docs: scope the formatting-skills migration to installs with the channel wired

/update-nanoclaw is agent-driven; an unscoped 're-run /add-whatsapp'
would install the whole Baileys adapter on channel-free installs.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01A2YZQDTw9TQrH3m8NBtVAW

.claude/skills/add-slack/SKILL.md

@@ -18,6 +18,7 @@ Skip to **Credentials** if all of these are already in place:
 - `src/channels/slack.ts` exists
 - `src/channels/slack-registration.test.ts` exists
 - `src/channels/index.ts` contains `import './slack.js';`
+- `container/skills/slack-formatting/SKILL.md` exists
 - `@chat-adapter/slack` is listed in `package.json` dependencies
 
 Otherwise continue. Every step below is safe to re-run.
@@ -33,8 +34,15 @@ git fetch origin channels
 ```bash
 git show origin/channels:src/channels/slack.ts                 > src/channels/slack.ts
 git show origin/channels:src/channels/slack-registration.test.ts > src/channels/slack-registration.test.ts
+mkdir -p container/skills/slack-formatting
+git show origin/channels:container/skills/slack-formatting/SKILL.md > container/skills/slack-formatting/SKILL.md
 ```
 
+The `slack-formatting` container skill is part of the channel payload: it
+reaches agents via `~/.claude/skills` (synced at spawn) and teaches Slack's
+mrkdwn syntax. Trunk does not ship it — without this copy step agents send
+Slack messages with generic markdown that renders literally.
+
 ### 3. Append the self-registration import
 
 Append to `src/channels/index.ts` (skip if the line is already present):

.claude/skills/add-whatsapp/SKILL.md

@@ -20,6 +20,7 @@ Skip to **Credentials** if all of these are already in place:
 - `src/channels/whatsapp.test.ts` exists
 - `src/channels/index.ts` contains `import './whatsapp.js';`
 - `setup/whatsapp-auth.ts` and `setup/groups.ts` both exist
+- `container/skills/whatsapp-formatting/instructions.md` exists
 - `setup/index.ts`'s `STEPS` map contains both `'whatsapp-auth':` and `groups:`
 - `@whiskeysockets/baileys`, `qrcode`, `pino` are listed in `package.json` dependencies
 - `.claude/skills/add-whatsapp/scripts/wa-qr-browser.ts` exists (ships with this skill)
@@ -40,8 +41,17 @@ git show origin/channels:src/channels/whatsapp-registration.test.ts    > src/cha
 git show origin/channels:src/channels/whatsapp.test.ts                 > src/channels/whatsapp.test.ts
 git show origin/channels:setup/whatsapp-auth.ts                        > setup/whatsapp-auth.ts
 git show origin/channels:setup/groups.ts                               > setup/groups.ts
+mkdir -p container/skills/whatsapp-formatting
+git show origin/channels:container/skills/whatsapp-formatting/SKILL.md        > container/skills/whatsapp-formatting/SKILL.md
+git show origin/channels:container/skills/whatsapp-formatting/instructions.md > container/skills/whatsapp-formatting/instructions.md
 ```
 
+The `whatsapp-formatting` container skill is part of the channel payload: its
+`instructions.md` becomes the `skill-whatsapp-formatting.md` fragment in every
+group's composed CLAUDE.md (see `src/claude-md-compose.ts`), teaching agents
+WhatsApp's formatting syntax. Trunk does not ship it — without this copy step
+agents format WhatsApp messages with generic markdown that renders literally.
+
 ### 3. Append the self-registration import
 
 Append to `src/channels/index.ts` (skip if already present):

CHANGELOG.md

@@ -4,6 +4,7 @@ All notable changes to NanoClaw will be documented in this file.
 
 ## [Unreleased]
 
+- [BREAKING] **`whatsapp-formatting` and `slack-formatting` container skills moved from trunk to the `channels` branch.** They now install with their channel — `/add-whatsapp` / `/add-slack` and the setup installers copy them in — so installs without those channels stop carrying channel-specific formatting instructions in every agent's context. **Migration — only if this install has the channel wired** (check `src/channels/whatsapp.ts` / `src/channels/slack.ts`): updating removes both skills from the working tree — WhatsApp agents lose the formatting fragment from their composed CLAUDE.md on next spawn, Slack agents lose the mrkdwn skill from `~/.claude/skills`. Re-run the matching skill, `/add-whatsapp` or `/add-slack` (idempotent), to restore. Installs without the channel need nothing — do NOT run the add-skill just in case; it installs the full channel adapter.
