@mmerterden/multi-agent-pipeline 11.3.2 → 11.4.0

package/CHANGELOG.md

@@ -14,6 +14,29 @@ Internal file-layout changes that don't affect the slash-command surface are sti
 
 ---
 
+## [11.4.0] - 2026-07-10
+
+Review PR-picker, two readiness-review commands, and durable local-only wrappers.
+
+- **`/multi-agent:review` no-URL PR picker.** With no argument (interactive), review
+  now lists open GitHub + Bitbucket PRs in one labeled list and multi-selects which
+  to review (per-PR inline comments + approve/needs-work), instead of silently
+  defaulting to the local branch diff. Autopilot / no open PRs falls back to the
+  local diff; explicit URL/`#N`/branch still work. The Copilot twin was brought to
+  parity (input-aware + PR posting).
+- **New `/multi-agent:review-jira` + `/multi-agent:review-issue`.** Grade whether a
+  Jira issue / GitHub issue is ready for the pipeline (scope, acceptance criteria,
+  repro, design reference, API contract, stack signal, dependencies) by reusing the
+  Phase 0 maturity engine (`issue-fetcher.sh`) plus a readiness rubric, then post
+  the gaps back as a comment on the item (confirmed; autopilot auto-posts). Read-only
+  on code: no worktree, no branch, no creation. Command count 36 -> 38.
+- **Corporate alias wrappers survive updates.** `install/claude.mjs` now preserves
+  command dirs whose SKILL.md is `local-only: true` across the namespace wipe, so
+  personal `multi-agent:<name>` aliases that delegate to a private marketplace plugin
+  are no longer destroyed on every install/update (they were, before). Covered by a
+  new `smoke-wrapper-preservation.sh`. (The wrappers themselves are local-only and
+  never ship in this package.)
+
 ## [11.3.2] - 2026-07-10
 
 Command rename + website refresh.

package/install/claude.mjs

@@ -12,7 +12,7 @@
  * @module install/claude
  */
 
-import { existsSync, readFileSync, rmSync } from "fs";
+import { existsSync, readFileSync, readdirSync, rmSync, statSync, writeFileSync } from "fs";
 import { join } from "path";
 import { execSync } from "child_process";
 
@@ -76,10 +76,52 @@ function installCommands(pipelineSrc, dest, useSymlinks) {
   // linger as ghost slash commands. Other namespaces under
   // `~/.claude/commands/` are untouched.
   const ownedCmdDir = join(dest, "multi-agent");
+  // Preserve local-only alias wrappers (frontmatter `local-only: true`) across
+  // the wipe. They live ONLY under ~/.claude (never in pipeline/commands, and
+  // never synced), so without this snapshot+restore they would be destroyed on
+  // every install/update. Pipeline never ships these names, so restore is safe.
+  const preservedWrappers = snapshotLocalOnlyWrappers(ownedCmdDir);
   wipeDir(ownedCmdDir);
 
   copyDir(commandsSrc, dest, { useSymlinks });
+  const restored = restoreLocalOnlyWrappers(ownedCmdDir, preservedWrappers);
   console.log(`    -> ${countFiles(commandsSrc)} files copied to ${dest}`);
+  if (restored > 0) {
+    console.log(`    -> preserved ${restored} local-only alias wrapper(s)`);
+  }
+}
+
+// Snapshot single-level command dirs whose SKILL.md declares `local-only: true`
+// (their files are read into memory) so installCommands can restore them after
+// the namespace wipe.
+function snapshotLocalOnlyWrappers(ownedCmdDir) {
+  const out = [];
+  if (!existsSync(ownedCmdDir)) return out;
+  for (const name of readdirSync(ownedCmdDir)) {
+    const dir = join(ownedCmdDir, name);
+    const skill = join(dir, "SKILL.md");
+    if (!existsSync(skill)) continue;
+    if (!/^local-only:\s*true\s*$/m.test(readFileSync(skill, "utf-8"))) continue;
+    const files = readdirSync(dir)
+      .filter((f) => statSync(join(dir, f)).isFile())
+      .map((f) => ({ rel: f, content: readFileSync(join(dir, f), "utf-8") }));
+    out.push({ name, files });
+  }
+  return out;
+}
+
+// Restore snapshotted local-only wrappers, but never clobber a real command the
+// pipeline just installed under the same name. Returns the count restored.
+function restoreLocalOnlyWrappers(ownedCmdDir, preserved) {
+  let n = 0;
+  for (const w of preserved) {
+    const dir = join(ownedCmdDir, w.name);
+    if (existsSync(dir)) continue; // pipeline shipped a real command with this name
+    ensureDir(dir);
+    for (const f of w.files) writeFileSync(join(dir, f.rel), f.content);
+    n++;
+  }
+  return n;
 }
 
 // The pipeline's reference docs (refs/) + internal pickers live OUTSIDE the

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-pipeline",
-  "version": "11.3.2",
+  "version": "11.4.0",
   "description": "8-phase AI development pipeline with full orchestration on Claude Code and Copilot CLI. Analysis, planning, TDD, CLI-aware parallel review with consensus surfacing + Fable triage, default-FAIL evidence gates, secret + intent guards, per-phase cost ledger, persistent learnings memory, wiki generation, commit automation. Token-preserving uninstall.",
   "type": "module",
   "main": "index.js",

package/pipeline/commands/multi-agent/SKILL.md

@@ -73,7 +73,9 @@ Lib scripts (`~/.claude/lib/`):
 | `kill [id]` | Delete worktree (logs preserved). Confirm first |
 | `clear-logs` | Clean global log directory. Keep counter |
 | `purge` | Worktree + logs + counter  -  full reset (double confirm) |
-| `review` | Review current diff only (lightweight, no worktree) |
+| `review [#N\|repo#N\|PR-url\|branch]` | Parallel review of a PR or branch diff; with no input (interactive) lists open GitHub + Bitbucket PRs to multi-select. Posts per-finding inline comments + approve/needs-work on PRs. No worktree. |
+| `review-jira [KEY\|url]` | Grade a Jira issue's readiness for the pipeline (scope / AC / repro / design / API / stack), then post the gaps as a Jira comment. Read-only on code. |
+| `review-issue [#N\|repo#N\|url]` | Grade a GitHub issue's readiness for the pipeline, then post the gaps as an issue comment. Read-only on code. |
 | `analysis ["<feature>"]` | Standalone feature-spec analizi: Figma / Swagger / Confluence / Jira / repo girdileri sabit 7-bölümlük şablona dökülür, humanizer'dan geçer, Local/Confluence/Jira hedef(ler)ine post edilir. Worktree veya commit yok. Dev'e zincirleme yok. |
 | `build-optimize` | iOS-only Xcode build performance wrapper. Vendored `xcode-build-orchestrator`'a dispatch eder; benchmark + compilation / project / SPM analyzer'lar + recommend-first plan `.build-benchmark/optimization-plan.md`. Non-iOS stack'lerde fail-fast. |
 | `channels [PR-url\|#N\|Jira-url\|Jira-id] [--channels pr,jira,confluence,wiki] [--content normal,test,auto-diff,note] [--message "..."]` | Post task report to multi-select channels (PR description, Jira comment, Confluence page, Wiki pages) with multi-select content sources. Humanizer pass per-channel. Bitbucket PR updates use reviewer-preserving PUT. Phase 7 delegates to this command; also invocable post-hoc for fixes made outside the pipeline. No worktree. |
@@ -111,6 +113,8 @@ This command uses lazy loading for token efficiency. Read the relevant sub-file
 | `sync` | `$HOME/.claude/commands/multi-agent/sync/SKILL.md` |
 | `clear-logs` | Handled inline  -  scan + delete agent-log.md/agent-state.json files |
 | `review` | `$HOME/.claude/commands/multi-agent/review/SKILL.md` |
+| `review-jira` | `$HOME/.claude/commands/multi-agent/review-jira/SKILL.md` (loads `$HOME/.claude/multi-agent-refs/readiness-review.md`) |
+| `review-issue` | `$HOME/.claude/commands/multi-agent/review-issue/SKILL.md` (loads `$HOME/.claude/multi-agent-refs/readiness-review.md`) |
 | `analysis` | `$HOME/.claude/commands/multi-agent/analysis/SKILL.md` |
 | `build-optimize` | `$HOME/.claude/commands/multi-agent/build-optimize/SKILL.md` |
 | `local` | `$HOME/.claude/commands/multi-agent/local/SKILL.md` |

package/pipeline/commands/multi-agent/help/SKILL.md

@@ -107,7 +107,9 @@ Status & Resume:
 Post-Hoc & Side-Channel:
 
