@mmerterden/multi-agent-pipeline 8.6.1 → 10.0.6

package/pipeline/skills/shared/core/multi-agent-setup/SKILL.md

@@ -1,26 +1,26 @@
 ---
 name: multi-agent-setup
-language: tr
+language: en
 description: "First-run setup wizard: keychain token discovery, Git Identity onboarding, and pipeline preparation."
 user-invocable: true
 ---
 
 ## Setup (Keychain Token + Git Identity Onboarding)
 
-Self-contained setup — works with inline `security` commands, no external script **required**. If `$HOME/.claude/scripts/keychain-save.sh` exists, it can be used as an interactive alternative but is not mandatory. The `setup` command starts interactive onboarding.
+Self-contained setup  -  works with inline `security` commands, no external script **required**. If `$HOME/.claude/scripts/keychain-save.sh` exists, it can be used as an interactive alternative but is not mandatory. The `setup` command starts interactive onboarding.
 
-### Step 0 — Language Selection
+### Step 0  -  Language Selection
 
 Ask BEFORE anything else. The pipeline has two language fields:
 
 | Field | Controls | Configurable? |
 |---|---|---|
-| `promptLanguage` | Interactive pickers and prompts during pipeline runs (account, project, branch, channels, Phase 5/6 confirmations) | **No — fixed to `en`.** Picker UI is always English. |
-| `outputLanguage` | The assistant's non-interactive explanations, status updates, error messages, and pipeline-generated reports | Yes — set here, change later via `/multi-agent-language <en\|tr>` |
+| `promptLanguage` | Interactive pickers and prompts during pipeline runs (account, project, branch, channels, Phase 5/6 confirmations) | **No  -  fixed to `en`.** Picker UI is always English. |
+| `outputLanguage` | The assistant's non-interactive explanations, status updates, error messages, and pipeline-generated reports | Yes  -  set here, change later via `/multi-agent-language <en\|tr>` |
 
 `promptLanguage` is seeded as `"en"` and never offered to the user. External payloads (commits, PR/Jira/wiki, reviewer/triage prompts, agent-log.md) always stay English regardless.
 
-**Step 0 — outputLanguage** (English UI per skill-prompt rules):
+**Step 0  -  outputLanguage** (English UI per skill-prompt rules):
 
 ```
 Which language should the assistant use for ITS OWN explanations,
@@ -36,7 +36,7 @@ Select (1-2):
 - New value → validate against `["en", "tr"]`, atomic write to `prefs.global.outputLanguage`, force `prefs.global.promptLanguage = "en"`, echo confirmation in the chosen `outputLanguage`.
 - Unknown input → re-ask once, then abort with a hint pointing to `/multi-agent-language`.
 
-### Step 1 — Dynamic Keychain Discovery
+### Step 1  -  Dynamic Keychain Discovery
 
 Instead of checking only hardcoded key names, discover ALL user keys and intelligently map them to services.
 
@@ -48,7 +48,7 @@ echo "$DISCOVERED"
 
 **1b. Standard key names (convention):**
 
-These are the RECOMMENDED key names. When creating NEW keys, use these. But existing keys under different names are perfectly valid — the discovery step will find them.
+These are the RECOMMENDED key names. When creating NEW keys, use these. But existing keys under different names are perfectly valid  -  the discovery step will find them.
 
 | Service ID | Standard Key Name | Search Keywords |
 |------------|------------------|-----------------|
@@ -70,7 +70,7 @@ For each service in the table above, follow this order:
 1. **Check standard key** -> `~/.copilot/lib/credential-store.sh get "<standard_key>" 2>/dev/null`
    - Found -> auto-map, done
 2. **Search discovered keys** -> filter `$DISCOVERED` by the service's search keywords (case-insensitive)
-   - Exactly 1 match -> show: `"Found '${matched_key}' for ${service} — use this? (enter=yes / n=skip)"` -> if yes, map it
+   - Exactly 1 match -> show: `"Found '${matched_key}' for ${service}  -  use this? (enter=yes / n=skip)"` -> if yes, map it
    - Multiple matches -> show numbered list, user picks:
      ```
      Multiple keys found for GitHub:
@@ -87,7 +87,7 @@ Before running discovery, check `prefs.global.keychainMapping`. If a mapping alr
 
 If a previously mapped key NO LONGER exists in Keychain -> clear the stale mapping, re-run discovery for that service.
 
-### Step 2 — Show Discovery Summary + Save Mapping
+### Step 2  -  Show Discovery Summary + Save Mapping
 
 Show results grouped by status:
 
@@ -126,20 +126,20 @@ Save the resolved mapping to preferences:
 }
 ```
 
-`null` = not mapped (missing or skipped). Pipeline phases read this mapping to retrieve tokens dynamically — never hardcoded key names.
+`null` = not mapped (missing or skipped). Pipeline phases read this mapping to retrieve tokens dynamically  -  never hardcoded key names.
 