 - **Pre-task script failures back their series off instead of spinning.** A `--script` that errors lands the occurrence as a failed run (`script-skip:error` ack → `failed` status); recurrence reads the series' trailing failed streak and re-arms at `max(cron next, now + 2·2^(n−1) min, cap 60)`; after 8 consecutive failures the series is auto-paused with a host-written note in its run log (`ncl tasks resume` revives it). A deliberate `wakeAgent:false` gate is a normal run and never backs off. Also fixed: an explicitly-addressed `<message to>` in a task fire's final text now delivers as a deliberate send (previously suppressed as a turn-reply echo → zero delivery when the agent skipped the MCP tool); identical echoes of an MCP send are dropped in the runner, where the duplication originates.
 - [BREAKING] **Scheduled tasks moved from MCP tools to `ncl tasks`.** The six scheduling MCP tools are no longer exposed to agent containers; agents and operators manage tasks with `ncl tasks list/get/create/update/cancel/pause/resume/delete`. New tasks run from a per-agent-group system session rather than waking the chat session that created them, and task writes are not approval-gated inside the owning group. **Migration:** [docs/ncl-tasks-migration.md](docs/ncl-tasks-migration.md).
 - **Optional per-container resource caps.** `CONTAINER_CPU_LIMIT` and `CONTAINER_MEMORY_LIMIT` pass through to `docker run` as `--cpus` / `--memory` (`container-runner.ts`). Both empty by default — no flag added, spawn args byte-identical to today — so existing installs are unaffected. Set them to cap an agent container's CPU/memory so one agent can't monopolize the host (e.g. `CONTAINER_CPU_LIMIT=2`, `CONTAINER_MEMORY_LIMIT=8g`). Swap is intentionally not managed here: `--memory` is a hard cap on a swapless host.

CLAUDE.md

@@ -79,7 +79,7 @@ For ad-hoc queries from skills or scripts, use the in-tree wrapper rather than t
 | `src/channels/` | Channel adapter infra (registry, Chat SDK bridge); specific channel adapters are skill-installed from the `channels` branch |
 | `src/providers/` | Host-side provider container-config (`claude` baked in; `opencode` etc. installed from the `providers` branch) |
 | `container/agent-runner/src/` | Agent-runner: poll loop, formatter, provider abstraction, MCP tools, destinations |
-| `container/skills/` | Container skills mounted into every agent session (`agent-browser`, `frontend-engineer`, `onecli-gateway`, `self-customize`, `slack-formatting`, `vercel-cli`, `welcome`, `whatsapp-formatting`) |
+| `container/skills/` | Container skills mounted into every agent session (`agent-browser`, `frontend-engineer`, `onecli-gateway`, `self-customize`, `vercel-cli`, `welcome`; channel-specific skills like `slack-formatting` and `whatsapp-formatting` install with their channel) |
 | `groups/<folder>/` | Per-agent-group filesystem (CLAUDE.md, skills) — agent-runner source is a shared read-only mount, not copied per group |
 | `scripts/init-first-agent.ts` | Bootstrap the first DM-wired agent (used by `/init-first-agent` skill) |
 | `migrate-v2.sh` + `setup/migrate-v2/` | v1→v2 migration. Standalone script: `bash migrate-v2.sh`. Seeds DB, copies groups/sessions, installs channels, builds container, offers service switchover, then hands off to `/migrate-from-v1` skill for owner setup and CLAUDE.md cleanup. See [docs/migration-dev.md](docs/migration-dev.md). |
@@ -183,7 +183,7 @@ Four types of skills. See [CONTRIBUTING.md](CONTRIBUTING.md) for the full taxono
 - **Channel/provider install skills** — copy the relevant module(s) in from the `channels` or `providers` branch, wire imports, install pinned deps (e.g. `/add-discord`, `/add-slack`, `/add-whatsapp`, `/add-opencode`).
 - **Utility skills** — ship code files alongside `SKILL.md` (e.g. a `scripts/` CLI or helper).
 - **Operational skills** — instruction-only workflows (`/setup`, `/debug`, `/customize`, `/init-first-agent`, `/manage-channels`, `/init-onecli`, `/update-nanoclaw`).