   /multi-agent:channels       Post multi-channel report (Jira / Confluence / Wiki / PR description)
-  /multi-agent:review         Parallel review of current diff only (no full pipeline)
+  /multi-agent:review         Parallel review of a PR or branch diff; no URL -> pick open GitHub/Bitbucket PRs
+  /multi-agent:review-jira    Grade a Jira issue's pipeline-readiness -> comment the gaps on it
+  /multi-agent:review-issue   Grade a GitHub issue's pipeline-readiness -> comment the gaps on it
   /multi-agent:analysis ["analysis-name"]  Feature-spec analysis (Figma + Swagger + Confluence + repos) → per-platform v3 doc (23-section Full / 7-section Lite)
   /multi-agent:analysis-resolve [doc]      Resolve Section 20 open questions of an analysis doc, one at a time with source-labeled candidates
   /multi-agent:build-optimize iOS-only Xcode build perf wrapper → benchmark + analyze + recommend-first .build-benchmark/optimization-plan.md
@@ -319,7 +321,9 @@ Status & Resume:
 Post-Hoc & Side-Channel:
 
   /multi-agent:channels       Multi-channel rapor gönder (Jira / Confluence / Wiki / PR description)
-  /multi-agent:review         Sadece mevcut diff'i paralel review et (full pipeline yok)
+  /multi-agent:review         PR veya branch diff'ini paralel review et; URL yoksa -> açık GitHub/Bitbucket PR'larını seçtir
+  /multi-agent:review-jira    Jira maddesinin pipeline'a hazırlığını değerlendir -> eksikleri yorum olarak ekle
+  /multi-agent:review-issue   GitHub issue'nun pipeline'a hazırlığını değerlendir -> eksikleri yorum olarak ekle
   /multi-agent:analysis ["analysis-name"]  Feature-spec analizi (Figma + Swagger + Confluence + repolar) → platform başına v3 doküman (23 bölüm Full / 7 bölüm Lite)
   /multi-agent:analysis-resolve [doc]      Analiz dokümanının Bölüm 20 açık sorularını kaynak etiketli adaylarla teker teker çözer
   /multi-agent:build-optimize iOS-only Xcode build performance wrapper → benchmark + analiz + recommend-first .build-benchmark/optimization-plan.md

package/pipeline/commands/multi-agent/review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 description: "Run parallel review on a branch's diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments and sets approve/needs-work review state."
-argument-hint: "[#N | repo#N | PR-URL | branch]  -  optional: PR by number/URL, repo+number, or local branch. Supports GitHub and Bitbucket Server URLs. If omitted, the current branch is used."
+argument-hint: "[#N | repo#N | PR-URL | branch]  -  optional: PR by number/URL, repo+number, or local branch. Supports GitHub and Bitbucket Server URLs. If omitted (interactive), open GitHub + Bitbucket PRs are listed for multi-select; autopilot falls back to the current branch."
 ---
 
 # multi-agent review  -  Review Only Mode
@@ -11,7 +11,8 @@ Skip Phase 0-3 and review a diff only. Five input shapes, two providers:
 
 | Input | Resolution | PR action? |
 |---|---|---|
-| (empty) | Current branch (`HEAD` vs `origin/develop`) | No (chat only) |
+| (empty), interactive | **PR picker** - list open GitHub + Bitbucket PRs, multi-select which to review | Yes (per selected PR) |
+| (empty), autopilot / no PRs found | Current branch (`HEAD` vs `origin/develop`) | No (chat only) |
 | `feature/foo` | Named local branch | No (chat only) |
 | `#1250` | PR number on the current repo | Yes |
 | `repo#1250` | PR on a specific repo (GitHub `org/repo`) | Yes |
@@ -40,7 +41,8 @@ trap 'rm -f /tmp/multi-agent-review-${TASK_ID}-*' EXIT
 # Pseudocode  -  orchestrator implements this:
 input="$ARGUMENTS"
 case "$input" in
-  "")                              kind=branch; provider=local; ref=$(git rev-parse --abbrev-ref HEAD) ;;
+  "")                              kind=pick   # interactive: go to Step 1a PR picker; autopilot/no-PRs falls back to branch (see 1a)
+                                   ;;
   https://github.com/*/pull/*)     kind=pr; provider=github; org_repo=<extracted>; pr_number=<extracted> ;;
   https://bitbucket.*/projects/*/repos/*/pull-requests/*)
                                    kind=pr; provider=bitbucket-server
@@ -60,6 +62,35 @@ Save to `agent-state.review.input = { kind, provider, ref?, orgRepo?, bbServerHo
 
 When `provider=github` and the diff is fetched in Step 2, also persist `agent-state.review.headCommitSha`  -  GitHub inline-comment posts (`POST /repos/{o}/{r}/pulls/{n}/comments`) require `commit_id`. Bitbucket Server's anchor API does not.
 
+### 1a. No-input PR picker  -  interactive only
+
+Reached when `kind=pick` (empty input). Skipped entirely in autopilot: autopilot with no ref goes straight to branch mode (`kind=branch; provider=local; ref=$(git rev-parse --abbrev-ref HEAD)`) so nothing prompts.
+
+**List open PRs across both providers** (a provider contributes nothing if its token/CLI is absent - never hard-fail on one provider):
+
+```bash
+# GitHub: current repo's open PRs + the user's own/requested open PRs across repos.
+gh pr list --state open --json number,title,url,headRefName,author,updatedAt 2>/dev/null   # current repo
+gh search prs --state open --review-requested=@me --json number,title,url,repository,updatedAt 2>/dev/null
+gh search prs --state open --author=@me           --json number,title,url,repository,updatedAt 2>/dev/null
+
+# Bitbucket Server: for each configured bitbucket repo (prefs recentRepos / dev-context),
+# resolve creds via credential-store (see Step 2 bitbucket block) then:
+#   GET https://$host/rest/api/1.0/projects/$KEY/repos/$slug/pull-requests?state=OPEN&role=REVIEWER
+```
+
+Merge into one deduped list, each row labeled with its provider and PR URL; sort by `updatedAt` desc. If the merged list is EMPTY -> tell the user "no open PRs found", fall back to branch mode, and continue.
+
+**Select** - follow `$HOME/.claude/multi-agent-refs/picker-contract.md` (breadcrumb narrator line before the prompt), then `AskUserQuestion` `multiSelect: true`:
+
+```
+question (outputLanguage): "Hangi PR('lar)ı review edeyim?"
+header   (English):        "Review PRs"
+options: one per open PR -> label "#<N> <short title>", description (outputLanguage): "<repo> · <provider> · <headRef>"
+```
+
+Each selected option maps back to a full `agent-state.review.input` descriptor (provider + orgRepo / bb coordinates + prNumber + raw URL), exactly as Step 1 would have parsed an explicit URL. Then **loop Steps 2-7 once per selected PR** (independent review + post each). If the user selects none, fall back to branch mode.
+
 ### 2. Fetch the diff  -  kind-aware
 