-### Step 3 — Jira Project Key (auto-learned)
+### Step 3  -  Jira Project Key (auto-learned)
 
 Jira project keys are NOT asked during setup. They are auto-learned from pipeline usage:
 - User runs `/multi-agent ABC-123` → `ABC` is extracted and saved to `prefs.global.defaultJiraKey` (first ever) and `prefs.projects[{project}].jiraProjectKeys` (per-project).
 - User later runs `/multi-agent MOBILE-456` in a different project → `MOBILE` is added to that project's keys.
-- Multiple keys accumulate over time — most recent first, deduped.
+- Multiple keys accumulate over time  -  most recent first, deduped.
 
 Phase 0 Step 1 (Parse Input) handles extraction and persistence. No setup interaction needed.
 
-### Step 4 — Git Identity Setup (one-time)
+### Step 4  -  Git Identity Setup (one-time)
 
-Git identities are NOT secrets — stored in the preferences file, not Keychain:
+Git identities are NOT secrets  -  stored in the preferences file, not Keychain:
 
 ```bash
 PREFS_FILE="$HOME/.claude/multi-agent-preferences.json"
@@ -152,13 +152,16 @@ Let's set up git identity.
 Identity 1 (corporate):
   Author name: ___
   Email: ___
+```
 
-Add another identity? (y/n)
+After each identity, ask with a native `AskUserQuestion` picker (never a typed y/n):
+- `question`: "Add another git identity?" (rendered in `outputLanguage`)
+- `header`: "Identity" (English, <=12 chars)
+- `options`:
+  - `{ label: "Add another", description: "Collect one more name + email identity" }`
+  - `{ label: "Done", description: "Finish identity setup and save" }`
 
-Identity 2 (personal):
-  Author name: ___
-  Email: ___
-```
+**Add another** → collect the next identity (e.g. Identity 2, personal: author name + email), then re-ask. **Done** → save.
 
 Save to preferences JSON:
 ```json
@@ -179,7 +182,7 @@ Git Identities (saved to preferences):
   2. {Full Name} <{personal@email.com}>
 ```
 
-### Step 5 — Interactive token onboarding (for missing tokens)
+### Step 5  -  Interactive token onboarding (for missing tokens)
 
 For each MISSING service, run the **Token Save Flow** (see `setup.md` for full spec).
 
@@ -187,20 +190,20 @@ Summary: ask `[1] Add now / [2] Skip` → if add, user copies token to clipboard
 
 The same flow is reused at Phase 0 runtime when a token is expired (401/403).
 
-### Step 6 — Verify all
+### Step 6  -  Verify all
 
 Re-run scan from Step 1. Show final status:
 ```
 All tokens present. Pipeline ready to use.
 
 Optional per-project features (configured on first use, nothing to do now):
-  • Phase 7 Report Step 2 Wiki — auto-generates component wiki pages + Figma
+  • Phase 7 Report Step 2 Wiki  -  auto-generates component wiki pages + Figma
     screenshots. Activates when (a) task is a component AND (b) a Figma token
     is in Keychain. Four adapters supported: submodule / in-repo / github-wiki
     / separate-repo. First run asks: use auto-detected path, use a custom
     path, skip once, or disable for this project (persisted).
-  • channels — post-hoc multi-channel reporter (Jira/Confluence/Wiki/PR), works on any branch with an open PR. v5.7+ replaces the older `enrich` command.
-  • Default reviewers — auto-fetched from Bitbucket default-reviewers endpoint
+  • channels  -  post-hoc multi-channel reporter (Jira/Confluence/Wiki/PR), works on any branch with an open PR. v5.7+ replaces the older `enrich` command.
+  • Default reviewers  -  auto-fetched from Bitbucket default-reviewers endpoint
     or GitHub CODEOWNERS on first PR.
 
