[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CASFRZSDJEXGKGQ3DN959M":3,"skill-same:01M6CASFRZSDJEXGKGQ3DN959M":84},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":78},"01M6CASFRZSDJEXGKGQ3DN959M","aiwg-refresh",null,"Update AIWG CLI and redeploy frameworks\u002Ftools to current project without leaving the session","jmagly\u002Faiwg","jmagly","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1159087?v=4","01M6C10AK8N2WCSQN11FYGTJWN","Joseph Magly","01M6C10AQ8A2RMED1Y1BSVY7NF",229,"MIT","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Faiwg-refresh\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"refresh","aiwg refresh","provider","dry-run","true","root","Redeploy","name","dry","project","frameworks","cli","channel","session","Bash","Tools","update","run","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: aiwg-refresh\nplatforms: [all]\nkernel: true\ndescription: Update AIWG CLI and redeploy frameworks\u002Ftools to current project without leaving the session\nscript:\n  entrypoint: run.sh\n  runtime: bash\n  cwd: project-root\n  argsHint: '[--update-cli] [--all] [--provider \u003Cname>] [--dry-run] [--channel \u003Cname>]'\n---\n\n> **Deterministic execution (#1267)**: this skill has a `script:` entrypoint\n> that shells out to `aiwg refresh \"$@\"`. Prefer\n> `aiwg run skill aiwg-refresh -- \u003Cflags>` when a platform supports it; on\n> platforms without a deployed command stub (e.g. hermes) invoke the CLI\n> directly. The CLI owns the deterministic execution step: version\u002Fchannel\n> resolution, CLI update, framework redeploy, provider detection, and exit\n> codes. The skill owns the agentic layer around that step: intent alignment,\n> output formatting, workspace-state reconciliation, summary, next actions,\n> gates, and recovery. Do not reimplement the refresh manually or add\n> redundant permission prompts before calling the CLI for execution.\n\n# Refresh AIWG Deployment\n\nUpdate the AIWG CLI and\u002For redeploy frameworks, agents, commands, and tools to the current\nproject without leaving the agentic session.\n\n## Use Cases\n\n- **After AIWG updates**: Get latest framework features without restarting\n- **After switching branches**: Ensure deployed content matches expectations\n- **After manual edits**: Restore canonical AIWG content\n- **Provider switch**: Redeploy for different platform (Claude → Factory)\n- **Model selection**: Redeploy with different AI models for each tier\n\n## Parameters\n\n| Flag | Description |\n|------|-------------|\n| `--update-cli` | Update AIWG CLI to latest version before redeploying |\n| `--all` | Redeploy all installed frameworks |\n| `--sdlc` | Redeploy SDLC framework only |\n| `--marketing` | Redeploy Marketing framework only |\n| `--utils` | Redeploy aiwg-utils addon only |\n| `--provider \u003Cname>` | Target platform: claude, factory, openai, cursor, warp (default: auto-detect) |\n| `--reasoning-model \u003Cname>` | Override model for reasoning agents (opus tier) |\n| `--coding-model \u003Cname>` | Override model for coding agents (sonnet tier) |\n| `--efficiency-model \u003Cname>` | Override model for efficiency agents (haiku tier) |\n| `--filter \u003Cpattern>` | Only deploy agents matching glob pattern (e.g., `*architect*`) |\n| `--filter-role \u003Crole>` | Only deploy agents of specified role: reasoning, coding, efficiency |\n| `--save` | Persist model selection to project models.json |\n| `--force` | Force redeploy even if already up-to-date |\n| `--dry-run` | Show what would be done without executing |\n\n## Execution Steps\n\nAny removal list requires explicit human review of the listed removals before execution.\nAuthorization lookup must never bypass that review, even with a receipt for other effects.