 **branch mode:**
@@ -252,7 +283,8 @@ Standalone `/multi-agent:review` runs use phase id 4 (matches Phase 4 Review in
 
 | Input | Mode | PR action |
 |---|---|---|
-| no args | branch (current) | none  -  chat only |
+| no args (interactive) | PR picker (open GitHub + Bitbucket PRs, multi-select) | inline comments + approve/needs-work, per selected PR |
+| no args (autopilot / no PRs) | branch (current) | none  -  chat only |
 | `feature/foo` | branch (named) | none  -  chat only |
 | `#N`, `repo#N`, GitHub PR URL | pr (github) | inline comments + approve/needs-work |
 | Bitbucket Server PR URL | pr (bitbucket-server) | inline comments + approve/needs-work |

package/pipeline/commands/multi-agent/review-issue/SKILL.md

@@ -0,0 +1,22 @@
+---
+description: "Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as an issue comment. Read-only on code."
+argument-hint: "[#N | repo#N | GitHub issue URL]  -  optional; with no argument, pick from open issues"
+---
+
+# multi-agent review-issue  -  GitHub issue readiness review
+
+**Input**: $ARGUMENTS
+
+Grades an existing GitHub issue for pipeline-readiness and comments the gaps back onto it so the reporter can fix them before a real `/multi-agent` run. No worktree, no branch, no code commits, no pipeline chaining.
+
+## Flow
+
+Read `$HOME/.claude/multi-agent-refs/readiness-review.md` and execute the shared readiness flow with **provider = github**:
+
+1. Resolve the item: `#N`, `repo#N` (`org/repo#N`), or a GitHub issue URL. With no argument, offer the picker reusing the `issue` command's list (`gh issue list`) and single-select one.
+2. Fetch + base maturity via `$HOME/.claude/lib/issue-fetcher.sh` (`gh issue view`; reuse its `maturity` output; no MCP).
+3. Apply the readiness rubric (testable scope, acceptance criteria / DoD, repro for bugs, design reference for UI, API contract for backend, stack signal, dependencies).
+4. Print the chat verdict (score + Blockers / Warnings / Gaps), reusing the maturity blocker-vs-warning severity contract.
+5. Confirm, then post the gap list as an issue comment via `$HOME/.claude/multi-agent-refs/channels/issue-comment.md` (`gh issue comment "$N" --repo "$org/$repo" --body-file <file>`). Autopilot auto-posts.
+
+Non-negotiables: verdict content + comment body follow `prefs.global.outputLanguage`; comment tone rules (no AI attribution, no em-dash / section-sign, `Ref:` never `Closes/Fixes`) per `channels/issue-comment.md`. No label change, no assignment, no issue creation, no auto-close.

package/pipeline/commands/multi-agent/review-jira/SKILL.md

@@ -0,0 +1,22 @@
+---
+description: "Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as a Jira comment. Read-only on code."
+argument-hint: "[JIRA-KEY | Jira URL]  -  optional; with no argument, pick from your open Jira issues"
+---
+
+# multi-agent review-jira  -  Jira readiness review
+
+**Input**: $ARGUMENTS
+
+Grades an existing Jira issue for pipeline-readiness and comments the gaps back onto it so the reporter can fix them before a real `/multi-agent` run. No worktree, no branch, no code commits, no pipeline chaining. This is the inverse of `/multi-agent:create-jira`.
+
+## Flow
+
+Read `$HOME/.claude/multi-agent-refs/readiness-review.md` and execute the shared readiness flow with **provider = jira**:
+
+1. Resolve the item: `KEY-123` or a `.../browse/KEY-123` URL. With no argument, offer the picker reusing the `jira` command's issue list (assignee=currentUser, open) and single-select one.
+2. Fetch + base maturity via `$HOME/.claude/lib/issue-fetcher.sh` (reuse its `maturity` output; no MCP).
+3. Apply the readiness rubric (testable scope, acceptance criteria / DoD, repro for bugs, design reference for UI, API contract for backend, stack signal, dependencies).
+4. Print the chat verdict (score + Blockers / Warnings / Gaps), reusing the maturity blocker-vs-warning severity contract.
+5. Confirm, then post the gap list as a Jira comment via `$HOME/.claude/multi-agent-refs/channels/jira.md` (`POST /rest/api/2/issue/{id}/comment`, Bearer token via `credential-store.sh`, UTF-8 verbatim, markdown->wiki). Autopilot auto-posts.
+
+Non-negotiables: verdict content + comment body follow `prefs.global.outputLanguage`; comment tone rules (no AI attribution, no em-dash / section-sign, `Ref:` never `Closes`) per `channels/issue-comment.md`. No status change, no assignment, no issue creation.

package/pipeline/commands/multi-agent/sync/SKILL.md

@@ -55,7 +55,7 @@ Run every step automatically:
 ```
 Step 1: PLATFORM    Detect macOS / Linux / Windows (Git Bash / WSL); export PLATFORM env
 Step 1.5: DETECT    Compare timestamps, find stale targets
-Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 36 sub-command skills)
+Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 38 sub-command skills)
 Step 3: REPO        Claude Code -> pipeline repo (genericized, personal data scrub, bash -n on all sh)
 Step 3c: PLUGINS    pipeline shared/external -> multi-agent-plugins marketplace (rebuild knowledge/,
                      bump changed plugins' patch version, commit + push the plugins repo)
@@ -126,7 +126,7 @@ If nothing is stale → report "All targets up to date" and stop.
      grep -rl "^local-only: true" ~/multi-agent-pipeline/pipeline/commands/ 2>/dev/null \
        && { echo "ABORT: local-only wrapper leaked into pipeline/commands"; exit 1; } || true
      # backstop: no corporate marketplace/skill reference in the synced tree
-     grep -rniE "ai-ios-engineering-toolkit:(create-ui-component|evolve-ui-component|component-wiki|figma-setup|resource-utility)" \
+     grep -rniE "ai-ios-engineering-toolkit:(create-ui-component|evolve-ui-component|fix-bug|branch-and-pr|backlog|code-connect|figma-utility|resource-utility|component-wiki|component-docs|figma-setup)" \
        ~/multi-agent-pipeline/pipeline/commands/ 2>/dev/null \
        && { echo "ABORT: corporate reference leaked into pipeline/commands"; exit 1; } || true
      ```
@@ -239,13 +239,13 @@ This runs on the Claude <-> Copilot axis — the two CLIs the pipeline supports
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}/SKILL.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**36 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
+**38 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels, create-jira, delete, dev,
 dev-autopilot, dev-local, dev-local-autopilot, diff-explain, finish, garbage-collect,
 help, issue, jira, kill, language, local,
-local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review,
+local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review, review-issue, review-jira,
 scan, search, setup, stack, status, sync, test, update
 ```
 