 Next step:
@@ -212,7 +215,7 @@ If still missing, show which ones and let user skip (pipeline will re-ask for an
 
 ### Token -> Source Mapping
 
-Standard key names (used when creating NEW tokens). Discovery may find existing keys under different names — that's fine, the mapping in preferences handles it.
+Standard key names (used when creating NEW tokens). Discovery may find existing keys under different names  -  that's fine, the mapping in preferences handles it.
 
 | Service ID | Standard Key Name | Type | Where to Get |
 |------------|------------------|------|---------------|
@@ -226,7 +229,7 @@ Standard key names (used when creating NEW tokens). Discovery may find existing
 | `fortify` | `${USER}_Fortify_Access_Token` | API Token | Fortify SSC -> Token Management (VPN required) |
 | `firebase` | `${USER}_Firebase_Access_Json` | Firebase JSON (base64) | Firebase Console -> Project settings -> Service accounts -> Generate new private key. Project id is parsed from the decoded JSON. |
 | `jenkins` | `${USER}_Jenkins_Access_Token` | API Token | Jenkins -> User -> Configure -> API Token |
-| — | Git Identities | JSON (preferences) | Stored in `$HOME/.claude/multi-agent-preferences.json` — not Keychain |
+|  -  | Git Identities | JSON (preferences) | Stored in `$HOME/.claude/multi-agent-preferences.json`  -  not Keychain |
 
 ### Inline Token Save Pattern
 
@@ -261,7 +264,7 @@ pbpaste | ~/.copilot/scripts/keychain.py set "<SERVICE_NAME>" -
 Figma MCP works in two modes:
 
 **Remote MCP** (Claude Code built-in):
-- Automatic — comes as `claude_ai_Figma` in Claude Code settings.json
+- Automatic  -  comes as `claude_ai_Figma` in Claude Code settings.json
 - If token renewal needed: re-auth from within Claude Code
 
 **Local MCP** (@anthropic-ai/figma-mcp package, with PAT):
@@ -277,7 +280,7 @@ pbcopy < /dev/null
 
 ### Security Rules
 
-- Never paste tokens into terminal or chat — use `pbpaste` for input
+- Never paste tokens into terminal or chat  -  use `pbpaste` for input
 - Never hardcode tokens in source code
 - Never commit tokens to git history
 - Clear clipboard immediately: `pbcopy < /dev/null`
@@ -306,4 +309,4 @@ To set up multi-agent on a new machine:
    /multi-agent "bug description"
 ```
 
-All tokens are optional — pipeline will ask for any needed token at Phase 0. Setup only does pre-preparation.
+All tokens are optional  -  pipeline will ask for any needed token at Phase 0. Setup only does pre-preparation.

package/pipeline/skills/shared/core/multi-agent-stack/SKILL.md

@@ -1,33 +1,33 @@
 ---
 name: multi-agent-stack
-language: tr
+language: en
 description: "Manually switch the active skill set by platform (ios/android/mobile/backend/frontend/fullstack/all)."
 user-invocable: true
 ---
 
-# multi-agent stack — Manual Stack Swap
+# multi-agent stack  -  Manual Stack Swap
 
-`pipeline/scripts/stack-swap.sh` SessionStart hook'u stack'i projeye göre otomatik tespit eder. Bu komut o kararı manuel olarak geçersiz kılar — aktif skill setini değiştirir ve eşleşmeyen skill'leri `skills-inactive/`'e taşır.
+The `pipeline/scripts/stack-swap.sh` SessionStart hook auto-detects the stack from the project. This command manually overrides that decision  -  it changes the active skill set and moves non-matching skills to `skills-inactive/`.
 
 ## Usage
 