\n\n### Step 1: Show Current Status\n\nRun status check and report current state:\n\n```bash\naiwg -status\n```\n\nReport:\n\n```text\nAIWG Refresh - Current Status\n==============================\n\nCLI Version: 1.2.3 (stable channel)\nWorkspace: \u002Fpath\u002Fto\u002Fproject\u002F.aiwg\n\nInstalled Frameworks:\n  - sdlc-complete v1.0.0 (58 agents, 48 commands)\n  - aiwg-utils v1.0.0 (3 agents, 25 commands)\n\nPlatform: Claude Code (.claude\u002F)\n  - Agents: 61 deployed\n  - Commands: 73 deployed\n```\n\n### Step 2: Update CLI (if --update-cli)\n\nIf `--update-cli` flag is set:\n\n```bash\naiwg -update\n```\n\nReport update status:\n\n```text\nChecking for updates...\n  Current: 1.2.3\n  Latest:  1.2.5\n\nUpdating AIWG CLI...\n✓ Updated to v1.2.5\n\nChanges in v1.2.5:\n  - New mutation-analyst agent\n  - Testing-quality addon\n  - Bug fixes\n```\n\nIf already up-to-date:\n\n```text\nAIWG CLI is up-to-date (v1.2.3)\n```\n\n### Step 3: Determine What to Redeploy\n\nBased on flags, determine scope:\n\n| Flags | Action |\n|-------|--------|\n| No flags | Show status only, prompt for action |\n| `--all` | Redeploy all installed frameworks |\n| `--sdlc` | Redeploy sdlc-complete only |\n| `--marketing` | Redeploy media-marketing-kit only |\n| `--utils` | Redeploy aiwg-utils addon only |\n| Multiple | Redeploy specified frameworks |\n\nIf no framework flags and not `--dry-run`, ask user:\n\n```text\nWhat would you like to refresh?\n\n[1] All frameworks (sdlc-complete, aiwg-utils)\n[2] SDLC framework only\n[3] Utils addon only\n[4] Just show status (no changes)\n\nChoice:\n```\n\n### Step 4: Detect Target Platform\n\nIf `--provider` not specified, auto-detect:\n\n1. Check existing deployments:\n   - `.claude\u002Fagents\u002F` exists → claude\n   - `.factory\u002Fdroids\u002F` exists → factory\n   - `.codex\u002Fagents\u002F` exists → openai\n   - `.cursor\u002Frules\u002F` exists → cursor\n\n2. If multiple detected, ask user:\n\n   ```text\n   Multiple platforms detected:\n   [1] Claude Code (.claude\u002F)\n   [2] Factory AI (.factory\u002F)\n\n   Which platform to refresh?\n   ```\n\n3. If none detected, default to claude\n\nReport:\n\n```text\nTarget platform: Claude Code\nDeployment paths:\n  - Agents: .claude\u002Fagents\u002F\n  - Commands: .claude\u002Fcommands\u002F\n```\n\n### Step 5: Execute Redeploy\n\nFor each framework to deploy:\n\n```bash\n# SDLC Framework\naiwg use sdlc --provider \u003Cplatform> --force [model-flags] [filter-flags]\n\n# Marketing Framework\naiwg use marketing --provider \u003Cplatform> --force [model-flags] [filter-flags]\n\n# Utils (included with sdlc)\n# No separate command needed\n```\n\n**Model flags** (if specified):\n- `--reasoning-model \u003Cname>` - applies to all opus-tier agents\n- `--coding-model \u003Cname>` - applies to all sonnet-tier agents\n- `--efficiency-model \u003Cname>` - applies to all haiku-tier agents\n\n**Filter flags** (if specified):\n- `--filter \u003Cpattern>` - only deploys matching agents\n- `--filter-role \u003Crole>` - only deploys agents of specified role\n\n**If `--dry-run`:**\nShow commands without executing:\n\n```text\nDry Run - Would execute:\n========================\n\n1. aiwg use sdlc --provider claude --force --reasoning-model opus-4-2\n   → Deploy 58 agents to .claude\u002Fagents\u002F (reasoning tier with opus-4-2)\n   → Deploy 48 commands to .claude\u002Fcommands\u002F\n\n2. aiwg use marketing --provider claude --force --reasoning-model opus-4-2\n   → Deploy 37 agents to .claude\u002Fagents\u002F (reasoning tier with opus-4-2)\n   → Deploy 20 commands to .claude\u002Fcommands\u002F\n\nNo changes made (dry run mode)\n```\n\n**Progress Reporting:**\n\n```text\nRefreshing AIWG Deployment\n==========================\n\n[1\u002F2] Deploying sdlc-complete...\n  → Copying 58 agents...\n  → Copying 48 commands...\n  → Copying 12 templates...\n  ✓ sdlc-complete deployed\n\n[2\u002F2] Deploying aiwg-utils...