-- **Container skills** — loaded inside agent containers at runtime (`container/skills/`: `agent-browser`, `frontend-engineer`, `onecli-gateway`, `self-customize`, `slack-formatting`, `vercel-cli`, `welcome`, `whatsapp-formatting`).
+- **Container skills** — loaded inside agent containers at runtime (`container/skills/`: `agent-browser`, `frontend-engineer`, `onecli-gateway`, `self-customize`, `vercel-cli`, `welcome`; channel-specific skills like `slack-formatting` and `whatsapp-formatting` are copied in by their `/add-<channel>` skill).
 
 | Skill | When to Use |
 |-------|-------------|

CONTRIBUTING.md

@@ -92,7 +92,7 @@ Skills that run inside the agent container, not on the host. These teach the Nan
 
 **Location:** `container/skills/<name>/`
 
-**Examples:** `agent-browser` (web browsing), `frontend-engineer`, `onecli-gateway` (OneCLI proxy usage), `self-customize`, `slack-formatting` (Slack mrkdwn syntax), `vercel-cli`, `welcome`, `whatsapp-formatting`
+**Examples:** `agent-browser` (web browsing), `frontend-engineer`, `onecli-gateway` (OneCLI proxy usage), `self-customize`, `vercel-cli`, `welcome`; channel-specific: `slack-formatting` (Slack mrkdwn syntax) and `whatsapp-formatting` (channels branch; installed by `/add-slack` / `/add-whatsapp`)
 
 **Key difference:** You never invoke these from a coding-agent session on the host, the way you run `/setup` or `/update-nanoclaw` in Claude Code/Codex/OpenCode. They're mounted into the sandbox and loaded by the NanoClaw agent itself, shaping how it behaves when you chat with it.
 

container/skills/agent-browser/SKILL.md

@@ -92,6 +92,41 @@ agent-browser wait --url "**/dashboard"    # Wait for URL pattern
 agent-browser wait --load networkidle      # Wait for network idle
 ```
 
+### Waiting for a custom condition — ALWAYS bound it
+
+Prefer the built-in `wait` subcommands above. Only fall back to `eval`-polling
+when you must wait on a custom JS condition (e.g. a spinner disappearing or a
+"Send" button re-enabling in a chat UI).
+
+**Never write an unbounded wait loop.** A bare `until … do sleep; done` that
+polls a page condition will loop *forever* if the condition never becomes true
+(page failed to load, selector changed, network stalled). That does not just
+fail the command — it wedges the entire agent turn: the runner keeps the model
+stream open, later messages get silently swallowed, and the container can hang
+for hours without the host's stuck-detection firing.
+
+Always cap the wait with BOTH a wall-clock `timeout` and a max-attempts counter,
+and always exit the loop (never leave a `sleep` loop as the last thing running):
+
+```bash
+# Bounded wait: succeeds when the condition is met, gives up after ~90s.
+timeout 90 bash -c '
+  for i in $(seq 1 30); do
+    if agent-browser eval "document.querySelector(\".loading\") === null" 2>/dev/null | grep -q true; then
+      echo READY; exit 0
+    fi
+    sleep 3
+  done
+  echo TIMEOUT; exit 1
+'
+# Check the exit status / output: on TIMEOUT, snapshot the page and decide —
+# do NOT re-enter another unbounded wait.
+```
+
+If the wait times out, treat it as a real failure: take a `snapshot -i` or
+`screenshot` to see the actual page state, report what you found, and move on.
+Retrying the same unbounded wait is what causes the hang.
+
 ### Semantic locators (alternative to refs)
 
 ```bash

container/skills/slack-formatting/SKILL.md

@@ -1,94 +0,0 @@
----
-name: slack-formatting
-description: Format messages for Slack using mrkdwn syntax. Use when responding to Slack channels (folder starts with "slack_" or JID contains slack identifiers).
----
-
-# Slack Message Formatting (mrkdwn)
-
-When responding to Slack channels, use Slack's mrkdwn syntax instead of standard Markdown.
