@mmerterden/multi-agent-pipeline 8.6.1 → 10.0.6

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

@@ -0,0 +1,55 @@
+---
+name: multi-agent-analysis
+language: en
+description: "Standalone feature-spec analysis (v3 template). Platform-agnostic concept layer with repo-driven convention extraction and per-platform Pass B render. 23 main sections + 3 footer in Full mode; 7 sections in Lite mode (auto for small features). Collects Figma / Swagger / Confluence / Jira / Standards / Firebase / repo inputs, then stops. Does not chain into dev or create branches."
+user-invocable: true
+argument-hint: "[\"<analysis-name>\"] [--lite | --full] [--no-cache] [--preview-conventions]"
+---
+
+# multi-agent-analysis - Feature Spec Analysis (v3)
+
+**Input**: $ARGUMENTS (optional analysis name, e.g. `"FlightStatus"`)
+
+Produces a stakeholder-ready, platform-agnostic feature-spec document set (one markdown file per selected platform) before any implementation starts. Do not confuse with the orchestrator's Phase 1 (which is an in-pipeline stack detector). This command is **independent and side-effect free**: no branches, worktrees, commits, or PRs.
+
+> **Language**: Per `refs/rules.md` Language Application matrix - instruction prose stays English. `AskUserQuestion.label` and `header` stay English. `question` and `description` follow `outputLanguage`. The emitted document body follows `outputLanguage` (`tr` or `en`).
+
+## When to use
+
+- Before kicking off a new feature: design + API + business rules + architecture plan + test strategy crystallized into one per-platform document set
+- To refresh a stale Confluence spec page
+- For API-only work (no Figma) or frontend-only work (no API) - the omission rule keeps the output clean
+
+## Template (v3)
+
+Full mode renders 23 main sections + 3 footer sections (Glossary, Changelog, References). Lite mode renders 7 sections (Summary, Goals + Non-Goals, User Stories, API Contracts, Architecture, Files to Add, References) and auto-activates for small features via three scored signals; `--lite` / `--full` flags always win.
+
+**Section omission**: zero-evidence sections are dropped entirely (no "TBD" placeholder); numbering re-flows to stay sequential. Sections 1, 2, 4, 9, 13, 14, 20, 21 are never omitted.
+
+**Two-pass render**: Pass A computes the shared logical content once; Pass B projects it onto each selected platform using conventions extracted from the repos (Phase 1c, seven pattern groups with confidence levels). Every projected cell carries an evidence footnote. A convention preview gate lets the user approve or override cells before any file renders.
+
+## Flow
+
+| Phase | Action |
+|-------|--------|
+| 0. Intake | Analysis name + account picker + platform multi-select (iOS / Android / Backend / Frontend) + repo multi-select per platform + 6-question URL batch (Figma / Swagger / Confluence / Jira / Standards / Firebase - each independently skippable) |
+| 1. Fetch | Parallel Swagger / Confluence / Figma (3-tier chain) / Jira / Standards / Firebase fetch + repo-evidence collector (13 buckets) + Code Connect index + convention extraction (Phase 1c) |
+| 2. Synth | Pass A shared synthesis, Pass B preview gate, per-platform Pass B render, schema validation |
+| 3. Humanize + Buffer | Resolve `outputLanguage`, render drafts to `/tmp`, humanizer pass, punctuation gate |
+| 3.5 Output picker | Local file (default) / Confluence page / Jira description (multi-select, asked only after drafts exist) |
+| 4. Dispatch + Report | Write per-platform files, post Confluence/Jira on request, report. **Stop.** |
+
+When the rendered Section 20 (Risks and Open Questions) has open rows, the report suggests `multi-agent-analysis-resolve` to close them interactively.
+
+## Detailed implementation
+
+Full steps: `pipeline/commands/multi-agent/analysis.md`.
+Template master copy: `pipeline/commands/multi-agent/refs/analysis-template.md`.
+Schema: `pipeline/schemas/analysis-spec.schema.json`.
+Convention extractor: `pipeline/lib/extract-conventions.sh` (output contract: `pipeline/schemas/conventions-output.schema.json`).
+
+## Notes
+
+- Output file naming: `analysis/<feature>-<platform>.md`, one per selected platform.
+- The `analysis/` directory is not gitignored, but no auto-commit happens.
+- If Confluence / Jira POST returns 401 / 403, the command surfaces the error and offers a Local fallback.