\n  → Copying 3 agents...\n  → Copying 25 commands...\n  ✓ aiwg-utils deployed\n```\n\n### Step 6: Verify Deployment\n\nAfter deployment, verify:\n\n```bash\n# Count deployed assets\nls .claude\u002Fagents\u002F*.md 2>\u002Fdev\u002Fnull | wc -l\nls .claude\u002Fcommands\u002F*.md 2>\u002Fdev\u002Fnull | wc -l\n```\n\nReport:\n\n```text\nVerification\n============\n\nDeployed Assets:\n  - Agents: 95 files\n  - Commands: 93 files\n\nPlatform Files:\n  - CLAUDE.md: Present\n  - .claude\u002Fsettings.local.json: Present\n\nAll assets deployed successfully!\n```\n\n### Step 7: Summary Report\n\n```text\nAIWG Refresh Complete\n=====================\n\nCLI:\n  Version: 1.2.5 (updated from 1.2.3)\n\nFrameworks Deployed:\n  ✓ sdlc-complete v1.0.0 (58 agents, 48 commands)\n  ✓ aiwg-utils v1.0.0 (3 agents, 25 commands)\n\nPlatform: Claude Code\n  - .claude\u002Fagents\u002F: 61 files\n  - .claude\u002Fcommands\u002F: 73 files\n\nNew capabilities available:\n  - \u002Fsetup-tdd - TDD enforcement setup\n  - \u002Fflow-test-strategy-execution - Test execution workflow\n  - mutation-analyst agent - Test quality analysis\n\nSession ready - new features are now available!\n```\n\nIf the installation update fails but re-deployment completes, do not use the\nunqualified `AIWG Refresh Complete` summary above. Report **AIWG Refresh\nPartial Recovery**, repeat the update failure, and warn that AIWG may remain on\nthe previous version. When relaying quiet output, preserve the CLI status\n`refreshed-with-update-failure` so automation can distinguish this result from\na successful package update.\n\n## Examples\n\n```bash\n# Check status only\n\u002Faiwg-refresh\n\n# Update CLI and redeploy everything\n\u002Faiwg-refresh --update-cli --all\n\n# Just redeploy SDLC framework\n\u002Faiwg-refresh --sdlc\n\n# Switch to Factory AI deployment\n\u002Faiwg-refresh --all --provider factory\n\n# Preview what would happen\n\u002Faiwg-refresh --all --dry-run\n\n# Force refresh even if up-to-date\n\u002Faiwg-refresh --all --force\n\n# Redeploy with custom reasoning model\n\u002Faiwg-refresh --all --reasoning-model claude-opus-4-2\n\n# Redeploy with custom models for all tiers\n\u002Faiwg-refresh --all --reasoning-model opus-4-2 --coding-model sonnet-5 --efficiency-model haiku-4\n\n# Redeploy and save model selection for future deploys\n\u002Faiwg-refresh --all --coding-model claude-sonnet-5-0 --save\n\n# Only update architect agents with new reasoning model\n\u002Faiwg-refresh --sdlc --filter \"*architect*\" --reasoning-model opus-4-2\n\n# Only update reasoning-tier agents\n\u002Faiwg-refresh --all --filter-role reasoning --reasoning-model custom-reasoning\n```\n\n## Natural Language Triggers\n\nThis command should activate when user says:\n\n- \"refresh aiwg\" \u002F \"update aiwg\"\n- \"redeploy frameworks\" \u002F \"redeploy agents\"\n- \"get latest aiwg features\"\n- \"update my aiwg tools\"\n- \"sync aiwg deployment\"\n- \"change agent models\" \u002F \"switch to opus\" \u002F \"use different model\"\n- \"redeploy with custom models\"\n- \"update reasoning agents\" \u002F \"update architect agents\"\n\n## Error Handling\n\n| Condition | Action |\n|-----------|--------|\n| AIWG CLI not found | Error: \"AIWG CLI not installed. Run: curl -fsSL ... \\| bash\" |\n| Network or package error on update | Warn, continue re-deployment, and report partial recovery with `refreshed-with-update-failure` |\n| Framework not installed | Offer to install: \"SDLC not installed. Install now? [y\u002FN]\" |\n| Permission denied | Error with specific file\u002Fdirectory that failed |\n| Invalid provider | Error listing valid providers |\n\n## Post-Refresh Recommendations\n\nAfter refresh, suggest:\n\n```text\nRecommended next steps:\n1. Review new features: aiwg -help\n2. Check framework docs: \u002Faiwg-kb sdlc\n3. Run health check: aiwg