering them against verified current state so nothing already-done or rejected is re-recommended. USE WHEN upgrade, system upgrade, check Anthropic, new Claude features, algorithm upgrade, LifeOS upgrade, mine reflections."

Customization

**Before executing, check for user customizations at:** `~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Upgrade/`

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.

🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

**You MUST send this notification BEFORE doing anything else when this skill is invoked.**

1. **Send voice notification:**

   curl -s -X POST http://localhost:31337/notify \
     -H "Content-Type: application/json" \
     -d '{"message": "Running the WORKFLOWNAME workflow in the Upgrade skill to ACTION"}' \
     > /dev/null 2>&1 &

2. **Output text notification:**

   Running the **WorkflowName** workflow in the **Upgrade** skill to ACTION...

Upgrade

**The ideal state:** the system knows what the best people on the internet are saying, doing, and implementing around AI harnesses — Anthropic most importantly — and its configuration improves from that input. A run is done when every worthwhile new technique from the monitored sources has been extracted (quoted, mapped to a specific LifeOS file or component), every candidate has been checked against what the system already has or already decided, and the result reaches the user as tiered, evidence-backed recommendations they can act on immediately.

Signal comes from two directions, and a good run uses both: **external** (what Anthropic and the best practitioners are shipping) and **internal** (what the system's own reflections and failure history say is weak). The most valuable recommendations are usually where the two agree.

Workflow Routing

| Workflow | Trigger | File | |----------|---------|------| | **Upgrade** | "check for upgrades", "check sources", "any updates", "check Anthropic", "check YouTube", "upgrade" | `Workflows/Upgrade.md` | | **MineReflections** | "mine reflections", "check reflections", "what have we learned", "internal improvements", "reflection insights" | `Workflows/MineReflections.md` | | **AlgorithmUpgrade** | "algorithm upgrade", "upgrade algorithm", "improve the algorithm", "algorithm improvements", "fix the algorithm" | `Workflows/AlgorithmUpgrade.md` | | **ResearchUpgrade** | "research this upgrade", "deep dive on [feature]", "further research" | `Workflows/ResearchUpgrade.md` | | **FindSources** | "find upgrade sources", "find new sources", "discover channels" | `Workflows/FindSources.md` |

<!-- public issue #1750, @xmasyx — the TwitterBookmarks routing row was removed here. Workflows/TwitterBookmarks.md is release-excluded (it depends on the private _X skill), so on a public install the row advertised a route to a file that does not ship. The workflow file itself is untouched and can still be run directly; bookmark sweeps route through _X PullBookmarks (`/tb`) and the BookmarkSweep launchd service. -->

**Default workflow:** a bare "upgrade" or "check for upgrades" runs **Upgrade** (which includes reflection mining).

The Contract (what every recommendation must satisfy)

1. **Grounded in current state.** No recommendation without a Prior Status tag (🆕/🔶/💬/🚫) backed by file:line evidence gathered *this run*. Already-implemented items go to Skipped Content with evidence — that's the proof the prior-state check ran. Rejected ideas (`MEMORY/KNOWLEDGE/REJECTED/`) only resurface with a named reason the context changed. **This standard binds internal synthesis inference exactly as it binds external findings:** before any absence-claim earns a 🆕/CRITICAL tag, the thing claimed missing must be positively probed this run (grep/read for it), never inferred. A reported absence you did not check is a fabricated finding — the 2026-08-06 scan shipped a false CRITICAL across seven skills by grepping `context: fork` while never grepping `background:`. Internal inference is exempt from nothing. 2. **A technique, not a pointer.** Quote or code-block the actual content; name the exact LifeOS file or component it improves; include What It Is and How It Helps LifeOS (≤2 concrete sentences each). The test: if "show me the technique" has no answer, it doesn't ship. Content with nothing extractable goes to Skipped with a reason — skip boldly rather than dilute. 3. **Won't break what exists.** Check backward compatibility against current skills, hooks, and workflows before recommending adoption. 4. **Formatted per the contract.** `References/OutputFormat.md` is the single source of truth for section order, Prior Status legend, table columns, and hard rules.

Sources & Tools

| Surface | Contract | |---------|----------| | Anthropic (30+ sources: blog, changelogs, GitHub repos, docs) | `bun Tools/Anthropic.ts` — diffs against `State/last-check.json`, updates it itself | | YouTube channels | Config: `youtube-channels.json` (base) + user copy in CUSTOMIZATIONS. List: `yt-dlp --flat-playlist --dump-json 'https://www.youtube.com/@HANDLE/videos'`. Transcript: `bun ~/.claude/LIFEOS/TOOLS/GetTranscript.ts '<url>'`. Seen-state: `State/youtube-videos.json` — update after processing | | GitHub trending | Config: `github_trending` block in user `user-sources.json`. `gh api 'search/repositories?q=QUERY+created:>DATE+stars:>N&sort=...&per_page=3'`. Seen-state: `State/github-trending.json` — merge, never drop entries | | Custom sources | `user-sources.json` in CUSTOMIZATIONS — f