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

@@ -0,0 +1,48 @@
+---
+name: multi-agent-analysis-resolve
+language: en
+description: "Resolve the Section 20 Risks and Open Questions of an analysis v3 document one row at a time. Proposes up to 3 source-labeled answer candidates per row (from evidence / from repo / AI reasoned), merges the chosen answer into the target body section, and updates the doc in place with a changelog bump. Companion to multi-agent-analysis."
+user-invocable: true
+argument-hint: "[path/to/analysis/<feature>-<platform>.md] [--autonomous]"
+---
+
+# multi-agent-analysis-resolve - Open Question Resolver for Analysis Docs
+
+**Input**: $ARGUMENTS (optional doc path; auto-globbed from `analysis/*-{ios,android,backend,frontend}.md` when empty)
+
+Companion to `multi-agent-analysis`. Walks the open rows of Section 20 (Risks and Open Questions) one at a time, proposes source-labeled answer candidates, and merges the chosen answer into the proper body section. The doc is authoritative and forward-looking; the resolver never invents an answer.
+
+> **Language**: instruction prose stays English; picker `question` / `description` follow `outputLanguage`; fragments written INTO the doc follow the doc's own front-matter `language` field.
+
+## Core rules
+
+- **One question per picker call** - never batch Section 20 rows; sequential resolution keeps each decision traceable.
+- **Up to 3 candidates + Defer per question.** Sources, never blended: `From evidence` (the doc's own sections and citations), `From repo` (one batched code-exploration pass with `file:line` citations), `AI reasoned` (one-line rationale required).
+- **Never invent.** No credible candidate means only Defer and free-text remain.
+- **Stop tokens** typed into the free-text field halt cleanly: `stop`, `pause`, `dur`, `kes`.
+- **Save after every answer** - atomic full-file writes; interruption loses nothing.
+- **No Figma access.** Rows that need new design information get only Defer plus a printed recommendation to re-run `multi-agent-analysis`. Repo reads and convention re-extraction are allowed.
+- **No auto-commit**; the user reviews the diff and commits manually.
+- **Status enum fixed**: `Acik / Open`, `Girdi bekleniyor / Pending input`, `Karar verildi / Decided`. Resolved rows stay in the table as a decision log with a trailing `[Resolved: <value> - <source>]` fragment.
+
+## Flow
+
+| Phase | Action |
+|-------|--------|
+| 0. Intake | Doc picker (auto-glob), repo root for `From repo` candidates, mode (interactive / autonomous) |
+| 1. Parse | Front-matter + Section 20 rows + reasoning context; classify each row (convention-fallback / reuse-vs-new / citation-tbd / legacy-decision / standards-conflict / design-gap / generic); one batched repo lookup |
+| 2. Resolve | Sequential loop: candidates per class, picker, merge into target section, save; follow-up questions insert immediately after the current row |
+| 3. Finalize | Optional sibling propagation (verbatim-matching rows in sibling platform files, one approval question), changelog bump, punctuation gate, report |
+
+## Detailed implementation
+
+Full steps: `pipeline/commands/multi-agent/analysis-resolve.md`.
+Section 20 / changelog contracts: `pipeline/commands/multi-agent/refs/analysis-template.md`.
+Convention defaults: `pipeline/commands/multi-agent/refs/conventions-defaults.md`.
+
+## Notes
+
+- Convention-fallback resolutions rewrite the affected Section 13 cell footnote to `^[user-override: resolved via analysis-resolve <date>]`.
+- Repo-sourced answers describing current behavior merge as `> Legacy reference: <text> (file:line)` blockquotes, never as primary content.
+- `evidence_digest` and the `generated` timestamp in front-matter stay untouched; only the changelog records the revision.
+- Re-running skips `Karar verildi / Decided` rows (idempotent).

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

@@ -1,12 +1,12 @@
 ---
 name: multi-agent-autopilot
-language: tr
+language: en
 description: "Launch any task in autopilot mode: skips every confirmation, runs end-to-end autonomously."
 user-invocable: true
-argument-hint: '"task" — issue URL, Jira ID, free-text, or #id (for resume)'
+argument-hint: '"task"  -  issue URL, Jira ID, free-text, or #id (for resume)'
 ---
 
-# multi-agent autopilot — Autonomous Pipeline
+# multi-agent autopilot  -  Autonomous Pipeline
 
 **Input**: $ARGUMENTS
 
@@ -14,12 +14,12 @@ Run the task end-to-end with no confirmations.
 
 ## What changes
 
-| Faz | Normal | Autopilot |
+| Phase | Normal | Autopilot |
 |-----|--------|-----------|
-| Phase 2 (Plan) | "Devam edeyim mi?" → bekle | Direkt Phase 3'e geç |
-| Phase 5 (Test) | "Test etmek ister misin?" → bekle | Atla → Phase 6 |
-| Phase 6 (Commit) | "Commit atayım mı?" → bekle | Otomatik commit + push |
-| Phase 6 (PR) | "PR açayım mı?" → bekle | Otomatik PR oluştur |
+| Phase 2 (Plan) | "Shall I continue?" → wait | Go straight to Phase 3 |
+| Phase 5 (Test) | "Do you want to test?" → wait | Skip → Phase 6 |
+| Phase 6 (Commit) | "Shall I commit?" → wait | Automatic commit + push |
+| Phase 6 (PR) | "Shall I open a PR?" → wait | Create PR automatically |
 
 ## What is NEVER skipped
 
@@ -30,22 +30,22 @@ Run the task end-to-end with no confirmations.
 ## Usage
 
 ```
-# GitHub Issue ile
+# With a GitHub Issue
 /multi-agent:autopilot https://github.com/.../issues/316
 
-# Jira ID ile
+# With a Jira ID
 /multi-agent:autopilot PROJ-12345
 
-# Free-text ile
+# With free-text
 /multi-agent:autopilot LoginView dark mode fix
 
-# Durmuş task'ı autopilot ile devam ettir
+# Resume a stopped task with autopilot
 /multi-agent:autopilot resume #3
 ```
 