package/pipeline/multi-agent-refs/cross-cli-contract.md

@@ -6,13 +6,13 @@
 
 ---
 
-## 1. Command Inventory (36 commands)
+## 1. Command Inventory (38 commands)
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels, create-jira, delete, dev,
 dev-autopilot, dev-local, dev-local-autopilot, diff-explain, finish, garbage-collect,
 help, issue, jira, kill, language, local,
-local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review,
+local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review, review-issue, review-jira,
 scan, search, setup, stack, status, sync, test, update
 ```
 
@@ -23,7 +23,7 @@ Categories:
 - **Full 8-phase modes**: `autopilot`, `local`, `local-autopilot`
 - **Fast modes** (Init -> Dev(Opus) -> Commit -> Report): `dev`, `dev-autopilot`, `dev-local`, `dev-local-autopilot`
 - **Tail modes** (run the pipeline tail over already-done local work): `finish`
-- **Ops commands** (one-shot, no worktree): `status`, `log`, `kill`, `purge`, `delete`, `resume`, `review`, `analysis`, `analysis-resolve`, `build-optimize`, `channels`, `scan`, `search`, `diff-explain`, `garbage-collect`, `prune-logs`
+- **Ops commands** (one-shot, no worktree): `status`, `log`, `kill`, `purge`, `delete`, `resume`, `review`, `review-jira`, `review-issue`, `analysis`, `analysis-resolve`, `build-optimize`, `channels`, `scan`, `search`, `diff-explain`, `garbage-collect`, `prune-logs`
 - **Meta-ops**: `setup`, `sync`, `update`, `help`, `refactor`, `test`, `stack`, `manual-test`, `language`
 
 > **Inventory drift is a contract violation.** Adding a slash command under `pipeline/commands/multi-agent/` without updating this list + its counterpart Copilot dir (`pipeline/skills/shared/core/multi-agent-<cmd>/`) is a merge blocker. `smoke-commands-skills-parity.sh` enforces command ↔ skill directory parity; `smoke-cross-cli-behavior.sh` enforces behavior parity. This doc is the authoritative command list  -  bump the count + table together.
@@ -245,7 +245,7 @@ For clipboard ops, callers still gate with `if command -v pbpaste >/dev/null; th
 
 This contract is validated by:
 
-- `smoke-cross-cli-behavior.sh`  -  asserts all 36 commands behave identically, pulls from Section 2 (placeholder vocab), Section 5 (argument parsing), Section 6 (output formats); also regression-locks the 6-persona agent deployment
+- `smoke-cross-cli-behavior.sh`  -  asserts all 38 commands behave identically, pulls from Section 2 (placeholder vocab), Section 5 (argument parsing), Section 6 (output formats); also regression-locks the 6-persona agent deployment
 - `smoke-commands-skills-parity.sh` (50 assertions)  -  enforces colon-form command ↔ dash-form skill directory parity
 - `smoke-compliance-skills.sh` (45 assertions)  -  enforces store-compliance skill catalog + 4 consumer wiring
 - `smoke-personal-data.sh`  -  extended in 0.5.5 to treat deprecated placeholders (`{github-username}`, `{your-website}`, `{website-repo}`) as leaks; adds `mmerterden` to public-handle blocklist for generic docs

package/pipeline/multi-agent-refs/readiness-review.md

@@ -0,0 +1,65 @@
+# Readiness Review (shared flow for review-jira + review-issue)
+
+Assess whether a tracker item (Jira issue or GitHub issue) is READY to hand to the multi-agent pipeline, list the concrete gaps, and - after confirmation - post them back as a comment on the item so the reporter can fix it. Read-only on code: no worktree, no branch, no commits, no dev chaining. This is the inverse of `/multi-agent:create-jira` (which authors a well-formed item); here we grade an existing one.
+
+Both `/multi-agent:review-jira` and `/multi-agent:review-issue` execute this flow; only the provider (fetch + comment endpoint + picker) differs.
+
+## Language
+Instruction prose here is English. The verdict shown in chat and the comment body follow `prefs.global.outputLanguage` (the comment is authored for the user's team, same exception as create-jira). AskUserQuestion `label`/`header` stay English; `question`/`description` follow `outputLanguage`.
+
+## Step 1 - resolve the item
+- With an argument: `review-jira KEY-123` / `https://<jira>/browse/KEY-123`; `review-issue #N` / `repo#N` / GitHub issue URL.
+- With no argument: offer the picker - review-jira reuses the `jira` command's issue list (`jira/SKILL.md` JQL, assignee=currentUser, open); review-issue reuses the `issue` command's list (`gh issue list`). Single-select (one item reviewed per run; re-run for more).
+
+## Step 2 - fetch + base maturity
+Run `$HOME/.claude/lib/issue-fetcher.sh` (the same fetcher Phase 0 uses). It returns a descriptor with `title`, `type`, `status`, `description`, and `maturity = { score (0..100), blockers[], warnings[], summary }`. Reuse that maturity verbatim as the baseline; never re-fetch through MCP.
+
+## Step 3 - readiness rubric (extends maturity)
+Maturity is generic; add these pipeline-readiness dimensions by reading the fetched `title` + `description` (no invention - only judge what is written). Each is `pass` / `gap`:
+
+| Dimension | Ready when | Gap signal |
+|---|---|---|
+| Scope is testable | the change is bounded + verifiable (what "done" means is stated) | vague ("improve X"), no measurable outcome |
+| Acceptance criteria / DoD | AC or DoD present (Task/Story/Feature) | none (aligns with maturity `no_acceptance_criteria`) |
+| Reproduction | Bugs have steps + expected/actual | none (aligns with maturity `no_repro_steps`) |
+| Design reference | UI work links a Figma frame or attaches a screenshot | UI implied but no design source |
+| API contract | backend/integration work names endpoints or a Swagger/OpenAPI ref | data/contract implied, none given |
+| Platform / stack signal | the target stack is inferable (iOS / Android / frontend / backend) | ambiguous - Phase 1 could not route |
+| Dependencies | blocking deps/links are called out when they exist | hidden dependency likely |
+
+Only emit a dimension as a gap when its trigger applies (do not demand an API contract on a copy-change task). Merge: `gaps = maturity.blockers + maturity.warnings + rubric gaps`.
+
+## Step 4 - verdict (chat, always)
+Print a compact verdict; reuse the maturity blocker-vs-warning severity contract (same as the Phase 0 maturity check):
+
+```
+Readiness: KEY-123  -  score 60/100  -  NEEDS WORK
+BLOCK  Description is empty
+WARN   No acceptance criteria detected
+GAP    UI work but no design reference
+GAP    Target stack ambiguous
+```
+Verdict rule: any blocker -> NOT READY (blocking); else any warning/gap -> NEEDS WORK; else READY. Mirrors `jira/SKILL.md` maturity handling: blockers would halt a real run, warnings would prompt.
+
+## Step 5 - post the comment (confirmed)
+Posting to a tracker is outward-facing - confirm first (autopilot auto-posts):
+
+```
+question (outputLanguage): "Eksiklikleri {KEY|#N} üzerine yorum olarak ekleyeyim mi?"
+header   (English):        "Post readiness comment"
+options:
+  - label "Post comment", description (outputLanguage): "Eksiklik listesini item'a yorum olarak yaz"
+  - label "Chat only",    description (outputLanguage): "Sadece sohbet özeti, item'a dokunma"
+default: option 1
+```
+
+Comment body: a short "Multi-agent readiness review" heading, the score + verdict, then the gap list grouped Blockers / Warnings / Gaps, each with a one-line fix suggestion. Tone rules (same as `channels/issue-comment.md`): no AI/Claude/Copilot attribution, no "generated by", no em-dash/section-sign, plain ASCII; if referencing another item use `Ref: #N` never `Closes/Fixes`. READY items get a short "ready to pick up" confirmation instead of a gap list.
+
+Provider dispatch:
