From 87287464919edac89a6c87a0bfba387eb85a3e23 Mon Sep 17 00:00:00 2001
From: dan <dan@delpad>
Date: Mon, 19 Jan 2026 20:36:27 -0800
Subject: [PATCH] docs: Update README and finalize Triad architecture

- Updated README.md with Triad (Gatekeeper, Auditor, Critic)
- verify.sh: Added support for project-local .verify override
- modules/ai-skills.nix: Finalized test-review lens deployment
---
 README.md                            | 11 ++++++-----
 modules/ai-skills.nix                |  4 ++++
 skills/verify-work/scripts/verify.sh | 16 ++++++++++++++++
 3 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index e634a5c..1f274ef 100644
--- a/README.md
+++ b/README.md
@@ -9,9 +9,8 @@ This repository provides a structured framework for building **skills** - compos
 **Why Skills?**
 - **Consistency**: Standardized workflows across different projects
 - **Reusability**: Write once, use everywhere
-- **Composability**: Skills can call other skills
-- **Version Control**: Track and evolve capabilities over time
-- **Multi-Agent Support**: Same skills work with both Claude Code and OpenCode
+- **The Review Triad**: A robust 3-tier architecture (Verify -> Test-Review -> Code-Review) for guaranteed quality
+- **Multi-Agent Support**: Same skills work with Claude, Gemini, Codex, and OpenCode
 
 ## Repository Structure
 
@@ -35,12 +34,14 @@ skills/
 
 | Skill | Description | Status |
 |-------|-------------|--------|
-| **code-review** | Multi-lens code review (bloat, smells, dead-code, redundancy). Interactive issue filing. | Deployed |
+| **code-review** | **The Critic:** Multi-lens code review (bloat, smells, dead-code, redundancy, defense-in-depth). | Deployed |
+| **test-review** | **The Auditor:** Audit test quality for flakiness, tautologies, and anti-patterns. | Deployed |
+| **verify-work** | **The Gatekeeper:** Run project build/tests before claiming success. Enforces "The Iron Law". | Deployed |
 | **niri-window-capture** | Invisibly capture screenshots of any window across workspaces using niri compositor. | Deployed |
 | **orch** | Query multiple AI models for consensus decisions, second opinions, and devil's advocate analysis. | Deployed |
 | **screenshot-latest** | Find and analyze the most recent screenshot without typing paths. | Deployed |
 | **worklog** | Create comprehensive structured org-mode worklogs documenting work sessions. | Deployed |
-| ai-tools-doctor | Check and sync AI coding tool versions against declared manifest. | Available |
+| ai-tools-doctor | Check and sync AI tool versions against declared manifest. | Available |
 | bd-issue-tracking | Track complex, multi-session work with dependency graphs using beads. | Available |
 | doc-review | Lint markdown documentation for AI agent consumption using deterministic rules + LLM semantic checks. | Available |
 | hq | Orchestrate multi-agent workflows using worker CLI and bd issue tracking. | Available |
diff --git a/modules/ai-skills.nix b/modules/ai-skills.nix
index dca029f..9bcf68d 100644
--- a/modules/ai-skills.nix
+++ b/modules/ai-skills.nix
@@ -126,6 +126,10 @@ in {
           source = "${cfg.skillsPath}/ops-review/lenses";
           recursive = true;
         };
+        ".config/lenses/test" = {
+          source = "${cfg.skillsPath}/test-review/lenses";
+          recursive = true;
+        };
       })
 
     ];
diff --git a/skills/verify-work/scripts/verify.sh b/skills/verify-work/scripts/verify.sh
index b0acfb2..137a395 100755
--- a/skills/verify-work/scripts/verify.sh
+++ b/skills/verify-work/scripts/verify.sh
@@ -35,6 +35,22 @@ cd "$PROJECT_ROOT"
 
 log_info "Verifying project in: $PROJECT_ROOT"
 
+# 1. Check for Project-Local Override
+# If a .verify script exists in the root, it takes absolute precedence.
+if [ -x "./.verify" ]; then
+    log_info "Detected local .verify script"
+    if run_cmd "./.verify" "Local .verify"; then
+        exit 0
+    fi
+    exit 1
+elif [ -x "./verify" ]; then
+    log_info "Detected local ./verify script"
+    if run_cmd "./verify" "Local ./verify"; then
+        exit 0
+    fi
+    exit 1
+fi
+
 # 2. Heuristics for Verification
 # We check for most specific to least specific