 ## Steps
 
-1. **Input parse et** — Normal multi-agent formatları
-2. **Autopilot flag'ı set et** — `agent-state.json`'a `"autopilot": true`
-3. **multi-agent pipeline'ı başlat** — Tüm onaylar skip edilir
-4. **Hata durumunda** — 3 retry sonra hala fail → pause, kullanıcıya sor
+1. **Parse the input**  -  Normal multi-agent formats
+2. **Set the autopilot flag**  -  `"autopilot": true` in `agent-state.json`
+3. **Start the multi-agent pipeline**  -  All confirmations are skipped
+4. **On failure**  -  After 3 retries still failing → pause, ask the user

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

@@ -0,0 +1,48 @@
+---
+name: multi-agent-build-optimize
+language: en
+description: "Wrapper that dispatches to xcode-build-orchestrator on iOS repos. Benchmarks the current Xcode build, runs compilation / project / SPM analyzers, produces a recommend-first optimization plan in .build-benchmark/, and re-benchmarks after the developer approves changes. Fails fast on non-iOS stacks."
+user-invocable: true
+argument-hint: "(none - operates on current repo)"
+---
+
+# multi-agent-build-optimize - Xcode Build Performance Wrapper
+
+**Input**: $ARGUMENTS (none - operates on the current repo)
+
+Thin wrapper around the vendored `xcode-build-orchestrator` skill so iOS users do not have to remember the underlying skill name. Recommend-first: no project files are modified without explicit developer approval. Output lands in `.build-benchmark/` in the cwd.
+
+> **Language**: Per `refs/rules.md` Language Application matrix - instruction prose stays English.
+
+## When to use
+
+- Slow clean or incremental Xcode builds
+- Build settings audit before a release branch cut
+- SPM resolution time concerns, plugin overhead suspicions
+- Pre-CI optimization pass when build wall-clock dominates PR cycle time
+
+## Flow
+
+| Phase | Action |
+|-------|--------|
+| 0. Stack detect | Find `.xcodeproj` / `.xcworkspace` / `Package.swift`. On non-iOS stacks, exit with explanatory error pointing to platform-appropriate perf skill. |
+| 1. Project context | Identify project + scheme + configuration + destination. Single AskUserQuestion when multiple schemes exist. |
+| 2. Dispatch analyze | Skill tool: `xcode-build-orchestrator`. Orchestrator runs benchmark + 3 specialists, writes `.build-benchmark/optimization-plan.md`. No project file edits. |
+| 3. Review handoff | Surface the plan path to the user for explicit approval via checkboxes in the plan. |
+| 4. Dispatch fix | When the user signals approval, Skill tool: `xcode-build-fixer`. Applies approved items, re-benchmarks, appends wall-clock delta. |
+
+## Side-effect contract
+
+- Phase 1 writes only inside `.build-benchmark/`. No project file edits, no branches, no worktrees, no commits, no PRs.
+- Phase 2 edits build settings / source / packages / scripts the developer approved. Re-benchmarks to verify.
+
+## Detailed implementation
+
+Full steps: `pipeline/commands/multi-agent/build-optimize.md`.
+Upstream attribution: `pipeline/skills/shared/external/NOTICE-xcode-build-skills.md`.
+
+## Notes
+
+- Wall-clock build time is the primary metric; parallel CPU savings are labeled separately.
+- Python 3 standard library is the only runtime dependency (vendored upstream uses no pip packages).
+- Default `outputLanguage` follows the pipeline user preference for any wrapper-authored prompts. Upstream skill output (the plan body) is English by upstream convention.

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

@@ -1,21 +1,21 @@
 ---
 name: multi-agent-channels
 language: en
-description: "Multi-channel reporter — Jira/Confluence/Wiki/PR description. Multi-select channels + content, humanizer pass, reviewer-preserving Bitbucket PR PUT. Phase 7 delegates to this skill; users can invoke post-hoc by Jira ID / PR URL / branch."
+description: "Multi-channel reporter  -  Jira/Confluence/Wiki/PR description. Multi-select channels + content, humanizer pass, reviewer-preserving Bitbucket PR PUT. Phase 7 delegates to this skill; users can invoke post-hoc by Jira ID / PR URL / branch."
 user-invocable: true
 argument-hint: '<Jira-id | PR-url | #N | Jira-url> [--channels pr,jira,confluence,wiki] [--content normal,technical,test,auto-diff,note] [--message "..."] [--message-file path] [--dry-run] [--append] [--ready]'
 ---
 
-# multi-agent-channels — Multi-Channel Reporter
+# multi-agent-channels  -  Multi-Channel Reporter
 
-> **TLDR** — Single entry point for posting task reports to external channels. Supports Jira, Confluence, Wiki (component-only), and PR description updates. Multi-select channels × multi-select content sources. Phase 7 of the pipeline delegates to this skill; users can also invoke it post-hoc by Jira ID / PR URL / branch.
+> **TLDR**  -  Single entry point for posting task reports to external channels. Supports Jira, Confluence, Wiki (component-only), and PR description updates. Multi-select channels × multi-select content sources. Phase 7 of the pipeline delegates to this skill; users can also invoke it post-hoc by Jira ID / PR URL / branch.
 >
-> **Replaces the old enrich skill in v5.7+** — all enrich capabilities (diff auto-summarize, manual mode, reviewer-preserving Bitbucket PR PUT) are preserved and extended with two additional channels (Confluence, Wiki).
+> **Replaces the old enrich skill in v5.7+**  -  all enrich capabilities (diff auto-summarize, manual mode, reviewer-preserving Bitbucket PR PUT) are preserved and extended with two additional channels (Confluence, Wiki).
 