doctor\n```\n\n## References\n\n- @$AIWG_ROOT\u002Fdocs\u002Fdevelopment\u002Ffile-placement-guide.md - Correct file placement workflow\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fcommands\u002Faiwg-regenerate.md - Context file regeneration\n- @$AIWG_ROOT\u002Fdocs\u002FCLI_USAGE.md - Full CLI documentation\n","> **Deterministic execution (#1267)**: this skill has a `script:` entrypoint\n> that shells out to `aiwg refresh \"$@\"`. Prefer\n> `aiwg run skill aiwg-refresh -- \u003Cflags>` when a platform supports it; on\n> platforms without a deployed command stub (e.g. hermes) invoke the CLI\n> directly. The CLI owns the deterministic execution step: version\u002Fchannel\n> resolution, CLI update, framework redeploy, provider detection, and exit\n> codes. The skill owns the agentic layer around that step: intent alignment,\n> output formatting, workspace-state reconciliation, summary, next actions,\n> gates, and recovery. Do not reimplement the refresh manually or add\n> redundant permission prompts before calling the CLI for execution.\n\n# Refresh AIWG Deployment\n\nUpdate the AIWG CLI and\u002For redeploy frameworks, agents, commands, and tools to the current\nproject without leaving the agentic session.\n\n## Use Cases\n\n- **After AIWG updates**: Get latest framework features without restarting\n- **After switching branches**: Ensure deployed content matches expectations\n- **After manual edits**: Restore canonical AIWG content\n- **Provider switch**: Redeploy for different platform (Claude → Factory)\n- **Model selection**: Redeploy with different AI models for each tier\n\n## Parameters\n\n| Flag | Description |\n|------|-------------|\n| `--update-cli` | Update AIWG CLI to latest version before redeploying |\n| `--all` | Redeploy all installed frameworks |\n| `--sdlc` | Redeploy SDLC framework only |\n| `--marketing` | Redeploy Marketing framework only |\n| `--utils` | Redeploy aiwg-utils addon only |\n| `--provider \u003Cname>` | Target platform: claude, factory, openai, cursor, warp (default: auto-detect) |\n| `--reasoning-model \u003Cname>` | Override model for reasoning agents (opus tier) |\n| `--coding-model \u003Cname>` | Override model for coding agents (sonnet tier) |\n| `--efficiency-model \u003Cname>` | Override model for efficiency agents (haiku tier) |\n| `--filter \u003Cpattern>` | Only deploy agents matching glob pattern (e.g., `*architect*`) |\n| `--filter-role \u003Crole>` | Only deploy agents of specified role: reasoning, coding, efficiency |\n| `--save` | Persist model selection to project models.json |\n| `--force` | Force redeploy even if already up-to-date |\n| `--dry-run` | Show what would be done without executing |\n\n## Execution Steps\n\nAny removal list requires explicit human review of the listed removals before execution.\nAuthorization lookup must never bypass that review, even with a receipt for other effects.\n\n### Step 1: Show Current Status\n\nRun status check and report current state:\n\n```bash\naiwg -status\n```\n\nReport:\n\n```text\nAIWG Refresh - Current Status\n==============================\n\nCLI Version: 1.2.3 (stable channel)\nWorkspace: \u002Fpath\u002Fto\u002Fproject\u002F.aiwg\n\nInstalled Frameworks:\n  - sdlc-complete v1.0.0 (58 agents, 48 commands)\n  - aiwg-utils v1.0.0 (3 agents, 25 commands)\n\nPlatform: Claude Code (.claude\u002F)\n  - Agents: 61 deployed\n  - Commands: 73 deployed\n```\n\n### Step 2: Update CLI (if --update-cli)\n\nIf `--update-cli` flag is set:\n\n```bash\naiwg -update\n```\n\nReport update status:\n\n```text\nChecking for updates...\n  Current: 1.2.3\n  Latest:  1.2.5\n\nUpdating AIWG CLI...