 ```bash
-multi-agent-stack                  # mevcut durumu göster
+multi-agent-stack                  # show the current state
 multi-agent-stack ios              # SwiftUI + Xcode
 multi-agent-stack android          # Compose + Gradle
-multi-agent-stack mobile           # iOS + Android birlikte
+multi-agent-stack mobile           # iOS + Android together
 multi-agent-stack backend          # Python / Node / Go
 multi-agent-stack frontend         # React / Vue / Next
 multi-agent-stack fullstack        # backend + frontend
-multi-agent-stack all              # hepsini aktif et
+multi-agent-stack all              # activate everything
 ```
 
 ## Behaviour
 
-1. Arg yoksa → status modu: aktif skill sayısını göster, herhangi bir dosya taşıma **yapma**.
-2. Arg varsa → `stack-swap.sh <arg>` çalıştır.
-3. Script stdout'u JSON (`{"systemMessage": "..."}`) — kullanıcıya `systemMessage` değerini yazdır.
-4. Bilinmeyen arg → script `exit 1` + hata mesajı döner; değeri tekrar sorma, kullanıcıya listeyi göster.
+1. No arg → status mode: show the active skill count, do **not** move any files.
+2. With an arg → run `stack-swap.sh <arg>`.
+3. The script's stdout is JSON (`{"systemMessage": "..."}`)  -  print the `systemMessage` value to the user.
+4. Unknown arg → the script returns `exit 1` + an error message; do not ask for the value again, show the user the list.
 
 ## Implementation
 
@@ -40,7 +40,7 @@ if [ -x "$HOME/.copilot/scripts/stack-swap.sh" ]; then
 elif [ -x "$HOME/.claude/scripts/stack-swap.sh" ]; then
   SCRIPT="$HOME/.claude/scripts/stack-swap.sh"
 else
-  echo "stack-swap.sh not found — run install.js --copilot (or --all) to deploy pipeline scripts."
+  echo "stack-swap.sh not found  -  run install.js --copilot (or --all) to deploy pipeline scripts."
   exit 1
 fi
 
@@ -50,6 +50,6 @@ ARG="${1:-status}"
 
 ## Notes
 
-- Manuel swap anlık etki eder ama Copilot CLI'ın skill keşfini tam yenilemek için **konuşmayı yeniden başlat**.
-- Auto-detect tekrar devreye girsin istersen sonraki SessionStart yeterli — hook `cwd`'a bakıp tekrar karar verir. Manuel override kalıcı değildir.
-- Pipeline Phase 1 stack tespiti bu komuttan bağımsızdır (proje dosyalarına bakar). `stack` sadece hangi skill set'inin aktif olduğunu etkiler.
+- A manual swap takes effect immediately, but to fully refresh Copilot CLI's skill discovery, **restart the conversation**.
+- If you want auto-detect to take over again, the next SessionStart is enough  -  the hook looks at `cwd` and decides again. The manual override is not permanent.
+- Pipeline Phase 1 stack detection is independent of this command (it looks at project files). `stack` only affects which skill set is active.

package/pipeline/skills/shared/core/multi-agent-status/SKILL.md

@@ -1,30 +1,30 @@
 ---
 name: multi-agent-status
-language: tr
+language: en
 description: "Show every multi-agent task's ID, phase, branch, and status."
 user-invocable: true
 ---
 
-# multi-agent status — Task Status Dashboard
+# multi-agent status  -  Task Status Dashboard
 
 Show every active and completed task as a table.
 
 ## Steps
 
-1. **Proje tespit et** — cwd'deki repo kökünü bul (yoksa tüm bilinen repo'lara bak):
+1. **Detect project**  -  Find the repo root from cwd (if none, look at all known repos):
    - `~/my-ui-components/.worktrees/`
    - `~/my-figma-app/.worktrees/`
    - `~/my-ios-app/.worktrees/`
 