 **Copilot CLI invocation:** `multi-agent-channels <target>` (top-level skill, dash-separated per Copilot no-namespace convention).
 **Claude Code equivalent:** `/multi-agent:channels <target>` (slash namespace).
 
-Both CLIs read the same underlying logic — see `~/.claude/commands/multi-agent/channels.md` (Claude) or this file (Copilot). Prompts MUST be byte-identical; `smoke-cross-cli-behavior.sh` asserts parity.
+Both CLIs read the same underlying logic  -  see `~/.claude/commands/multi-agent/channels.md` (Claude) or this file (Copilot). Prompts MUST be byte-identical; `smoke-cross-cli-behavior.sh` asserts parity.
 
 ## Input
 
@@ -27,7 +27,7 @@ multi-agent-channels https://github.com/<org>/<repo>/pull/N
 multi-agent-channels https://<bitbucket-host>/projects/.../pull-requests/N
 multi-agent-channels https://<jira-host>/browse/PROJ-12345
 
-multi-agent-channels PROJ-12345 --channels jira,confluence # non-interactive kanal
+multi-agent-channels PROJ-12345 --channels jira,confluence # non-interactive channel
 multi-agent-channels PROJ-12345 --content auto-diff        # non-interactive content
 multi-agent-channels PROJ-12345 --message "root: ..."      # manual source
 multi-agent-channels PROJ-12345 --message-file notes.md    # manual, long
@@ -36,13 +36,13 @@ multi-agent-channels PROJ-12345 --dry-run                  # preview, no POST
 
 ## Flow
 
-1. **Target resolution** — Parse argument, classify (Jira-id, Jira-url, PR-url GitHub or Bitbucket, GitHub-issue-number, empty→cwd+branch). Resolve linked entities (Jira→PR, PR→Jira). Detect remote type.
-2. **Context source detection** — auto-pick best available: pipeline log (`$HOME/.claude/logs/multi-agent/<project>/<task-id>/agent-log.md` matching jiraId), PR diff (`gh pr diff` or Bitbucket `/diff?contextLines=5`), or manual `--message`.
-3. **Menu (multi-select)** — kanal + content, previous selections pre-ticked from `prefs.global.reportChannels` + `prefs.global.reportContent`. Greyed-out rules per context availability.
-4. **Mode short-circuit** — `--channels X,Y` + `--content A,B` flags skip menu. Autopilot ALWAYS pauses at the menu (v5.7+ Phase 7 exception).
-5. **Generator** — for each selected content source, produce a section body. Humanizer pass per channel separately.
-6. **Channel dispatch** — parallel adapter calls: PR description (reviewer-preserving PUT on Bitbucket), Jira comment (wiki markup), Confluence page (storage format + parent page), Wiki (component adapter — Case A scope multi-select or Case B precondition menu).
-7. **Summary** — per-adapter status line, persist selections to prefs.
+1. **Target resolution**  -  Parse argument, classify (Jira-id, Jira-url, PR-url GitHub or Bitbucket, GitHub-issue-number, empty→cwd+branch). Resolve linked entities (Jira→PR, PR→Jira). Detect remote type.
+2. **Context source detection**  -  auto-pick best available: pipeline log (`$HOME/.claude/logs/multi-agent/<project>/<task-id>/agent-log.md` matching jiraId), PR diff (`gh pr diff` or Bitbucket `/diff?contextLines=5`), or manual `--message`.
+3. **Menu (multi-select)**  -  channel + content, previous selections pre-ticked from `prefs.global.reportChannels` + `prefs.global.reportContent`. Greyed-out rules per context availability.
+4. **Mode short-circuit**  -  `--channels X,Y` + `--content A,B` flags skip menu. Autopilot ALWAYS pauses at the menu (v5.7+ Phase 7 exception).
+5. **Generator**  -  for each selected content source, produce a section body. Humanizer pass per channel separately.
+6. **Channel dispatch**  -  parallel adapter calls: PR description (reviewer-preserving PUT on Bitbucket), Jira comment (wiki markup), Confluence page (storage format + parent page), Wiki (component adapter  -  Case A scope multi-select or Case B precondition menu).
+7. **Summary**  -  per-adapter status line, persist selections to prefs.
 
 ## Multi-select menu
 
@@ -57,7 +57,7 @@ Rendered in English (`promptLanguage` is locked to `en`).
 └───────────────────────────────────────────────────────
 
 ┌─ İçerik ──────────────────────────────────────────────
-│   [x] Normal analiz       (Phase 1+2+4'ten — high-level impact + risks)
+│   [x] Normal analiz       (Phase 1+2+4'ten  -  high-level impact + risks)
 │   [ ] Teknik analiz       (Changes · Architecture · Dependencies)
 │   [x] Test senaryoları    (Phase 1+2+4'ten)
 │   [ ] PR diff'ten auto-gen (PR varsa diff'i summarize eder)
@@ -100,7 +100,7 @@ curl -s -X PUT -u "$BB_USER:$BB_TOKEN" -H "Content-Type: application/json" \
 
 **(strict):** every Bitbucket PR PUT MUST include `reviewers`, `fromRef`, `toRef`, `draft`. Omitting any resets that field server-side (default reviewers wiped, branch link broken).
 