+- **Jira** (`review-jira`): post via `$HOME/.claude/multi-agent-refs/channels/jira.md` comment path - `POST /rest/api/2/issue/{id}/comment`, Bearer token from `keychainMapping.jira` via `credential-store.sh`, UTF-8 verbatim (`jq --rawfile` + `curl --data-binary @payload.json`), markdown->wiki conversion.
+- **GitHub** (`review-issue`): `gh issue comment "$N" --repo "$org/$repo" --body-file <file>` per `channels/issue-comment.md` (auth via the Phase 0 `gh` account).
+
+On post failure, surface the failing endpoint on stderr; the chat verdict remains the source of truth.
+
+## Not in scope
+No status transitions, no assignment changes, no issue creation, no code review (that is `/multi-agent:review`). This command only reads the item and comments its readiness.

package/pipeline/scripts/fixtures/install-layout.tsv

@@ -1,17 +1,17 @@
 .claude/CLAUDE.md	1
 .claude/agents	8
-.claude/commands	42
+.claude/commands	44
 .claude/lib	24
 .claude/multi-agent-preferences.json	1
-.claude/multi-agent-refs	50
+.claude/multi-agent-refs	51
 .claude/rules	12
 .claude/schemas	23
-.claude/scripts	178
+.claude/scripts	180
 .claude/settings.json	1
 .claude/skills	428
 .copilot/agents	8
 .copilot/copilot-instructions.md	1
 .copilot/lib	24
 .copilot/schemas	23
-.copilot/scripts	178
-.copilot/skills	465
+.copilot/scripts	180
+.copilot/skills	467

package/pipeline/scripts/smoke-generate-issue.sh

@@ -91,11 +91,11 @@ echo ""
 echo "→ 8. registration + count consistency (36)"
 grep -Fq '| `create-jira ' "$DISPATCHER" && pass "dispatcher routing: create-jira" || fail "dispatcher routing missing: generate"
 grep -Fq "create-jira/SKILL.md" "$DISPATCHER" && pass "dispatcher loading row" || fail "dispatcher loading row missing"
-grep -Fq "## 1. Command Inventory (36 commands)" "$CONTRACT" && pass "contract count = 36" || fail "contract count wrong"
+grep -Fq "## 1. Command Inventory (38 commands)" "$CONTRACT" && pass "contract count = 38" || fail "contract count wrong"
 grep -Eq '(^|[ ,])create-jira([ ,]|$)' "$CONTRACT" && pass "contract list has create-jira" || fail "contract list missing generate"
-grep -Fq "**36 commands are synced**" "$SYNC" && pass "sync count = 36" || fail "sync count wrong"
+grep -Fq "**38 commands are synced**" "$SYNC" && pass "sync count = 38" || fail "sync count wrong"
 SYNC_SKILL="$ROOT/pipeline/skills/shared/core/multi-agent-sync/SKILL.md"
-grep -Fq "**36 commands are synced**" "$SYNC_SKILL" && pass "sync SKILL count = 36" || fail "sync SKILL count wrong (Copilot parity)"
+grep -Fq "**38 commands are synced**" "$SYNC_SKILL" && pass "sync SKILL count = 38" || fail "sync SKILL count wrong (Copilot parity)"
 grep -Fq "create-jira" "$ROOT/pipeline/skills/shared/core/multi-agent-help/SKILL.md" && pass "help SKILL lists create-jira" || fail "help SKILL missing create-jira (Copilot parity)"
 grep -c "multi-agent:create-jira" "$HELP" | awk '{exit !($1>=2)}' && pass "help.md has EN + TR entries" || fail "help.md entries incomplete"
 # no stale split-command references anywhere in the synced surfaces

package/pipeline/scripts/smoke-review-readiness.sh

@@ -0,0 +1,91 @@
+#!/usr/bin/env bash
+# smoke-review-readiness.sh  -  contract for /multi-agent:review-jira + /multi-agent:review-issue.
+#
+# Verifies:
+#   1. Files exist: 2 commands, 2 Copilot skills, 1 shared ref.
+#   2. Frontmatter keys on both surfaces.
+#   3. Both commands delegate to refs/readiness-review.md and reuse issue-fetcher.
+#   4. The shared ref names the maturity engine + both comment channels + the confirm gate.
+#   5. Registration: dispatcher rows, routing rows, help EN+TR, contract inventory + count (38).
+#   6. Read-only guarantee (no worktree/commit/create) stated.
+#   7. Forbidden strings absent (em-dash, section sign, the M-word).
+
+set -euo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"
+ROOT="$(cd "$HERE/../.." && pwd)"
+
+REF="$ROOT/pipeline/multi-agent-refs/readiness-review.md"
+CMD_J="$ROOT/pipeline/commands/multi-agent/review-jira/SKILL.md"
+CMD_I="$ROOT/pipeline/commands/multi-agent/review-issue/SKILL.md"
+SK_J="$ROOT/pipeline/skills/shared/core/multi-agent-review-jira/SKILL.md"
+SK_I="$ROOT/pipeline/skills/shared/core/multi-agent-review-issue/SKILL.md"
+DISPATCHER="$ROOT/pipeline/commands/multi-agent/SKILL.md"
+CONTRACT="$ROOT/pipeline/multi-agent-refs/cross-cli-contract.md"
+HELP="$ROOT/pipeline/commands/multi-agent/help/SKILL.md"
+
+PASS=0; FAIL=0
+pass() { PASS=$((PASS+1)); echo "  ✓ $1"; }
+fail() { FAIL=$((FAIL+1)); echo "  ✗ $1"; }
+
+echo "→ 1. files exist"
+for f in "$REF" "$CMD_J" "$CMD_I" "$SK_J" "$SK_I"; do
+  if [ -f "$f" ]; then pass "exists: ${f#$ROOT/}"; else fail "missing: ${f#$ROOT/}"; fi
+done
+[ "$FAIL" -eq 0 ] || { echo "══ review-readiness smoke: $PASS passed, $FAIL failed ══"; exit 1; }
+
+echo ""
+echo "→ 2. frontmatter keys"
+for f in "$CMD_J" "$CMD_I"; do
+  head -4 "$f" | grep -q '^description:' && pass "description: ${f#$ROOT/}" || fail "description missing: ${f#$ROOT/}"
+  head -4 "$f" | grep -q '^argument-hint:' && pass "argument-hint: ${f#$ROOT/}" || fail "argument-hint missing: ${f#$ROOT/}"
+done
+head -8 "$SK_J" | grep -q '^name: multi-agent-review-jira$' && pass "name: multi-agent-review-jira" || fail "name wrong: $SK_J"
+head -8 "$SK_I" | grep -q '^name: multi-agent-review-issue$' && pass "name: multi-agent-review-issue" || fail "name wrong: $SK_I"
+for f in "$SK_J" "$SK_I"; do
+  head -8 "$f" | grep -q '^user-invocable: true' && pass "user-invocable: ${f#$ROOT/}" || fail "user-invocable missing: ${f#$ROOT/}"
+done
+
+echo ""
+echo "→ 3. delegate to shared ref + reuse issue-fetcher"
+for f in "$CMD_J" "$CMD_I" "$SK_J" "$SK_I"; do
+  grep -Fq "readiness-review.md" "$f" && pass "ref link: ${f#$ROOT/}" || fail "ref link missing: ${f#$ROOT/}"
+  grep -Fq "issue-fetcher.sh" "$f" && pass "issue-fetcher reuse: ${f#$ROOT/}" || fail "issue-fetcher missing: ${f#$ROOT/}"
+done
+
+echo ""
+echo "→ 4. shared ref names maturity + channels + confirm gate"
+grep -Fqi "maturity" "$REF" && pass "ref uses maturity engine" || fail "ref missing maturity"
+grep -Fq "channels/jira.md" "$REF" && pass "ref -> jira comment channel" || fail "ref missing jira channel"
+grep -Fq "channels/issue-comment.md" "$REF" && pass "ref -> github comment channel" || fail "ref missing issue channel"
+grep -Fqi "confirm" "$REF" && pass "ref has confirm-before-post gate" || fail "ref missing confirm gate"
+grep -Fqi "rubric" "$REF" && pass "ref has readiness rubric" || fail "ref missing rubric"
+
+echo ""
+echo "→ 5. registration + count (38)"
+grep -Fq '| `review-jira ' "$DISPATCHER" && pass "dispatcher desc: review-jira" || fail "dispatcher desc missing review-jira"
+grep -Fq '| `review-issue ' "$DISPATCHER" && pass "dispatcher desc: review-issue" || fail "dispatcher desc missing review-issue"
+grep -Fq "review-jira/SKILL.md" "$DISPATCHER" && pass "dispatcher routing: review-jira" || fail "dispatcher routing missing review-jira"
+grep -Fq "review-issue/SKILL.md" "$DISPATCHER" && pass "dispatcher routing: review-issue" || fail "dispatcher routing missing review-issue"
+grep -Fq "## 1. Command Inventory (38 commands)" "$CONTRACT" && pass "contract count = 38" || fail "contract count wrong"
+grep -Eq '(^|[ ,])review-jira([ ,]|$)' "$CONTRACT" && pass "contract inventory has review-jira" || fail "contract missing review-jira"
+grep -Eq '(^|[ ,])review-issue([ ,]|$)' "$CONTRACT" && pass "contract inventory has review-issue" || fail "contract missing review-issue"
+grep -Fq "multi-agent:review-jira" "$HELP" && pass "help lists review-jira" || fail "help missing review-jira"
+grep -Fq "multi-agent:review-issue" "$HELP" && pass "help lists review-issue" || fail "help missing review-issue"
+
+echo ""
+echo "→ 6. read-only guarantee stated"
+for f in "$CMD_J" "$CMD_I"; do
+  grep -Fqi "no worktree" "$f" && pass "read-only stated: ${f#$ROOT/}" || fail "read-only note missing: ${f#$ROOT/}"