\n✓ Updated to v1.2.5\n\nChanges in v1.2.5:\n  - New mutation-analyst agent\n  - Testing-quality addon\n  - Bug fixes\n```\n\nIf already up-to-date:\n\n```text\nAIWG CLI is up-to-date (v1.2.3)\n```\n\n### Step 3: Determine What to Redeploy\n\nBased on flags, determine scope:\n\n| Flags | Action |\n|-------|--------|\n| No flags | Show status only, prompt for action |\n| `--all` | Redeploy all installed frameworks |\n| `--sdlc` | Redeploy sdlc-complete only |\n| `--marketing` | Redeploy media-marketing-kit only |\n| `--utils` | Redeploy aiwg-utils addon only |\n| Multiple | Redeploy specified frameworks |\n\nIf no framework flags and not `--dry-run`, ask user:\n\n```text\nWhat would you like to refresh?\n\n[1] All frameworks (sdlc-complete, aiwg-utils)\n[2] SDLC framework only\n[3] Utils addon only\n[4] Just show status (no changes)\n\nChoice:\n```\n\n### Step 4: Detect Target Platform\n\nIf `--provider` not specified, auto-detect:\n\n1. Check existing deployments:\n   - `.claude\u002Fagents\u002F` exists → claude\n   - `.factory\u002Fdroids\u002F` exists → factory\n   - `.codex\u002Fagents\u002F` exists → openai\n   - `.cursor\u002Frules\u002F` exists → cursor\n\n2. If multiple detected, ask user:\n\n   ```text\n   Multiple platforms detected:\n   [1] Claude Code (.claude\u002F)\n   [2] Factory AI (.factory\u002F)\n\n   Which platform to refresh?\n   ```\n\n3. If none detected, default to claude\n\nReport:\n\n```text\nTarget platform: Claude Code\nDeployment paths:\n  - Agents: .claude\u002Fagents\u002F\n  - Commands: .claude\u002Fcommands\u002F\n```\n\n### Step 5: Execute Redeploy\n\nFor each framework to deploy:\n\n```bash\n# SDLC Framework\naiwg use sdlc --provider \u003Cplatform> --force [model-flags] [filter-flags]\n\n# Marketing Framework\naiwg use marketing --provider \u003Cplatform> --force [model-flags] [filter-flags]\n\n# Utils (included with sdlc)\n# No separate command needed\n```\n\n**Model flags** (if specified):\n- `--reasoning-model \u003Cname>` - applies to all opus-tier agents\n- `--coding-model \u003Cname>` - applies to all sonnet-tier agents\n- `--efficiency-model \u003Cname>` - applies to all haiku-tier agents\n\n**Filter flags** (if specified):\n- `--filter \u003Cpattern>` - only deploys matching agents\n- `--filter-role \u003Crole>` - only deploys agents of specified role\n\n**If `--dry-run`:**\nShow commands without executing:\n\n```text\nDry Run - Would execute:\n========================\n\n1. aiwg use sdlc --provider claude --force --reasoning-model opus-4-2\n   → Deploy 58 agents to .claude\u002Fagents\u002F (reasoning tier with opus-4-2)\n   → Deploy 48 commands to .claude\u002Fcommands\u002F\n\n2. aiwg use marketing --provider claude --force --reasoning-model opus-4-2\n   → Deploy 37 agents to .claude\u002Fagents\u002F (reasoning tier with opus-4-2)\n   → Deploy 20 commands to .claude\u002Fcommands\u002F\n\nNo changes made (dry run mode)\n```\n\n**Progress Reporting:**\n\n```text\nRefreshing AIWG Deployment\n==========================\n\n[1\u002F2] Deploying sdlc-complete...\n  → Copying 58 agents...\n  → Copying 48 commands...\n  → Copying 12 templates...\n  ✓ sdlc-complete deployed\n\n[2\u002F2] Deploying aiwg-utils...\n  → Copying 3 agents...\n  → Copying 25 commands...\n  ✓ aiwg-utils deployed\n```\n\n### Step 6: Verify Deployment\n\nAfter deployment, verify:\n\n```bash\n# Count deployed assets\nls .claude\u002Fagents\u002F*.md 2>\u002Fdev\u002Fnull | wc -l\nls .claude\u002Fcommands\u002F*.md 2>\u002Fdev\u002Fnull | wc -l\n```\n\nReport:\n\n```text\nVerification\n============\n\nDeployed Assets:\n  - Agents: 95 files\n  - Commands: 93 files\n\nPlatform Files:\n  - CLAUDE.md: Present\n  - .claude\u002Fsettings.local.json: Present\n\nAll assets deployed successfully!\n```\n\n### Step 7: Summary Report\n\n```text\nAIWG Refresh Complete\n=====================\n\nCLI:\n  Version: 1.2.5 (updated from 1.2.3)\n\nFrameworks Deployed:\n  ✓ sdlc-complete v1.0.0 (58 agents, 48 commands)\n  ✓ aiwg-utils v1.0.0 (3 agents, 25 commands)\n\nPlatform: Claude Code\n  - .claude\u002Fagents\u002F: 61 files\n  - .claude\u002Fcommands\u002F: 73 files\n\nNew capabilities available:\n  - \u002Fsetup-tdd - TDD enforcement setup\n  - \u002Fflow-test-strategy-execution - Test execution workflow\n  - mutation-analyst agent - Test quality analysis\n\nSession ready - new features are now available!