-GitHub uses `gh pr edit --body-file` — reviewers independent, no risk.
+GitHub uses `gh pr edit --body-file`  -  reviewers independent, no risk.
 
 ### Jira comment (wiki markup)
 
@@ -110,7 +110,7 @@ PR: {prUrl}
 *Root cause:* {single paragraph summary}
 
 *Solution:*
-- {{file.ext → func}} — {one line}
+- {{file.ext → func}}  -  {one line}
 
 *Changed files:* file.ext (+N/-M), other.ext (+N/-M)
 
@@ -123,40 +123,40 @@ First line: PR URL (one-click jump). POST `/rest/api/2/issue/{id}/comment` with
 
 ### Confluence page
 
-1. Token from `keychainMapping.confluence` via `~/.copilot/lib/credential-store.sh get` — missing→Token Save Flow from setup skill.
+1. Token from `keychainMapping.confluence` via `~/.copilot/lib/credential-store.sh get`  -  missing→Token Save Flow from setup skill.
 2. Parent page URL prompt; recent URLs from `prefs.projects[<project>].confluenceUrls` (LRU, max 5).
 3. Extract `spaceKey` + `parentId` from URL.
-4. Auto-suggest page title `"{jiraId} — {taskTitle}"`, editable.
-5. POST `/rest/api/content` — humanizer'd storage-format body.
+4. Auto-suggest page title `"{jiraId}  -  {taskTitle}"`, editable.
+5. POST `/rest/api/content`  -  humanizer'd storage-format body.
 6. Save URL to prefs for next run.
 
 ### Wiki (component tasks only)
 
-**Case A — preconditions met** (`taskType=component` + `wiki.enabled=true`): scope multi-select menu offers Main page / iOS sub-page / Screenshots / Index updates / Diğer. Adapter dispatches with selected scope.
+**Case A  -  preconditions met** (`taskType=component` + `wiki.enabled=true`): scope multi-select menu offers Main page / iOS sub-page / Screenshots / Index updates / Other. Adapter dispatches with selected scope.
 
-**Case B — preconditions missing**: actionable menu — [1] setup Figma config, [2] skip this run, [3] disable forever, [4] manual note. Full contract in `refs/wiki-capture.md`.
+**Case B  -  preconditions missing**: actionable menu  -  [1] setup Figma config, [2] skip this run, [3] disable forever, [4] manual note. Full contract in `refs/wiki-capture.md`.
 
 ## Output template (aggregated across selected content)
 
 ```markdown
 ### Analysis                        ← if "Normal analiz" selected
-{impact summary, risks — high-level}
+{impact summary, risks  -  high-level}
 
 ### Technical Details               ← if "Teknik analiz" selected
 #### Changes
-{Per changed-file-group, what changed + why — from Phase 3 dev log}
+{Per changed-file-group, what changed + why  -  from Phase 3 dev log}
 #### Architecture
-{Structural decisions, pattern changes — from Phase 2 plan}
+{Structural decisions, pattern changes  -  from Phase 2 plan}
 #### Dependencies
-{New imports / frameworks / packages — from git diff --stat, or "None"}
+{New imports / frameworks / packages  -  from git diff --stat, or "None"}
 
 ### Root Cause                      ← if "Auto-diff" selected
-{single paragraph — from diff}
+{single paragraph  -  from diff}
 
 - `path/to/File.ext → funcName`: {why it broke}
 
 ### Solution                        ← if "Auto-diff" selected
-- `path/to/File.ext:LINE-LINE` — {change, one line}
+- `path/to/File.ext:LINE-LINE`  -  {change, one line}
 
 ### Changed Files                   ← if "Auto-diff" selected
 | File | +/- |
@@ -172,7 +172,7 @@ First line: PR URL (one-click jump). POST `/rest/api/2/issue/{id}/comment` with
 {user message}
 
 ### Store compliance                ← auto-appended if cached compliance report exists
-{summary line — see below}
+{summary line  -  see below}
 
 Ref: {jiraId}
 ```
@@ -190,11 +190,11 @@ If cached report exists AND any selected channel is PR / Jira / Confluence, appe
 
 | Blocker count | Output |
 |---|---|
-| `errors > 0` | `### Store compliance` + `⚠️ {N} blocker(s), {M} warning(s)` + per-blocker `- \`{ruleID}\` — {ref}: {message}` (cap 5 rows, rest `+N more`) |
-| `errors == 0, warnings > 0` | `### Store compliance` + `✅ No blockers. {M} warning(s) — see multi-agent-test "store-ready" for detail.` |
-| `errors == 0, warnings == 0` | Skip — don't pollute PR body |
+| `errors > 0` | `### Store compliance` + `⚠️ {N} blocker(s), {M} warning(s)` + per-blocker `- \`{ruleID}\`  -  {ref}: {message}` (cap 5 rows, rest `+N more`) |
+| `errors == 0, warnings > 0` | `### Store compliance` + `✅ No blockers. {M} warning(s)  -  see multi-agent-test "store-ready" for detail.` |
+| `errors == 0, warnings == 0` | Skip  -  don't pollute PR body |
 
-`ruleID` + policy ref stay verbatim (apple-archive-compliance / google-play-compliance catalog identifiers — no translation).
+`ruleID` + policy ref stay verbatim (apple-archive-compliance / google-play-compliance catalog identifiers  -  no translation).
 
