Add mega-pr skill for combined parallel PR review

README.md

@@ -307,7 +307,7 @@ Self-Improvement (self:* commands)
 ```
 devkit/
 ├── commands/          # 24 slash commands
-├── skills/            # 18 context-activated skills
+├── skills/            # 19 context-activated skills
 ├── agents/            # 6 agents (reviewer, researcher, improver, ...)
 ├── hooks/             # 10 hooks (safety, security, quality gates)
 ├── workflows/         # 18 YAML workflow definitions

ROADMAP.md

@@ -3,7 +3,7 @@
 ## Implemented
 
 - **24 slash commands** — Lifecycle workflows, self-improvement loops, multi-agent dispatch, project health audit, post-PR monitoring, AST repo mapping, autoresearch-inspired self-audit, autoloop, setup-rules
-- **18 context-activated skills** — 9 auto-trigger workflows (test-gen, doc-gen, changelog, onboard, research, deep-research, scrape, autoloop, adr) + 6 coding principles (executing, clean-code, DRY, YAGNI, dont-reinvent, stuck) + 2 tools (gcli, creating-workflows) + 1 iteration memory (scratchpad)
+- **19 context-activated skills** — 9 auto-trigger workflows (test-gen, doc-gen, changelog, onboard, research, deep-research, scrape, autoloop, adr) + 6 coding principles (executing, clean-code, DRY, YAGNI, dont-reinvent, stuck) + 2 tools (gcli, creating-workflows) + 1 iteration memory (scratchpad) + 1 orchestration (mega-pr)
 - **6 agents** — Scoped tool access, worktree isolation, model assignment
 - **10 hooks** — Safety (destructive command blocking, edit-time security patterns, PR gate), observability (audit trail, slop detection, post-validation, subagent verification, language-aware code review), optimization (RTK token compression)
 - **Graceful degradation** — tri:* commands work with 1-3 agents depending on installed CLIs
@@ -34,6 +34,6 @@ Items below were on the roadmap but determined to be unnecessary — either alre
 | Stop hook redesign | Still fires every turn, but exits early with `approve` when no files are changed — near-instant on clean trees, so the performance concern is moot. Revisit only if it causes measurable latency. |
 | Cost event hooks | Budget enforcement already exists in the Go engine via `overBudget()` + `addCost()` callbacks with hard limits |
 | Execution registry | Step tracking already handled by SQLite via `lib.DB` with status, cost, and timing per step |
-| Preset library | The 18 YAML workflows and 18 skills already serve this purpose |
+| Preset library | The 18 YAML workflows and 19 skills already serve this purpose |
 | Framework-specific review checklists | `lang-review.sh` covers language-level patterns; framework-specific rules are better added per-project via hookify |
 | Conditional hook firing | Hooks already self-filter internally (extension checks, changed-file checks); a generic condition system adds complexity for no current need |

skills/mega-pr/SKILL.md

@@ -0,0 +1,43 @@
+---
+name: mega-pr
+description: Run tri-review and pr-review-toolkit review-pr in parallel for maximum coverage — use when asked for mega PR review, mega-pr, mega review, full PR review, or both review tools at once.
+---
+
+# Mega PR Review
+
+Run `/devkit:tri-review` and `/pr-review-toolkit:review-pr` simultaneously for maximum review coverage.
+
+## Step 1: Launch Both Reviews
+
+**[PARALLEL]** — invoke both in a single message using the Skill tool:
+
+1. `Skill: devkit:tri-review` — dispatches Claude + Codex + Gemini reviewers
+2. `Skill: pr-review-toolkit:review-pr` — dispatches specialized aspect reviewers (silent-failure-hunter, type-design-analyzer, test-analyzer, code-reviewer, etc.)
+
+Pass any user-provided arguments (custom prompt, specific files) to both skills unchanged.
+
+## Step 2: Present Combined Results
+
+After both complete, present a unified report:
+
+```
+## Mega PR Review: <branch_name>
+
+### tri-review Results
+<consensus + unique findings>
+
+### pr-review-toolkit Results
+<categorized by severity>
+
+### Summary
+- Total agents participated: <count>
+- Critical issues: <count>
+- Warnings: <count>
+- Suggestions: <count>
+```
+
+## Rules
+
+- Always run both in parallel — never sequential
+- If one skill fails, still present the other's results
+- Do not deduplicate — let the user see both perspectives