-2. **Worktree'leri tara** — Her worktree dizininde `agent-state.json` dosyasını oku:
+2. **Scan worktrees**  -  Read the `agent-state.json` file in each worktree directory:
    ```bash
    find {repo}/.worktrees/ -name "agent-state.json" -maxdepth 2
    ```
 
-3. **State parse et** — Her task için:
+3. **Parse state**  -  For each task:
    - `taskId`, `branch`, `currentPhase`, `status`, `startedAt`, `autopilot`
 
-4. **Tablo formatında göster**:
+4. **Show as a table**:
    ```
    🤖 Multi-Agent Tasks
 
@@ -36,6 +36,6 @@ Show every active and completed task as a table.
    💡 log #1 | resume #N | kill #N
    ```
 
-5. **Kısa komut önerileri** — Duruma göre:
-   - Paused task varsa → `resume #N` öner
-   - Done task varsa → `log #N` öner
+5. **Short command suggestions**  -  Based on state:
+   - If there is a paused task → suggest `resume #N`
+   - If there is a done task → suggest `log #N`

package/pipeline/skills/shared/core/multi-agent-sync/SKILL.md

@@ -3,100 +3,100 @@ name: multi-agent-sync
 language: en
 description: "One-shot sync of the entire multi-agent ecosystem: Claude Code, Copilot CLI, pipeline repo, website, and remote-control."
 user-invocable: true
-argument-hint: 'release | "degisiklik aciklamasi"'
+argument-hint: 'release | "change description"'
 ---
 
 # Multi-Agent Sync
 
-**Tek komut. Full ecosystem sync. Arguman gerekmez.**
+**Single command. Full ecosystem sync. No argument required.**
 
-Cagrildiginda 6 hedefin tamamini sirayla senkronize eder. Neyin degistigini algilar, sadece stale olanlari gunceller, sonuc raporu verir.
+When invoked, it synchronizes all 6 targets in order. It detects what changed, updates only the stale ones, and reports the result.
 
-**Input**: $ARGUMENTS (opsiyonel — `release` veya tum hedeflere uygulanacak degisiklik aciklamasi)
+**Input**: $ARGUMENTS (optional  -  `release` or a change description to apply to all targets)
 
-## Hedefler (her zaman 6'si birden)
+## Targets (always all 6)
 
-| # | Hedef | Yol | Yon |
+| # | Target | Path | Direction |
 |---|-------|-----|-----|
 | 0 | Figma source (opt-in) | `prefs.global.figmaSource.path` -> `pipeline/skills/figma-ios/` + `figma-common/` | <- upstream |
-| 1 | Claude Code (source of truth) | `~/.claude/commands/multi-agent.md` + `~/.claude/commands/multi-agent/` + `~/.claude/agents/` + `~/.claude/scripts/` | kaynak |
-| 2 | Copilot CLI | `~/.copilot/copilot-instructions.md` + `~/.copilot/skills/` | <- Claude'dan |
-| 3 | multi-agent-pipeline repo | `~/multi-agent-pipeline/pipeline/` | <- Claude'dan (genericized) |
-| 4 | Website | `{owner}/{website-host}` | <- versiyon + ozellikler |
-| 5 | Remote Control | `{owner}/remote-control` | <- pipeline referanslari |
+| 1 | Claude Code (source of truth) | `~/.claude/commands/multi-agent.md` + `~/.claude/commands/multi-agent/` + `~/.claude/agents/` + `~/.claude/scripts/` | source |
+| 2 | Copilot CLI | `~/.copilot/copilot-instructions.md` + `~/.copilot/skills/` | <- from Claude |
+| 3 | multi-agent-pipeline repo | `~/multi-agent-pipeline/pipeline/` | <- from Claude (genericized) |
+| 4 | Website | `{owner}/{website-host}` | <- version + features |
+| 5 | Remote Control | `{owner}/remote-control` | <- pipeline references |
 
-## Varsayilan Davranis (argumansiz)
+## Default Behavior (no argument)
 
-Tum adimlari otomatik calistir:
+Run all steps automatically:
 