 If no cached report: skip silently. Augmentation, not a gate.
 
@@ -204,9 +204,9 @@ Target length: < 80 lines (fits one screen). Auto-diff capped at 5 lines per sec
 
 | Flag | Effect |
 |------|--------|
-| `--channels pr,jira,confluence,wiki` | Non-interactive kanal selection. |
+| `--channels pr,jira,confluence,wiki` | Non-interactive channel selection. |
 | `--content normal,test,auto-diff,note` | Non-interactive content selection. |
-| `--message "..."` | Manual mode — user text as source. Forces `content=note`. |
+| `--message "..."` | Manual mode  -  user text as source. Forces `content=note`. |
 | `--message-file path` | Manual mode, long message from file. |
 | `--append` | PR description: append instead of replace. |
 | `--dry-run` | Generate + print, no POST. |
@@ -215,13 +215,13 @@ Target length: < 80 lines (fits one screen). Auto-diff capped at 5 lines per sec
 
 ## Required rules
 
-- Bitbucket reviewer preservation — every PR PUT MUST carry current `reviewers`, `fromRef`, `toRef`, `draft`.
+- Bitbucket reviewer preservation  -  every PR PUT MUST carry current `reviewers`, `fromRef`, `toRef`, `draft`.
 - Default is **replace** (not append) for PR description; `--append` opt-in.
 - Real newlines + no HTML entities in ALL bodies (Jira, Confluence, PR).
-- Humanizer per-channel — each body runs humanizer independently (tones differ).
-- No markers — full replace each run, no `<!-- channels:start -->` bookmarks.
+- Humanizer per-channel  -  each body runs humanizer independently (tones differ).
+- No markers  -  full replace each run, no `<!-- channels:start -->` bookmarks.
 - Every body item references a file/symbol/line from diff or pipeline log. No generic sentences.
-- Adapter failures are non-blocking — one channel failing does NOT abort others.
+- Adapter failures are non-blocking  -  one channel failing does NOT abort others.
 
 ## Error handling
 
@@ -260,7 +260,7 @@ Phase 7 builds a state bundle and invokes this skill internally. Responsibilitie
 }
 ```
 
-**Autopilot pause contract:** Phase 7 ALWAYS pauses at the channels menu — 30-min timeout → session ends cleanly → resumable via `/multi-agent:resume`. Full contract in `refs/phases/modes.md` + `refs/phases/phase-7-report.md`.
+**Autopilot pause contract:** Phase 7 ALWAYS pauses at the channels menu  -  30-min timeout → session ends cleanly → resumable via `/multi-agent:resume`. Full contract in `refs/phases/modes.md` + `refs/phases/phase-7-report.md`.
 
 ## Cross-CLI parity
 
@@ -296,5 +296,5 @@ multi-agent-channels https://<bitbucket>/.../pull-requests/42 --dry-run
 
 multi-agent-channels --message "root: PNR empty, UI silent. fix: length>0 guard in HomeVC.m"
   → auto-diff from cwd+branch PR + user note combined
-  → posts to default kanals (PR + Jira)
+  → posts to default channels (PR + Jira)
 ```

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

@@ -1,63 +1,66 @@
 ---
 name: multi-agent-delete
-language: tr
-description: "Uninstall the pipeline from every CLI (Claude / Copilot / Cursor / Windsurf / Cline). Keychain access tokens are left untouched. Asks for double confirmation."
+language: en
+description: "Uninstall the pipeline from every CLI (Claude / Copilot / Cursor / Copilot Chat). Keychain access tokens are left untouched. Asks for double confirmation."
 user-invocable: true
-argument-hint: "[--dry-run] [--claude] [--copilot] [--cursor] [--windsurf] [--cline] [--target=<path>]"
+argument-hint: "[--dry-run] [--claude] [--copilot] [--cursor] [--copilot-chat] [--target=<path>]"
 ---
 
-# multi-agent-delete — Token-Preserving Uninstall
+# multi-agent-delete  -  Token-Preserving Uninstall
 
 **Input**: $ARGUMENTS
 
-Pipeline'ın kendisini sistemden kaldırır. **`multi-agent-purge`'den farklıdır:**
+Removes the pipeline itself from the system. **Different from `multi-agent-purge`:**
 
-| Komut | Ne siler |
+| Command | What it deletes |
 |---|---|
-| `multi-agent-purge` | Aktif task'ların worktree / branch / log / state'leri (geliştirme verisi) |
-| `multi-agent-delete` | Pipeline'ın kendisi: skills, commands, agents, scripts, rules — her CLI'dan |
+| `multi-agent-purge` | Active tasks' worktree / branch / log / state (development data) |
+| `multi-agent-delete` | The pipeline itself: skills, commands, agents, scripts, rules  -  from every CLI |
 