\n```\n\nIf the installation update fails but re-deployment completes, do not use the\nunqualified `AIWG Refresh Complete` summary above. Report **AIWG Refresh\nPartial Recovery**, repeat the update failure, and warn that AIWG may remain on\nthe previous version. When relaying quiet output, preserve the CLI status\n`refreshed-with-update-failure` so automation can distinguish this result from\na successful package update.\n\n## Examples\n\n```bash\n# Check status only\n\u002Faiwg-refresh\n\n# Update CLI and redeploy everything\n\u002Faiwg-refresh --update-cli --all\n\n# Just redeploy SDLC framework\n\u002Faiwg-refresh --sdlc\n\n# Switch to Factory AI deployment\n\u002Faiwg-refresh --all --provider factory\n\n# Preview what would happen\n\u002Faiwg-refresh --all --dry-run\n\n# Force refresh even if up-to-date\n\u002Faiwg-refresh --all --force\n\n# Redeploy with custom reasoning model\n\u002Faiwg-refresh --all --reasoning-model claude-opus-4-2\n\n# Redeploy with custom models for all tiers\n\u002Faiwg-refresh --all --reasoning-model opus-4-2 --coding-model sonnet-5 --efficiency-model haiku-4\n\n# Redeploy and save model selection for future deploys\n\u002Faiwg-refresh --all --coding-model claude-sonnet-5-0 --save\n\n# Only update architect agents with new reasoning model\n\u002Faiwg-refresh --sdlc --filter \"*architect*\" --reasoning-model opus-4-2\n\n# Only update reasoning-tier agents\n\u002Faiwg-refresh --all --filter-role reasoning --reasoning-model custom-reasoning\n```\n\n## Natural Language Triggers\n\nThis command should activate when user says:\n\n- \"refresh aiwg\" \u002F \"update aiwg\"\n- \"redeploy frameworks\" \u002F \"redeploy agents\"\n- \"get latest aiwg features\"\n- \"update my aiwg tools\"\n- \"sync aiwg deployment\"\n- \"change agent models\" \u002F \"switch to opus\" \u002F \"use different model\"\n- \"redeploy with custom models\"\n- \"update reasoning agents\" \u002F \"update architect agents\"\n\n## Error Handling\n\n| Condition | Action |\n|-----------|--------|\n| AIWG CLI not found | Error: \"AIWG CLI not installed. Run: curl -fsSL ... \\| bash\" |\n| Network or package error on update | Warn, continue re-deployment, and report partial recovery with `refreshed-with-update-failure` |\n| Framework not installed | Offer to install: \"SDLC not installed. Install now? [y\u002FN]\" |\n| Permission denied | Error with specific file\u002Fdirectory that failed |\n| Invalid provider | Error listing valid providers |\n\n## Post-Refresh Recommendations\n\nAfter refresh, suggest:\n\n```text\nRecommended next steps:\n1. Review new features: aiwg -help\n2. Check framework docs: \u002Faiwg-kb sdlc\n3. Run health check: aiwg doctor\n```\n\n## References\n\n- @$AIWG_ROOT\u002Fdocs\u002Fdevelopment\u002Ffile-placement-guide.md - Correct file placement workflow\n- @$AIWG_ROOT\u002Fagentic\u002Fcode\u002Faddons\u002Faiwg-utils\u002Fcommands\u002Faiwg-regenerate.md - Context file regeneration\n- @$AIWG_ROOT\u002Fdocs\u002FCLI_USAGE.md - Full CLI documentation\n",{"name":5,"kernel":47,"script":48,"namespace":53,"platforms":54,"description":7},true,{"cwd":49,"runtime":50,"argsHint":51,"entrypoint":52},"project-root","bash","[--update-cli] [--all] [--provider \u003Cname>] [--dry-run] [--channel \u003Cname>]","run.sh","aiwg",[55],"all","main","ac56f6a215342ed836e51f1945653968b95edd64","agentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Faiwg-refresh",36,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg","https:\u002F\u002Faiwg.io","https:\u002F\u002Fgithub.com\u002Fjmagly","https:\u002F\u002Fintegrolabs.io","ml\u002Fai, industrial