 ```
-Adim 0: FIGMA_SYNC  (opt-in) pipeline/scripts/sync-figma-source.sh
-                    -- figmaSource.path set ise upstream'den incremental pull
-Adim 1: DETECT      Timestamp karsilastir, stale hedefleri bul
-Adim 2: COPILOT     Claude Code -> Copilot CLI (instructions + 26 sub-command skills)
-Adim 3: REPO        Claude Code -> pipeline repo (genericized, personal data scrub)
-Adim 4: WEBSITE     Versiyon + faz/model sayilari -> {website-host} (i18n + projects.ts)
-Adim 5: REMOTE      Pipeline referanslari -> remote-control README
-Adim 6: Commit      Degisen tum repolari commit + push
-Adim 7: Report      Ozet: sync edilen hedefler, degisen dosyalar, deploy durumu
+Step 0: FIGMA_SYNC  (opt-in) pipeline/scripts/sync-figma-source.sh
+                    -- incremental pull from upstream if figmaSource.path is set
+Step 1: DETECT      Compare timestamps, find stale targets
+Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 26 sub-command skills)
+Step 3: REPO        Claude Code -> pipeline repo (genericized, personal data scrub)
+Step 4: WEBSITE     Version + phase/model counts -> {website-host} (i18n + projects.ts)
+Step 5: REMOTE      Pipeline references -> remote-control README
+Step 6: Commit      Commit + push all changed repos
+Step 7: Report      Summary: synced targets, changed files, deploy status
 ```
 
-Hicbir sey stale degilse -> "Tum hedefler guncel" raporla ve dur.
+If nothing is stale -> report "All targets up to date" and stop.
 
 ## Special inputs
 
-| Girdi | Davranis |
+| Input | Behavior |
 |-------|----------|
-| (argumansiz) | Full ecosystem sync (varsayilan) |
-| `release` | Full sync + versiyon bump + tag + npm publish + website deploy |
-| `"degisiklik aciklamasi"` | Aciklamayi TUM hedeflere ayni anda uygula |
+| (no argument) | Full ecosystem sync (default) |
+| `release` | Full sync + version bump + tag + npm publish + website deploy |
+| `"change description"` | Apply the description to ALL targets at once |
 
 
 ## Sync rules
 
-1. **Once oku** — Degisiklik yapmadan once tum hedeflerin mevcut durumunu anla
-2. **Dosya yapisini koru** — Her hedefin kendi formati var:
-   - `multi-agent.md` + phases/: detayli pipeline spec (frontmatter, phases, routing)
-   - `copilot-instructions.md`: genel gelistirme talimatlari + pipeline ozet bolumu
-   - `multi-agent-pipeline/pipeline/`: generic acik kaynak versiyonu (kisisel veri YOK)
-3. **Shared section'lari sync et** (Claude <-> Copilot):
-   - Pipeline modlari tablosu (normal / autopilot / --dev / --dev autopilot)
-   - Proje tespiti (URL-based + cwd-based)
-   - Figma pipeline akisi
+1. **Read first**  -  Understand the current state of all targets before making changes
+2. **Preserve file structure**  -  Each target has its own format:
+   - `multi-agent.md` + phases/: detailed pipeline spec (frontmatter, phases, routing)
+   - `copilot-instructions.md`: general development instructions + pipeline summary section
+   - `multi-agent-pipeline/pipeline/`: generic open-source version (NO personal data)
+3. **Sync shared sections** (Claude <-> Copilot):
+   - Pipeline modes table (normal / autopilot / --dev / --dev autopilot)
+   - Project detection (URL-based + cwd-based)
+   - Figma pipeline flow
    - Git conventions (author, branch, commit format)
-   - --dev mode model bilgisi (Opus)
-   - Keychain yonetimi (registry, naming convention, multi-agent pattern)
-4. **Duplike etme** — Copilot'ta ozet, Claude'da full spec. Bu ayrimi koru.
-5. **Rapor ver** — Sync sonrasi kisa diff ozeti goster
-
-## Pipeline Repo Sync Kurallari (KRITIK)
-
-1. **Kaynak**: `~/.claude/commands/multi-agent.md` + `~/.claude/commands/multi-agent/` + `~/.claude/agents/`
-2. **Hedef**: `~/multi-agent-pipeline/pipeline/`
-3. **Genericization** (hedefe yazmadan ONCE uygulanmali):
-   - Jira proje key'i (`prefs.global.defaultJiraKey`) -> `{JIRA_KEY}`, orneklerde `PROJ`
-   - Kisisel isimler/emailler -> generic placeholder
-   - Branch isimleri -> `develop`
-   - Proje isimleri -> `my-app`
-   - `{JIRA_HOST}`, `{BITBUCKET_HOST}`, `{CONFLUENCE_HOST}`, `{CORP_DOMAIN}` oldugu gibi kalir
-   - **Dogrula**: `grep` ile pipeline/ icinde kisisel/kurumsal veri taramasi -> 0 sonuc
-4. **Dosya esleme**:
+   - --dev mode model info (Opus)
+   - Keychain management (registry, naming convention, multi-agent pattern)
+4. **Do not duplicate**  -  Summary in Copilot, full spec in Claude. Preserve this distinction.
+5. **Report**  -  Show a short diff summary after the sync
+
+## Pipeline Repo Sync Rules (CRITICAL)
+
+1. **Source**: `~/.claude/commands/multi-agent.md` + `~/.claude/commands/multi-agent/` + `~/.claude/agents/`
+2. **Target**: `~/multi-agent-pipeline/pipeline/`
+3. **Genericization** (must be applied BEFORE writing to the target):
+   - Jira project key (`prefs.global.defaultJiraKey`) -> `{JIRA_KEY}`, `PROJ` in examples
+   - Personal names/emails -> generic placeholder
+   - Branch names -> `develop`
+   - Project names -> `my-app`
+   - `{JIRA_HOST}`, `{BITBUCKET_HOST}`, `{CONFLUENCE_HOST}`, `{CORP_DOMAIN}` stay as-is
+   - **Verify**: scan for personal/corporate data inside pipeline/ with `grep` -> 0 results
+4. **File mapping**:
    ```
    ~/.claude/commands/multi-agent.md      -> pipeline/commands/multi-agent.md
    ~/.claude/commands/multi-agent/        -> pipeline/commands/multi-agent/
    ~/.claude/commands/sim-test.md         -> pipeline/commands/sim-test.md
    ~/.claude/agents/*.md                  -> pipeline/agents/
    ```
-5. **Sync EDILMEYEN dosyalar** (local-only, kisisel veri icerebilir):
+5. **Files NOT synced** (local-only, may contain personal data):
    - `~/.claude/multi-agent-preferences.json`
    - `~/.claude/CLAUDE.md`, `~/.claude/rules/`, `~/.claude/knowledge/`
-   - `~/.claude/scripts/` — `pre-commit-check.sh` ve `stack-swap.sh` HARIC (generic, sync edilir)
+   - `~/.claude/scripts/`  -  EXCEPT `pre-commit-check.sh` and `stack-swap.sh` (generic, synced)
    - `~/.claude/settings.json`
 
 
-## Website Sync (Adim 4)
+## Website Sync (Step 4)
 
-Pipeline versiyon, faz sayisi, model sayisi ve ozellik aciklamalarini website'a propagate et.
+Propagate the pipeline version, phase count, model count, and feature descriptions to the website.
 