 ## Never deleted
 
-- **Keychain / Credential Manager / libsecret** içindeki personal access token'lar (GitHub, Jira, Bitbucket, Confluence, Telegram, Vercel, Firebase, vs.)
-- `~/.claude/CLAUDE.md` ve `~/.claude/multi-agent-preferences.json` (kullanıcı veriyse)
-- `<!-- multi-agent-pipeline:begin/end -->` marker'ları DIŞINDAKİ kullanıcı içerikleri (`.windsurfrules`, `copilot-instructions.md`)
+- Personal access tokens in the **Keychain / Credential Manager / libsecret** (GitHub, Jira, Bitbucket, Confluence, Telegram, Vercel, Firebase, etc.)
+- `~/.claude/CLAUDE.md` and `~/.claude/multi-agent-preferences.json` (if the user provided them)
+- User content OUTSIDE the `<!-- multi-agent-pipeline:begin/end -->` markers (`.cursorrules`, `copilot-instructions.md`)
 
 ## Steps
 
-1. **Kapsam belirle** — `$ARGUMENTS`'ı parse et:
-   - Hiçbir hedef flag yoksa: tüm yüklü hedefler (varsayılan)
-   - `--claude / --copilot / --cursor / --windsurf / --cline`: seçici
-   - `--target=<path>`: adapter hedefi (default cwd)
-   - `--dry-run`: sadece raporla, hiçbir şey silme
+1. **Determine the scope**  -  parse `$ARGUMENTS`:
+   - No target flag: all installed targets (default)
+   - `--claude / --copilot / --cursor / --copilot-chat`: selective
+   - `--target=<path>`: adapter target (default cwd)
+   - `--dry-run`: only report, delete nothing
 
-2. **Önizleme göster** (`--dry-run` ile script'i çalıştır):
+2. **Show a preview** (run the script with `--dry-run`):
    ```bash
    node "$HOME/.copilot/scripts/uninstall.mjs" --dry-run --yes <flags>
    ```
-   Çıktıyı kullanıcıya ham haliyle göster.
+   Show the output to the user verbatim.
 
-3. **İlk onay**:
-   > "Yukarıdakiler silinecek. Token'lar dokunulmayacak. Devam? (y/N)"
+3. **First confirmation**  -  native `AskUserQuestion` picker (no typed y/N):
+   - `question`: "Delete the pipeline from the listed targets? Tokens are NOT touched." (`outputLanguage`)
+   - `header`: "Delete" · `options`: `{ label: "Continue", description: "Proceed to the final confirmation" }`, `{ label: "Cancel", description: "Keep everything installed" }`
+   - **Cancel** → exit.
 
-4. **İkinci onay** (paranoya gate):
-   > "Geri alınamaz. Onaylamak için 'delete' yaz:"
-   - `delete` değilse → iptal et.
+4. **Second confirmation** (paranoia gate)  -  a second `AskUserQuestion` picker:
+   - `question`: "This is irreversible. Permanently remove the pipeline files now?" (`outputLanguage`)
+   - `header`: "Confirm" · `options`: `{ label: "Delete permanently", description: "Remove the distributed files; tokens are preserved" }`, `{ label: "Cancel", description: "Abort, change nothing" }`
+   - Anything other than **Delete permanently** → cancel.
 
-5. **Sil** — gerçek script'i `--yes` ile çalıştır:
+5. **Delete**  -  run the real script with `--yes`:
    ```bash
    node "$HOME/.copilot/scripts/uninstall.mjs" --yes <flags>
    ```
 
-6. **Onayla**:
+6. **Confirm**:
    ```
-   ✓ multi-agent-pipeline kaldırıldı.
-   ℹ Personal access token'lar Keychain'de korundu.
+   ✓ multi-agent-pipeline removed.
+   ℹ Personal access tokens preserved in the Keychain.
    ```
 
-7. **Yeniden kurulum** (kullanıcı isterse): `npx @mmerterden/multi-agent-pipeline install --copilot`
+7. **Reinstall** (if the user wants): `npx @mmerterden/multi-agent-pipeline install --copilot`
 
 ## Notes
 
-- `--dry-run` her zaman güvenli — sıfır yan etki.
-- Adapter hedefi cwd. Farklı bir repo için `--target=<path>`.
+- `--dry-run` is always safe  -  zero side effects.
+- The adapter target is cwd. For a different repo, use `--target=<path>`.

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

@@ -1,64 +1,64 @@
 ---
 name: multi-agent-dev
-language: tr
+language: en
 description: "Fast development mode: Init → Dev (Opus) → Test → Commit → Report. Analysis, planning, and review phases are skipped."
 user-invocable: true
-argument-hint: '"task" [autopilot] — issue URL, Jira ID, veya free-text + opsiyonel autopilot'
+argument-hint: '"task" [autopilot]  -  issue URL, Jira ID, or free-text + optional autopilot'
 ---
 
-# multi-agent dev — Fast Development Mode (--dev)
+# multi-agent dev  -  Fast Development Mode (--dev)
 
 **Input**: $ARGUMENTS
 
-5 fazlı hızlı pipeline: Init → Dev → Test → Commit → Report. Development Opus modelinde çalışır.
+A 5-phase fast pipeline: Init → Dev → Test → Commit → Report. Development runs on the Opus model.
 