+done
+
+echo ""
+echo "→ 7. forbidden strings absent"
+MWORD="MAN""DATORY"
+for f in "$REF" "$CMD_J" "$CMD_I" "$SK_J" "$SK_I"; do
+  if grep -q $'—\|§\|…' "$f"; then fail "forbidden unicode punctuation in ${f##*/}"; else pass "punctuation clean: ${f##*/}"; fi
+  if grep -q "$MWORD" "$f"; then fail "forbidden word in ${f##*/}"; else pass "vocabulary clean: ${f##*/}"; fi
+done
+
+echo ""
+echo "══ review-readiness smoke: $PASS passed, $FAIL failed ══"
+[ "$FAIL" -eq 0 ]

package/pipeline/scripts/smoke-wrapper-preservation.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+# smoke-wrapper-preservation.sh  -  local-only alias wrappers must survive install/update.
+#
+# Local-only wrappers (frontmatter `local-only: true`) live ONLY under
+# ~/.claude/commands/multi-agent/ (never in pipeline/, never synced). install
+# wipes that namespace before copying from pipeline; without the snapshot+restore
+# carve-out in install/claude.mjs installCommands, wrappers are destroyed on every
+# run. This asserts they survive a second install.
+
+set -uo pipefail
+HERE="$(cd "$(dirname "$0")" && pwd)"
+ROOT="$(cd "$HERE/../.." && pwd)"
+INSTALL_JS="$ROOT/install.js"
+
+PASS=0; FAIL=0
+pass() { PASS=$((PASS+1)); echo "  ✓ $1"; }
+fail() { FAIL=$((FAIL+1)); echo "  ✗ $1"; }
+
+TMP="$(mktemp -d)"
+trap 'rm -rf "$TMP"' EXIT
+
+echo "→ 1. first install lays down the namespace"
+if HOME="$TMP" node "$INSTALL_JS" --claude >/dev/null 2>&1; then
+  pass "install --claude (1st) exited 0"
+else
+  fail "install --claude (1st) failed"
+  echo "══ wrapper-preservation smoke: $PASS passed, $FAIL failed ══"; exit 1
+fi
+
+WRAP_DIR="$TMP/.claude/commands/multi-agent/zz-wrapper-probe"
+mkdir -p "$WRAP_DIR"
+cat > "$WRAP_DIR/SKILL.md" <<'EOF'
+---
+description: "probe local-only wrapper"
+allowed-tools: Skill
+local-only: true
+---
+Use the Skill tool to invoke `some-plugin:some-skill`.
+EOF
+[ -f "$WRAP_DIR/SKILL.md" ] && pass "seeded a local-only wrapper" || fail "could not seed wrapper"
+
+echo ""
+echo "→ 2. second install must PRESERVE the wrapper"
+if HOME="$TMP" node "$INSTALL_JS" --claude >/dev/null 2>&1; then
+  pass "install --claude (2nd) exited 0"
+else
+  fail "install --claude (2nd) failed"
+fi
+if [ -f "$WRAP_DIR/SKILL.md" ] && grep -q '^local-only: true' "$WRAP_DIR/SKILL.md"; then
+  pass "local-only wrapper survived re-install"
+else
+  fail "local-only wrapper was DESTROYED by re-install (carve-out regressed)"
+fi
+
+echo ""
+echo "→ 3. a normal (non-local-only) stray dir is still wiped"
+STRAY="$TMP/.claude/commands/multi-agent/zz-stray-probe"
+mkdir -p "$STRAY"; printf -- '---\ndescription: "stray"\n---\n' > "$STRAY/SKILL.md"
+HOME="$TMP" node "$INSTALL_JS" --claude >/dev/null 2>&1
+if [ -f "$STRAY/SKILL.md" ]; then
+  fail "non-local-only stray survived (wipe too weak)"
+else
+  pass "non-local-only stray correctly wiped"
+fi
+
+echo ""
+echo "══ wrapper-preservation smoke: $PASS passed, $FAIL failed ══"
+[ "$FAIL" -eq 0 ]

package/pipeline/skills/.skill-manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": "1.0.0",
-  "generatedAt": "2026-07-10T13:07:43Z",
-  "skillCount": 187,
+  "generatedAt": "2026-07-10T13:33:19Z",
+  "skillCount": 189,
   "entries": [
     {
       "path": "shared/core/apple-archive-compliance/SKILL.md",
@@ -69,7 +69,7 @@
     },
     {
       "path": "shared/core/multi-agent-help/SKILL.md",
-      "sha256": "15755c1abd508f708e548529c869bc937f1ea038bbabb1cf47dfc3a8b0343346"
+      "sha256": "00772bab27906cdbdcae72d115c4e1f12ddd914fa7aa274923618a3a906e6caa"
     },
     {
       "path": "shared/core/multi-agent-issue/SKILL.md",
@@ -119,9 +119,17 @@
       "path": "shared/core/multi-agent-resume/SKILL.md",
       "sha256": "2d781df8da65dc3def03e9064d191bbf7d17411470ecd16d8473cccd74a2927a"
     },
+    {
+      "path": "shared/core/multi-agent-review-issue/SKILL.md",
+      "sha256": "76c742bc7ac2cd1f909216989a235a8953aa4e6997a31801c9953bcd431c9317"
+    },
+    {
+      "path": "shared/core/multi-agent-review-jira/SKILL.md",
+      "sha256": "4121907fd27fae70491785f8e15e7c2c8fd6f1bf1b1846262070639063cc83ee"
+    },
     {
       "path": "shared/core/multi-agent-review/SKILL.md",
-      "sha256": "e2b8cf23775cfd6be2727cef1c47d78030c6600240e4446f7ceb4297e8cf7d46"
+      "sha256": "b1fd57d2b80ee0fe2490439d9f2688fcf415857c2aab60549c5456e27693b9a9"
     },
     {
       "path": "shared/core/multi-agent-scan/SKILL.md",
@@ -145,7 +153,7 @@
     },
     {
       "path": "shared/core/multi-agent-sync/SKILL.md",
-      "sha256": "0ec56a2a802bbd59843bf8e9a6adfdae8c1e626ea07700914cf12e0d0c00dace"
+      "sha256": "28a057b30ec642f5cc1f22c9c50834aae280e6abaf58194b36d85bde717cfb14"
     },
     {
       "path": "shared/core/multi-agent-test/SKILL.md",

package/pipeline/skills/.skills-index.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": "1.0.0",
-  "skillCount": 187,
+  "skillCount": 189,
   "entries": [
     {
       "name": "accessibility-compliance-accessibility-audit",
@@ -985,13 +985,31 @@
     },
     {
       "name": "multi-agent-review",
-      "description": "Run parallel review on the current branch's diff: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). Review-only slice of the pipeline.",
+      "description": "Run parallel review on a branch diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments + approve/needs-work. With no input (interactive), lists open GitHub + Bitbucket PRs to multi-select.",
       "platform": null,
       "group": "core",
       "triggerKeywords": [],
       "triggerPaths": [],
       "relativePath": "shared/core/multi-agent-review/SKILL.md"
     },
+    {
+      "name": "multi-agent-review-issue",
+      "description": "Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as an issue comment. Read-only on code.",
+      "platform": null,
+      "group": "core",
+      "triggerKeywords": [],
+      "triggerPaths": [],
+      "relativePath": "shared/core/multi-agent-review-issue/SKILL.md"
+    },
+    {
+      "name": "multi-agent-review-jira",
+      "description": "Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as a Jira comment. Read-only on code.",
+      "platform": null,
+      "group": "core",
+      "triggerKeywords": [],
+      "triggerPaths": [],
+      "relativePath": "shared/core/multi-agent-review-jira/SKILL.md"
+    },
     {
       "name": "multi-agent-scan",
       "description": "Skill security scan: walks local skill directories against a tiered pattern catalog.",

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

@@ -97,7 +97,9 @@ Utility Commands (dash form on Copilot, colon form on Claude Code):
   /multi-agent:clear-logs     Clean global log directory
   /multi-agent:purge          Worktree + logs  -  full reset (double confirm)
   /multi-agent:channels       Post multi-channel report (Jira/Confluence/Wiki/PR)
-  /multi-agent:review         Review current diff only
+  /multi-agent:review         Review a PR or branch diff; no URL -> pick open GitHub/Bitbucket PRs
+  /multi-agent:review-jira    Grade a Jira issue's pipeline-readiness -> comment the gaps
+  /multi-agent:review-issue   Grade a GitHub issue's pipeline-readiness -> comment the gaps
   /multi-agent:create-jira ["desc"] [figma-url] [swagger-url]  Create a Jira Task/Bug/Story matching team conventions (asks type + preview + approval)
   /multi-agent:sync           Sync ecosystem (Claude + Copilot + website)
   /multi-agent:setup          Keychain tokens + Git identity + language onboarding
@@ -233,7 +235,9 @@ Utility Komutları:
   /multi-agent:clear-logs     Global log dizinini temizle
   /multi-agent:purge          Worktree + log'lar  -  tam reset (çift onay)