 ```bash
 gh auth switch --user {owner}
@@ -105,10 +105,10 @@ WEBSITE_DIR="$HOME/{website-host}"
 cd "$WEBSITE_DIR" && git pull origin main
 ```
 
-| Dosya | Sync edilecek |
+| File | To sync |
 |-------|--------------|
-| `src/lib/i18n.tsx` | Faz sayisi, model sayisi, ozellik aciklamalari (EN + TR) |
-| `src/data/projects.ts` | Versiyon numarasi, tagline, aciklama, ozellik listesi |
+| `src/lib/i18n.tsx` | Phase count, model count, feature descriptions (EN + TR) |
+| `src/data/projects.ts` | Version number, tagline, description, feature list |
 
 ```bash
 cd "$WEBSITE_DIR"
@@ -117,7 +117,7 @@ git push origin main  # Vercel auto-deploy
 ```
 
 
-## Remote Control Sync (Adim 5)
+## Remote Control Sync (Step 5)
 
 ```bash
 REMOTE_DIR="$HOME/remote-control"
@@ -125,29 +125,29 @@ REMOTE_DIR="$HOME/remote-control"
 cd "$REMOTE_DIR" && git pull origin main
 ```
 
-| Dosya | Sync edilecek |
+| File | To sync |
 |-------|--------------|
-| `README.md` | Pipeline ozellik aciklamasi |
-| `src/index.ts` | Help text / chip label'lari (varsa) |
+| `README.md` | Pipeline feature description |
+| `src/index.ts` | Help text / chip labels (if any) |
 
-Sadece pipeline'in public-facing ozellikleri degistiyse guncelle.
+Update only if the pipeline's public-facing features changed.
 
 
-## Release Akisi
+## Release Flow
 
-`release` argumaniyla cagrildiginda:
+When invoked with the `release` argument:
 
 ```
 1. REPO          Claude Code -> pipeline repo (genericized)
-2. VERIFY        Kisisel veri taramasi -> 0 sonuc
+2. VERIFY        Personal data scan -> 0 results
 3. LINT + TEST   ESLint + smoke tests
 4. VERSION       package.json version bump (patch/minor/major)
 5. Commit + TAG  git commit + git tag v{VERSION}
 6. PUSH          git push --tags -> release.yml auto-publish
-7. WEBSITE       Versiyon + ozellikler -> {website-host}
-8. REMOTE        remote-control referanslari guncelle
+7. WEBSITE       Version + features -> {website-host}
+8. REMOTE        Update remote-control references
 9. COPILOT       Copilot CLI instructions + skills sync
-10. Report        Ozet: versiyon, dokunulan repolar, deploy durumu
+10. Report        Summary: version, touched repos, deploy status
 ```
 
 
@@ -157,7 +157,7 @@ Sadece pipeline'in public-facing ozellikleri degistiyse guncelle.
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**26 komut sync edilir** (v7.0.0+ canonical inventory — `cross-cli-contract.md` §1 ile eşleşmeli, drift = contract violation):
+**26 commands are synced** (v7.0.0+ canonical inventory  -  must match `cross-cli-contract.md` section1, drift = contract violation):
 
 ```
 autopilot, channels, dev, dev-autopilot, dev-local, dev-local-autopilot,
@@ -165,20 +165,20 @@ help, issue, jira, kill, local, local-autopilot, log, manual-test, purge,
 refactor, resume, review, scan, search, setup, stack, status, sync, test, update
 ```
 
-**Sync EDILMEZ**: `refs/*` — Lazy-load referanslari, Claude Code'a ozel
+**NOT synced**: `refs/*`  -  Lazy-load references, Claude Code specific
 
-**Claude -> Copilot**: SKILL.md frontmatter ekle (`name`, `description`, `user-invocable: true`, `argument-hint`)
-**Copilot -> Claude**: Frontmatter'i basitlestir (`description` + `allowed-tools`), `$ARGUMENTS` ekle
+**Claude -> Copilot**: Add SKILL.md frontmatter (`name`, `description`, `user-invocable: true`, `argument-hint`)
+**Copilot -> Claude**: Simplify the frontmatter (`description` + `allowed-tools`), add `$ARGUMENTS`
 
 
-## Keychain Token Erisimi
+## Keychain Token Access
 
-| Islem | Token Kaynagi |
+| Operation | Token Source |
 |-------|---------------|
 | `gh` CLI (personal) | `{owner}` gh auth (Keychain) |
 | `gh` CLI (work) | `${USER}_{work-gh-alias}` gh auth (Keychain) |
-| npm publish | `NODE_AUTH_TOKEN` — CI'da `GITHUB_TOKEN`, local'de Keychain PAT |
+| npm publish | `NODE_AUTH_TOKEN`  -  `GITHUB_TOKEN` in CI, Keychain PAT locally |
 