automation, safety\u002Fsecurity, ssi\r\n\r\nmagly.net\r\nintegrolabs.io\r\naiwg.io\r\nfortemi.com\r\npagenary.com\r\nbytecask.com","2026-11-14 02:10:01",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":47},[68,71,74],{"tool":69,"command":70},"npx","npx skills add jmagly\u002Faiwg --skill aiwg-refresh",{"tool":72,"command":73},"bunx","bunx skills add jmagly\u002Faiwg --skill aiwg-refresh",{"tool":75,"command":76},"pnpm","pnpm dlx skills add jmagly\u002Faiwg --skill aiwg-refresh","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Faiwg-refresh\u002FSKILL.md",[79],{"path":52,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"SCRIPT","脚本",436,"https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Futils\u002Fskills\u002Faiwg-refresh\u002Frun.sh",[85,112,136,142,149,162],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":92,"publishedAt":42},"01M70QA0BSYJ49EES9V4RE8QH1","host-hardening","Read-only system hardening baseline and plan-first host hardening recommendations for SSH, Docker bind addresses, firewall persistence, datastores, exporters and audit retention.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[91],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[93,94,95,96,97,98,99,100,101,102,38,103,104,105,106,107,108,109,110,111],"host","host hardening","hardening","read","re","recommendations","remediation","plan","port","verification","access","only","retention","audit","never","firewall","bind","secrets","request",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":122,"publishedAt":42},"01M70PNT2Z4HMZPRBTAF6073NN","exposure-analysis","Read-only firewall analysis and effective host exposure reconstruction for Docker published ports, UFW bypass, stale rules, CDN scope, IPv6 asymmetry and external probe allowlists.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fplugins\u002Fforensics\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[118,121],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[123,124,125,96,126,101,127,128,38,129,93,130,104,131,132,107,108,133,134,135],"exposure analysis","analysis","unknown","credentials","collection","ufw","ports","internet","local","scope","reconstruction","operator","write",{"skillNo":137,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":42},"01M70P8QATMPKA78E4FT5D2TNA","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fsecurity-engineering\u002Fskills\u002Fhost-hardening\u002FSKILL.md",[140],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[95,93,94,103,96,111,99,98,106,100,101,102,38,110,104,105,97,107,108,109],{"skillNo":143,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":148,"publishedAt":42},"01M70NMPVJ5H0JH131P60FW4R8","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Fagentic\u002Fcode\u002Fframeworks\u002Fforensics-complete\u002Fskills\u002Fexposure-analysis\u002FSKILL.md",[146,147],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[124,123,107,126,101,127,38,125,93,130,104,131,132,96,108,129,128,133,134,135],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":42},"01M6CB4DDR0B4NNCFK7ZK7449H","fixture-skill","Exercise rule delivery.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Frule-delivery\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[155],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[157,158,159,160,28,161],"fixture skill","fixture","rule","delivery","exercise",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":169,"publishedAt":42},"01M6CB4AVK1W76MFMPP0JP32CJ","pi-local","Pi-local duplicate-precedence fixture.","https:\u002F\u002Fgithub.com\u002Fjmagly\u002Faiwg\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fproviders\u002Fpi\u002Fproject\u002F.pi\u002Fskills\u002Fpi-local\u002FSKILL.md",[168],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[170,171,131,172,158],"pi","pi local","duplicate"]