   /multi-agent:channels       Multi-channel rapor gönder (Jira/Confluence/Wiki/PR)
-  /multi-agent:review         Sadece mevcut diff'i review et
+  /multi-agent:review         PR veya branch diff'ini review et; URL yoksa -> açık GitHub/Bitbucket PR seç
+  /multi-agent:review-jira    Jira maddesinin pipeline hazırlığını değerlendir -> eksikleri yorumla
+  /multi-agent:review-issue   GitHub issue hazırlığını değerlendir -> eksikleri yorumla
   /multi-agent:create-jira ["açıklama"] [figma-url] [swagger-url]  Takım standartlarına uygun Jira Task/Bug/Story oluştur (tip sorar + önizleme + onay)
   /multi-agent:sync           Ekosistemi senkronize et
   /multi-agent:setup          Keychain token + Git kimliği + dil onboarding

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

@@ -1,27 +1,34 @@
 ---
 name: multi-agent-review
 language: en
-description: "Run parallel review on the current branch's diff: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). Review-only slice of the pipeline."
+description: "Run parallel review on a branch diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). On PR input, posts per-finding inline comments + approve/needs-work. With no input (interactive), lists open GitHub + Bitbucket PRs to multi-select."
 user-invocable: true
-argument-hint: "[branch]  -  optional: branch to review. If omitted, the current branch is used."
+argument-hint: "[#N | repo#N | PR-URL | branch]  -  PR by number/URL, repo+number, or branch (GitHub + Bitbucket Server). If omitted: interactive PR picker, else current branch."
 ---
 
 # multi-agent review  -  Review Only Mode
 
 **Input**: $ARGUMENTS
 
-Skip Phase 0-3 and review the current diff only.
+Skip Phase 0-3 and review a diff only. Input shapes: a PR (`#N`, `repo#N`, GitHub/Bitbucket-Server PR URL), a branch name, or empty.
 
 ## Steps
 
-1. **Determine the branch**  -  if there is an argument, that branch; otherwise the current branch:
-   ```bash
-   git rev-parse --abbrev-ref HEAD
-   ```
+1. **Resolve the input** (`{kind, provider}`):
+   - PR URL / `#N` / `repo#N` -> `kind=pr` (`github` or `bitbucket-server`).
+   - branch name -> `kind=branch` (local).
+   - **empty + interactive** -> `kind=pick` (Step 1a picker); **empty + autopilot** -> current branch.
 
-2. **Get the diff**  -  diff against the target branch:
+1a. **No-input PR picker** (interactive only): list open PRs across both providers and multi-select which to review.
+   - GitHub: `gh pr list --state open --json number,title,url,headRefName,updatedAt` (current repo) plus `gh search prs --state open --review-requested=@me`/`--author=@me`.
+   - Bitbucket Server: for each configured repo, `GET /rest/api/1.0/projects/{KEY}/repos/{slug}/pull-requests?state=OPEN` (creds via `credential-store`).
+   - Merge + label each row `(github)`/`(bitbucket)`, then AskUserQuestion `multiSelect: true` (breadcrumb per `multi-agent-refs/picker-contract.md`). Review each selected PR (loop steps 2-6). Empty list or none selected -> fall back to the current branch.
+
+2. **Get the diff**  -  kind-aware:
    ```bash
-   git diff origin/develop...HEAD
+   # branch: git diff origin/develop...HEAD
+   # github PR: gh pr diff "$N" --repo "$org/$repo"  (+ head SHA for inline anchors)
+   # bitbucket PR: curl -u "$BB_USER:$BB_TOKEN" .../pull-requests/$N/diff?contextLines=10
    ```
 
 3. **Start parallel reviewers**  -  reviewer set depends on the host CLI:
@@ -53,9 +60,11 @@ Skip Phase 0-3 and review the current diff only.
    - 🟡 **Important** → fix recommended
    - 🟢 **Suggestion** → optional
 
-6. **Show a summary**:
+6. **Show a summary** (always prints, any mode):
    ```
    🔍 Review Complete
    | Model | Verdict | Blocking | Important | Suggestion |
    Consensus: ✅ APPROVED
    ```
+
+7. **Post to PR**  -  only when `kind=pr` (full contract: `$HOME/.copilot/multi-agent-refs/channels/pr-review-actions.md`). Decision from accepted findings: 0 accepted blocking AND 0 accepted important -> APPROVE, else NEEDS WORK. Posts one inline comment per accepted blocking/important finding (in `outputLanguage`), then sets the review state via the provider API. Interactive prompts to post (default yes); autopilot auto-posts; `--no-post` skips. Entry point: `bash $HOME/.copilot/lib/post-pr-review.sh "$TASK_ID"`. No monolithic advisory comment. Branch/pick-fallback runs stay chat-only.

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

@@ -0,0 +1,25 @@
+---
+name: multi-agent-review-issue
+language: en
+description: "Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as an issue comment. Read-only on code."
+user-invocable: true
+argument-hint: "[#N | repo#N | GitHub issue URL]  -  optional; with no argument, pick from open issues"
+---
+
+# multi-agent review-issue  -  GitHub issue readiness review
+
+**Input**: $ARGUMENTS
+
+Grades an existing GitHub issue for pipeline-readiness and comments the gaps back onto it. No worktree, no branch, no code commits.
+
+## Flow
+
+Read `$HOME/.copilot/multi-agent-refs/readiness-review.md` and execute the shared readiness flow with **provider = github**:
+
+1. Resolve the item (`#N` / `repo#N` / GitHub issue URL); no argument -> pick from `gh issue list`, single-select.
+2. Fetch + base maturity via `$HOME/.copilot/lib/issue-fetcher.sh` (`gh issue view`; reuse its `maturity`; no MCP).
+3. Apply the readiness rubric (testable scope, acceptance criteria / DoD, repro for bugs, design reference for UI, API contract for backend, stack signal, dependencies).
+4. Print the chat verdict (score + Blockers / Warnings / Gaps) using the maturity severity contract.
+5. Confirm, then post the gaps as an issue comment via `channels/issue-comment.md` (`gh issue comment "$N" --repo "$org/$repo" --body-file <file>`). Autopilot auto-posts.
+
+Verdict + comment body follow `outputLanguage`; comment tone rules (no AI attribution, no em-dash / section-sign, `Ref:` never `Closes/Fixes`). No label/assignment change, no creation, no auto-close.

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

@@ -0,0 +1,25 @@
+---
+name: multi-agent-review-jira
+language: en
+description: "Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack readiness, then (after confirm) post the gaps as a Jira comment. Read-only on code."
+user-invocable: true
+argument-hint: "[JIRA-KEY | Jira URL]  -  optional; with no argument, pick from your open Jira issues"
+---
+
+# multi-agent review-jira  -  Jira readiness review
+
+**Input**: $ARGUMENTS
+
+Grades an existing Jira issue for pipeline-readiness and comments the gaps back onto it. No worktree, no branch, no code commits. Inverse of `multi-agent-create-jira`.
+
+## Flow
+
+Read `$HOME/.copilot/multi-agent-refs/readiness-review.md` and execute the shared readiness flow with **provider = jira**:
+
+1. Resolve the item (`KEY-123` / `.../browse/KEY-123`); no argument -> pick from the `jira` command's open-issue list, single-select.
+2. Fetch + base maturity via `$HOME/.copilot/lib/issue-fetcher.sh` (reuse its `maturity`; no MCP).
+3. Apply the readiness rubric (testable scope, acceptance criteria / DoD, repro for bugs, design reference for UI, API contract for backend, stack signal, dependencies).
+4. Print the chat verdict (score + Blockers / Warnings / Gaps) using the maturity severity contract.
+5. Confirm, then post the gaps as a Jira comment via `channels/jira.md` (`POST /rest/api/2/issue/{id}/comment`, Bearer token via `credential-store`, UTF-8 verbatim, markdown->wiki). Autopilot auto-posts.
+
+Verdict + comment body follow `outputLanguage`; comment tone rules (no AI attribution, no em-dash / section-sign, `Ref:` never `Closes`). No status/assignment change, no creation.

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

@@ -29,7 +29,7 @@ Run all steps automatically:
 
