/customize-rebuild
Rebuild and redeploy AIWG from local customization source — makes recent edits live
$ npx -y skills add jmagly/aiwg --skill customize-rebuild --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/customize-rebuild
Context preview
The summary Claude sees to decide when to auto-load this skill.
Rebuild and redeploy AIWG from local customization source — makes recent edits live
SKILL.md
customize-rebuild.SKILL.mdnamespace: aiwg
name: customize-rebuild
platforms: [all]
description: Rebuild and redeploy AIWG from local customization source — makes recent edits live
Customize Rebuild
You rebuild and redeploy AIWG from the user's local clone so their recent edits go live. This is the daily-driver skill for anyone in customization mode — fast, frictionless, and no jargon.
Triggers
- "apply my changes"
- "make this live" / "make it live"
- "rebuild" / "redeploy"
- "recompile"
- "push my edits live"
- "update my AIWG"
- "deploy my customizations"
Trigger Patterns Reference
| Pattern | Example | Action | |---------|---------|--------| | Apply changes | "apply my changes" | `aiwg use all` (fast path) | | Full rebuild | "rebuild everything" | `npm run build` + `aiwg use all` | | Redeploy workflow | "redeploy the current customizations" | Verify dev mode and build need, then use `aiwg use all` as the deployment step |
Behavior
When triggered:
1. **Verify customization mode is active**:
aiwg version # should show [dev] and the repo path
If not in dev mode, tell the user and offer to run `customize-setup`.
2. **Determine whether a TypeScript build is needed**:
- Check if any `.ts` files changed since last build: `git -C <edgePath> diff --name-only HEAD -- src/ '*.ts'`
- If only files in `agentic/code/` changed (agents, skills, rules, prompts) — **skip `npm run build`** and use `aiwg use all` as the deployment step
- If `src/`, `apps/web/`, or `package.json` changed — run `npm run build` first
For simplicity: if uncertain, ask "Did you change any TypeScript source files, or just agents/rules/skills?" and act accordingly. Default to the fast path (`aiwg use all` only) since most user customizations are in `agentic/code/`.
3. **Fast path** (most common — editing agents, rules, skills):
aiwg use all
4. **Full rebuild path** (when TS source changed):
npm --prefix <edgePath> run build
aiwg use all
5. **Report result** concisely:
Done — deployed X agents, Y skills, Z rules from ~/my-aiwg.
Changes are live in your next session.
Do NOT surface "npm run build" details to the user unless they asked about TypeScript changes. Just report "Done" with the deployment counts.
Examples
Example 1: Daily-use apply
**User**: "apply my changes"
**Action**: Check dev mode → `aiwg use all` (fast path, no TS changes detected)
**Response**: "Done — deployed 180 agents, 360 skills, 16 rules from ~/my-aiwg."
Example 2: After adding a rule file
**User**: "I added a rule, make it live"
**Action**: `aiwg use all` (rule files are in `agentic/code/`, no build needed)
**Response**: "Done — your new rule is live. 181 rules deployed."
Example 3: After editing TypeScript
**User**: "I changed some TypeScript source, rebuild everything"
**Action**: `npm run build` → `aiwg use all`
**Response**: "Built and deployed from ~/my-aiwg. All changes are live."
Clarification Prompts
If not in customization mode: > "It looks like AIWG isn't running from a local clone right now. Want me to set up customization mode first?"
References
- @$AIWG_ROOT/bin/aiwg.mjs — dev mode delegation logic
- @$AIWG_ROOT/src/channel/manager.mjs — `loadConfig()` for edgePath
- @$AIWG_ROOT/docs/customization/README.md — Customization guide
Read more
namespace: aiwg name: customize-rebuild platforms: [all] description: Rebuild and redeploy AIWG from local customization source — makes recent edits live
Customize Rebuild
You rebuild and redeploy AIWG from the user's local clone so their recent edits go live. This is the daily-driver skill for anyone in customization mode — fast, frictionless, and no jargon.
Triggers
- "apply my changes"
- "make this live" / "make it live"
- "rebuild" / "redeploy"
- "recompile"
- "push my edits live"
- "update my AIWG"
- "deploy my customizations"
Trigger Patterns Reference
| Pattern | Example | Action | |---------|---------|--------| | Apply changes | "apply my changes" | `aiwg use all` (fast path) | | Full rebuild | "rebuild everything" | `npm run build` + `aiwg use all` | | Redeploy workflow | "redeploy the current customizations" | Verify dev mode and build need, then use `aiwg use all` as the deployment step |
Behavior
When triggered:
1. **Verify customization mode is active**:
aiwg version # should show [dev] and the repo path
If not in dev mode, tell the user and offer to run `customize-setup`.
2. **Determine whether a TypeScript build is needed**:
- Check if any `.ts` files changed since last build: `git -C <edgePath> diff --name-only HEAD -- src/ '*.ts'`
- If only files in `agentic/code/` changed (agents, skills, rules, prompts) — **skip `npm run build`** and use `aiwg use all` as the deployment step
- If `src/`, `apps/web/`, or `package.json` changed — run `npm run build` first
For simplicity: if uncertain, ask "Did you change any TypeScript source files, or just agents/rules/skills?" and act accordingly. Default to the fast path (`aiwg use all` only) since most user customizations are in `agentic/code/`.
3. **Fast path** (most common — editing agents, rules, skills):
aiwg use all
4. **Full rebuild path** (when TS source changed):
npm --prefix <edgePath> run build aiwg use all
5. **Report result** concisely:
Done — deployed X agents, Y skills, Z rules from ~/my-aiwg. Changes are live in your next session.
Do NOT surface "npm run build" details to the user unless they asked about TypeScript changes. Just report "Done" with the deployment counts.
Examples
Example 1: Daily-use apply
**User**: "apply my changes"
**Action**: Check dev mode → `aiwg use all` (fast path, no TS changes detected)
**Response**: "Done — deployed 180 agents, 360 skills, 16 rules from ~/my-aiwg."
Example 2: After adding a rule file
**User**: "I added a rule, make it live"
**Action**: `aiwg use all` (rule files are in `agentic/code/`, no build needed)
**Response**: "Done — your new rule is live. 181 rules deployed."
Example 3: After editing TypeScript
**User**: "I changed some TypeScript source, rebuild everything"
**Action**: `npm run build` → `aiwg use all`
**Response**: "Built and deployed from ~/my-aiwg. All changes are live."
Clarification Prompts
If not in customization mode: > "It looks like AIWG isn't running from a local clone right now. Want me to set up customization mode first?"
References
- @$AIWG_ROOT/bin/aiwg.mjs — dev mode delegation logic
- @$AIWG_ROOT/src/channel/manager.mjs — `loadConfig()` for edgePath
- @$AIWG_ROOT/docs/customization/README.md — Customization guide
Multi-agent AI framework for Claude Code, Copilot, Cursor, Warp, and 6 more platforms 200+ agents, 109+ CLI commands, 400+ deployable agent/skill/command/rule artifacts, 8 core frameworks, 32 addons, and a 40-plugin Claude Code marketplace.
Repo: jmagly/aiwg
Other skills on aiwg.
- /agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Open skill - /agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Open skill - /auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Open skill - /cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
Open skill - /debug-memory
Query and manage the executable feedback debug memory
Open skill - /execute-feedback
Execute tests on generated code and iterate until passing
Open skill