-
-## How to detect Slack context
-
-Check your group folder name or workspace path:
-- Folder starts with `slack_` (e.g., `slack_engineering`, `slack_general`)
-- Or check `/workspace/group/` path for `slack_` prefix
-
-## Formatting reference
-
-### Text styles
-
-| Style | Syntax | Example |
-|-------|--------|---------|
-| Bold | `*text*` | *bold text* |
-| Italic | `_text_` | _italic text_ |
-| Strikethrough | `~text~` | ~strikethrough~ |
-| Code (inline) | `` `code` `` | `inline code` |
-| Code block | ` ```code``` ` | Multi-line code |
-
-### Links and mentions
-
-```
-<https://example.com|Link text>     # Named link
-<https://example.com>                # Auto-linked URL
-<@U1234567890>                       # Mention user by ID
-<#C1234567890>                       # Mention channel by ID
-<!here>                              # @here
-<!channel>                           # @channel
-```
-
-### Lists
-
-Slack supports simple bullet lists but NOT numbered lists:
-
-```
-• First item
-• Second item
-• Third item
-```
-
-Use `•` (bullet character) or `- ` or `* ` for bullets.
-
-### Block quotes
-
-```
-> This is a block quote
-> It can span multiple lines
-```
-
-### Emoji
-
-Use standard emoji shortcodes: `:white_check_mark:`, `:x:`, `:rocket:`, `:tada:`
-
-## What NOT to use
-
-- **NO** `##` headings (use `*Bold text*` for headers instead)
-- **NO** `**double asterisks**` for bold (use `*single asterisks*`)
-- **NO** `[text](url)` links (use `<url|text>` instead)
-- **NO** `1.` numbered lists (use bullets with numbers: `• 1. First`)
-- **NO** tables (use code blocks or plain text alignment)
-- **NO** `---` horizontal rules
-
-## Example message
-
-```
-*Daily Standup Summary*
-
-_March 21, 2026_
-
-• *Completed:* Fixed authentication bug in login flow
-• *In Progress:* Building new dashboard widgets
-• *Blocked:* Waiting on API access from DevOps
-
-> Next sync: Monday 10am
-
-:white_check_mark: All tests passing | <https://ci.example.com/builds/123|View Build>
-```
-
-## Quick rules
-
-1. Use `*bold*` not `**bold**`
-2. Use `<url|text>` not `[text](url)`
-3. Use `•` bullets, avoid numbered lists
-4. Use `:emoji:` shortcodes
-5. Quote blocks with `>`
-6. Skip headings — use bold text instead

container/skills/whatsapp-formatting/SKILL.md

@@ -1,61 +0,0 @@
----
-name: whatsapp-formatting
-description: Format messages for WhatsApp, including mentions that render as real WhatsApp tags. Use when responding in a WhatsApp conversation (platform_id / chatJid ends with @s.whatsapp.net or @g.us).
----
-
-# WhatsApp Message Formatting
-
-WhatsApp uses its own lightweight markup and a phone-number-based mention syntax. The host's WhatsApp adapter (Baileys) handles markdown conversion automatically, but **mentions are only protocol-level mentions if you use the right syntax** — otherwise they render as plain text and don't notify the recipient.
-
-## How to detect WhatsApp context
-
-You're in a WhatsApp conversation when any of these are true:
-- The chat JID / platform id ends with `@s.whatsapp.net` (1-on-1 DM)
-- The chat JID / platform id ends with `@g.us` (group)
-- Your inbound message metadata has `chatJid` matching the above
-
-## Mentions — the important part
-
-To tag a user so their name appears **bold and clickable** in WhatsApp and they get a push notification, write the `@` followed by their phone number digits (no `+`, no spaces, no display name):
-
-```
-@15551234567 can you confirm?
-```
-
-The adapter scans your outgoing text for `@<digits>` (5–15 digits, optional leading `+` is stripped) and tells WhatsApp to render them as real mention tags.
-
-**The sender's phone JID is always in your inbound message metadata.** When a user writes to you, inbound `content.sender` looks like `15551234567@s.whatsapp.net`. The part before the `@` is exactly what you put after `@` when tagging them back.
-
-### Wrong vs right
-
-| You write | What recipients see |
-|-----------|---------------------|
-| `@Adam can you...` | Plain text `@Adam`. No tag, no notification. |
-| `@15551234567 can you...` | Bold/blue **@Adam** (or whatever name they're saved as), notification fires. |
-| `@+15551234567 ...` | Same as above — adapter strips the `+`. |
-
-### Picking who to tag
-
-- In a DM, there's no real need to tag the recipient (they already see every message), but tagging still works if you want emphasis.