-## Ne zaman kullanılır
-- Küçük değişiklikler, bugfix, hızlı feature
-- 8 fazlı pipeline gerektirmeyen basit task'lar
-- Resmi review gerektirmeyen rutin işler
+## When to use it
+- Small changes, bug fixes, quick features
+- Simple tasks that do not require the 8-phase pipeline
+- Routine work that needs no formal review
 
 ## Pipeline
 
 ```
-Phase 0: Init       → Proje tespit, worktree, branch, identity (full picker)
-Phase 3: Dev        → Opus ile doğrudan geliştirme (TDD opsiyonel)
+Phase 0: Init       → Project detection, worktree, branch, identity (full picker)
+Phase 3: Dev        → Direct development with Opus (TDD optional)
 Phase 5: Test       → User Test (interactive simulator)
 Phase 6: Commit     → Commit + push + PR
 Phase 7: Report     → Channels (Jira / Confluence / PR / Wiki)
 ```
 
-`--dev` Phase 1 (Analysis), Phase 2 (Planning + Approval Gate) ve Phase 4 (Review)'ı atlar. Phase 3 Dev modeli **Opus**'tur. Phase 0 picker, Phase 5 test, Phase 6 commit ve Phase 7 channels full pipeline ile birebir aynıdır.
+`--dev` skips Phase 1 (Analysis), Phase 2 (Planning + Approval Gate), and Phase 4 (Review). The Phase 3 Dev model is **Opus**. The Phase 0 picker, Phase 5 test, Phase 6 commit, and Phase 7 channels are identical to the full pipeline.
 
-> `--dev` sözleşmesi: plan tartışması yok, direkt geliştirmeye geçilir. Plan üzerinde konuşmak istiyorsan normal mode kullan.
+> `--dev` contract: no plan discussion, development starts directly. If you want to discuss the plan, use normal mode.
 
 ## Steps
 
-1. **Input parse et** — Aynı multi-agent formatları (GitHub Issue URL, Jira ID, free-text)
+1. **Parse the input**  -  Same multi-agent formats (GitHub Issue URL, Jira ID, free-text)
 
-2. **Phase 0: Init** — Full pipeline ile aynı (full picker: account, project, dev-context, base branch, branch name, maturity check, identity, worktree, state)
-   - `agent-state.json`'a `"mode": "dev"` ekle
+2. **Phase 0: Init**  -  Same as the full pipeline (full picker: account, project, dev-context, base branch, branch name, maturity check, identity, worktree, state)
+   - Add `"mode": "dev"` to `agent-state.json`
 
-3. **Phase 3: Dev** — **Opus model** ile:
-   - Kısa analiz (explore agent yok — doğrudan dosyalara bak)
-   - Kod yaz + build doğrula
-   - Test gerekiyorsa yaz (zorunlu değil dev modda)
+3. **Phase 3: Dev**  -  With the **Opus model**:
+   - Brief analysis (no explore agent  -  look at files directly)
+   - Write code + verify build
+   - Write tests if needed (not required in dev mode)
 
-4. **Phase 5: User Test** — Full pipeline ile aynı (interactive simulator / local-test prompt)
+4. **Phase 5: User Test**  -  Same as the full pipeline (interactive simulator / local-test prompt)
 
-5. **Phase 6: Commit** — Full pipeline ile aynı (commit + push + PR + shared-branch final confirm)
+5. **Phase 6: Commit**  -  Same as the full pipeline (commit + push + PR + shared-branch final confirm)
 
-6. **Phase 7: Report** — Full pipeline ile aynı (channels prompt: Jira / Confluence / PR description / Wiki)
+6. **Phase 7: Report**  -  Same as the full pipeline (channels prompt: Jira / Confluence / PR description / Wiki)
 
 ## Differences vs full pipeline
 
-| Özellik | Full (`/multi-agent`) | Dev (`/multi-agent:dev`) |
+| Feature | Full (`/multi-agent`) | Dev (`/multi-agent:dev`) |
 |---------|---------------------|------------------------|
-| Fazlar | 8 (0-7) | 5 (0, 3, 5, 6, 7) — 1, 2, 4 skipped |
+| Phases | 8 (0-7) | 5 (0, 3, 5, 6, 7)  -  1, 2, 4 skipped |
 | Phase 3 Dev model | Sonnet | **Opus** |
 | Phase 1 Analysis (explore agents) | ✅ | ❌ |
 | Phase 2 Planning + Approval Gate | ✅ | ❌ |
 | Phase 4 Review (parallel + triage) | ✅ | ❌ |
-| Phase 0 picker (account, repos, branch, …) | ✅ | ✅ (same) |
+| Phase 0 picker (account, repos, branch, ...) | ✅ | ✅ (same) |
 | Phase 5 User Test | ✅ | ✅ (same) |
 | Phase 7 channels (Jira / Confluence / PR / Wiki) | ✅ | ✅ (same) |
-| Süre | ~10-15 dk | ~5-7 dk |
+| Duration | ~10-15 min | ~5-7 min |