 ```bash
-gh auth switch --user {owner}  # personal repolar icin
+gh auth switch --user {owner}  # for personal repos
 ```

package/pipeline/skills/shared/core/multi-agent-test/SKILL.md

@@ -1,16 +1,16 @@
 ---
 name: multi-agent-test
 language: en
-description: "UI Bug Hunter — iOS Simulator (simctl) + Android Emulator (adb). Auto-detects platform. Screenshot + tap + analyze on the booted device. The Phase 5 Manual Test flow lives at multi-agent-manual-test."
+description: "UI Bug Hunter  -  iOS Simulator (simctl) + Android Emulator (adb). Auto-detects platform. Screenshot + tap + analyze on the booted device. The Phase 5 Manual Test flow lives at multi-agent-manual-test."
 user-invocable: true
-argument-hint: '[scenario] — e.g. "dark mode" | "accessibility" | "dynamic type" | "screenshot tr" | "store-ready" | (empty = full sweep)'
+argument-hint: '[scenario]  -  e.g. "dark mode" | "accessibility" | "dynamic type" | "screenshot tr" | "store-ready" | (empty = full sweep)'
 ---
 
-# multi-agent-test — UI Bug Hunter
+# multi-agent-test  -  UI Bug Hunter
 
 Mobile UI test runner. Boots a simulator / emulator, drives it via MCP tools, and audits the running app for visual / accessibility / platform issues. Auto-detects iOS vs Android from cwd.
 
-**Input**: $ARGUMENTS (optional — test scenario tag).
+**Input**: $ARGUMENTS (optional  -  test scenario tag).
 
 ## Dispatcher
 
@@ -22,7 +22,7 @@ $HOME/.copilot/multi-agent/sim-test.md
 
 (Equivalent on Claude Code: `$HOME/.claude/commands/sim-test.md`.)
 
-Pass `$ARGUMENTS` through verbatim — the target doc picks the right test matrix based on the argument.
+Pass `$ARGUMENTS` through verbatim  -  the target doc picks the right test matrix based on the argument.
 
 ## Quick reference
 

package/pipeline/skills/shared/core/multi-agent-update/SKILL.md

@@ -1,23 +1,23 @@
 ---
 name: multi-agent-update
-language: tr
+language: en
 description: "Update the pipeline to the latest version: git pull, install, migrate."
 user-invocable: true
 argument-hint: ""
 ---
 
-# multi-agent-update — Pipeline Güncelleme
+# multi-agent-update  -  Pipeline Update
 
-Tek komutla pipeline'ı güncelle. Preferences korunur, sadece skill/script/schema dosyaları yenilenir.
+Update the pipeline with a single command. Preferences are preserved; only skill/script/schema files are refreshed.
 
 ## Steps
 
-1. Pipeline repo'yu bul (`~/multi-agent-pipeline` veya `~/dev/multi-agent-pipeline`)
-2. Mevcut versiyonu kaydet
+1. Find the pipeline repo (`~/multi-agent-pipeline` or `~/dev/multi-agent-pipeline`)
+2. Record the current version
 3. `git pull origin main`
 4. `node install.js --all` (Claude + Copilot)
-5. `node migrate-prefs.mjs` (schema upgrade varsa)
-6. Yeni versiyonu göster + changelog
+5. `node migrate-prefs.mjs` (if there is a schema upgrade)
+6. Show the new version + changelog
 7. Smoke test (schema + cross-cli)
 
 ## Usage
@@ -26,9 +26,9 @@ Tek komutla pipeline'ı güncelle. Preferences korunur, sadece skill/script/sche
 /multi-agent-update
 ```
 
-Çıktı:
+Output:
 ```
-v3.6.0 → v3.7.0 güncellendi
-  5 commit, 25 dosya değişti
+v3.6.0 → v3.7.0 updated
+  5 commits, 25 files changed
   schema-validation: 27/27 pass
 ```