-- In a group, look at the `participants` / inbound `content.sender` to find the JID of the person you mean. Don't guess from display names — pushNames can collide and are not reliable.
-- If you don't know the JID, just refer to the person by name in plain prose. Don't write `@<name>` — it won't tag and it will look like a tag that failed.
-
-## Text styles
-
-WhatsApp uses single-character delimiters, *not* doubled like standard Markdown.
-
-| Style | Syntax | Renders as |
-|-------|--------|------------|
-| Bold | `*bold*` | **bold** |
-| Italic | `_italic_` | *italic* |
-| Strikethrough | `~strike~` | ~strike~ |
-| Monospace | `` `code` `` | `code` |
-| Block monospace | ```` ```block``` ```` | preformatted block |
-
-The adapter converts standard Markdown (`**bold**`, `[link](url)`, `# heading`) to the WhatsApp-native form automatically, so you don't have to think about it — but be aware that single asterisks become italics, not bold.
-
-## What not to do
-
-- Don't write `<@U123>` (that's Slack), `<@!123>` (Discord), or any other channel's mention syntax.
-- Don't paste a full JID like `@15551234567@s.whatsapp.net` in the text — only the digits before the JID's `@` go after your `@`.
-- Don't try to tag display names. WhatsApp has no display-name-based mention API.

container/skills/whatsapp-formatting/instructions.md

@@ -1,19 +0,0 @@
-## WhatsApp mentions — always use phone digits
-
-When you are replying in a WhatsApp conversation (the inbound message's `chatJid` ends with `@s.whatsapp.net` for a DM or `@g.us` for a group), and you want to tag a person so their name appears **bold and clickable** with a push notification, write `@` followed by their phone-number digits — never the display name.
-
-**The sender's phone JID is in your inbound message metadata** at `content.sender` (e.g. `15551234567@s.whatsapp.net`). The part before the `@` is exactly what you put after `@` when tagging them.
-
-| You write | What recipients see |
-|-----------|---------------------|
-| `@Adam, can you...` | Plain text. No tag, no notification. |
-| `@15551234567, can you...` | Bold/blue **@Adam** (whatever name they're saved as), notification fires. |
-| `@+15551234567 ...` | Same as above — the adapter strips the `+` automatically. |
-
-The host adapter scans your outbound text for `@<5–15 digits>` (with optional leading `+`) and tells WhatsApp to render those as real mention tags. If the digits aren't in the text, the tag doesn't render — no exceptions.
-
-### In groups
-
-Tag the person you're addressing using their JID from inbound metadata (look at the most recent message from them). Don't guess — pushNames collide and aren't reliable.
-
-If you don't know someone's JID, refer to them by name in plain prose. Do not write `@<displayname>` hoping it works.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "nanoclaw",
-  "version": "2.1.43",
+  "version": "2.1.44",
   "description": "Personal Claude assistant. Lightweight, secure, customizable.",
   "type": "module",
   "packageManager": "pnpm@10.33.0",

repo-tokens/badge.svg

@@ -1,5 +1,5 @@
-<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="224k tokens, 112% of context window">
-  <title>224k tokens, 112% of context window</title>
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="90" height="20" role="img" aria-label="225k tokens, 113% of context window">
+  <title>225k tokens, 113% of context window</title>
   <linearGradient id="s" x2="0" y2="100%">
     <stop offset="0" stop-color="#bbb" stop-opacity=".1"/>
     <stop offset="1" stop-opacity=".1"/>
@@ -15,8 +15,8 @@
       <g fill="#fff" text-anchor="middle" font-family="Verdana,Geneva,DejaVu Sans,sans-serif" font-size="11">
         <text aria-hidden="true" x="26" y="15" fill="#010101" fill-opacity=".3">tokens</text>
         <text x="26" y="14">tokens</text>
-        <text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">224k</text>
-        <text x="71" y="14">224k</text>
+        <text aria-hidden="true" x="71" y="15" fill="#010101" fill-opacity=".3">225k</text>
+        <text x="71" y="14">225k</text>
       </g>
     </g>
   </a>

setup/add-slack.sh

@@ -51,6 +51,7 @@ fi
 
 need_install() {
   [ ! -f src/channels/slack.ts ] && return 0
+  [ ! -f container/skills/slack-formatting/SKILL.md ] && return 0
   ! grep -q "^import './slack.js';" src/channels/index.ts 2>/dev/null && return 0
   return 1
 }
@@ -67,6 +68,10 @@ if need_install; then
   log "Copying adapter from ${CHANNELS_BRANCH}…"
   git show "${CHANNELS_BRANCH}:src/channels/slack.ts" > src/channels/slack.ts
 
+  # Slack formatting container skill — reaches agents via ~/.claude/skills.