 ```
 Step 1: DETECT      Compare timestamps, find stale targets
-Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 36 sub-command skills)
+Step 2: COPILOT     Claude Code -> Copilot CLI (instructions + 38 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: Commit      Commit + push all changed repos
@@ -136,13 +136,13 @@ When invoked with the `release` argument:
 |-------------|-------------|
 | `~/.claude/commands/multi-agent/{cmd}.md` | `~/.copilot/skills/multi-agent-{cmd}/SKILL.md` |
 
-**36 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
+**38 commands are synced** (canonical inventory  -  must match `cross-cli-contract.md` section 1; drift = contract violation):
 
 ```
 analysis, analysis-resolve, autopilot, build-optimize, channels, create-jira, delete, dev,
 dev-autopilot, dev-local, dev-local-autopilot, diff-explain, finish, garbage-collect,
 help, issue, jira, kill, language, local,
-local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review,
+local-autopilot, log, manual-test, prune-logs, purge, refactor, resume, review, review-issue, review-jira,
 scan, search, setup, stack, status, sync, test, update
 ```
 

package/pipeline/skills/skills-index.md

@@ -3,7 +3,7 @@
 > Auto-generated by `pipeline/scripts/build-skills-index.mjs`  -  do not hand-edit.
 > Regenerate with `node pipeline/scripts/build-skills-index.mjs`.
 
-**187 skills** across 2 groups.
+**189 skills** across 2 groups.
 
 | Group | Name | Platform | Description |
 |-------|------|----------|-------------|
@@ -116,7 +116,9 @@
 | core | `multi-agent-purge` |  -  | ⚠️ Wipes every worktree, branch, log, and state file. Irreversible; asks for double confirmation. |
 | core | `multi-agent-refactor` |  -  | Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, draft one p |
 | core | `multi-agent-resume` |  -  | Resume a stopped or failed task from the phase where it left off. |
-| core | `multi-agent-review` |  -  | Run parallel review on the current branch's diff: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonnet). R |
+| core | `multi-agent-review` |  -  | Run parallel review on a branch diff or a Pull Request: 2 models on Claude Code (Fable + Sonnet), 3 models on Copilot CLI (GPT + Opus + Sonn |
+| core | `multi-agent-review-issue` |  -  | Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / sta |
+| core | `multi-agent-review-jira` |  -  | Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack |
 | core | `multi-agent-scan` |  -  | Skill security scan: walks local skill directories against a tiered pattern catalog. |
 | core | `multi-agent-search` |  -  | Log search across every agent-log.md with smart ranking and filters. Optional --semantic flag queries the per-repo triage corpus. |
 | core | `multi-agent-setup` |  -  | First-run setup wizard: keychain token discovery, Git Identity onboarding, and pipeline preparation. |