+  mkdir -p container/skills/slack-formatting
+  git show "${CHANNELS_BRANCH}:container/skills/slack-formatting/SKILL.md" > container/skills/slack-formatting/SKILL.md
+
   # Append self-registration import if missing.
   if ! grep -q "^import './slack.js';" src/channels/index.ts; then
     echo "import './slack.js';" >> src/channels/index.ts

setup/add-whatsapp.sh

@@ -43,6 +43,7 @@ log() { echo "[add-whatsapp] $*" >&2; }
 need_install() {
   [ ! -f src/channels/whatsapp.ts ] && return 0
   [ ! -f setup/groups.ts ] && return 0
+  [ ! -f container/skills/whatsapp-formatting/instructions.md ] && return 0
   ! grep -q "^import './whatsapp.js';" src/channels/index.ts 2>/dev/null && return 0
   ! grep -q "'whatsapp-auth':" setup/index.ts 2>/dev/null && return 0
   ! grep -q "^  groups:" setup/index.ts 2>/dev/null && return 0
@@ -64,6 +65,12 @@ if need_install; then
   git show "${CHANNELS_BRANCH}:src/channels/whatsapp.ts" > src/channels/whatsapp.ts
   git show "${CHANNELS_BRANCH}:setup/groups.ts"          > setup/groups.ts
 
+  # WhatsApp formatting container skill — feeds the composed CLAUDE.md
+  # (skill-whatsapp-formatting.md fragment) and ~/.claude/skills.
+  mkdir -p container/skills/whatsapp-formatting
+  git show "${CHANNELS_BRANCH}:container/skills/whatsapp-formatting/SKILL.md"        > container/skills/whatsapp-formatting/SKILL.md
+  git show "${CHANNELS_BRANCH}:container/skills/whatsapp-formatting/instructions.md" > container/skills/whatsapp-formatting/instructions.md
+
   # Append self-registration import if missing.
   if ! grep -q "^import './whatsapp.js';" src/channels/index.ts; then
     echo "import './whatsapp.js';" >> src/channels/index.ts

setup/install-slack.sh

@@ -15,6 +15,7 @@ echo "=== NANOCLAW SETUP: INSTALL_SLACK ==="
 
 needs_install=false
 [[ -f src/channels/slack.ts ]] || needs_install=true
+[[ -f container/skills/slack-formatting/SKILL.md ]] || needs_install=true
 grep -q "import './slack.js';" src/channels/index.ts || needs_install=true
 grep -q '"@chat-adapter/slack"' package.json || needs_install=true
 [[ -d node_modules/@chat-adapter/slack ]] || needs_install=true
@@ -30,6 +31,8 @@ git fetch origin channels
 
 echo "STEP: copy-files"
 git show origin/channels:src/channels/slack.ts > src/channels/slack.ts
+mkdir -p container/skills/slack-formatting
+git show origin/channels:container/skills/slack-formatting/SKILL.md > container/skills/slack-formatting/SKILL.md
 
 echo "STEP: register-import"
 if ! grep -q "import './slack.js';" src/channels/index.ts; then

setup/install-whatsapp.sh

@@ -20,6 +20,8 @@ CHANNEL_FILES=(
   src/channels/whatsapp.ts
   setup/whatsapp-auth.ts
   setup/groups.ts
+  container/skills/whatsapp-formatting/SKILL.md
+  container/skills/whatsapp-formatting/instructions.md
 )
 
 needs_install=false
@@ -45,6 +47,7 @@ git fetch origin channels
 
 echo "STEP: copy-files"
 for f in "${CHANNEL_FILES[@]}"; do
+  mkdir -p "$(dirname "$f")"
   git show "origin/channels:$f" > "$f"
 done