specweave 1.0.253 → 1.0.255

package/plugins/specweave/skills/docs/SKILL.md

@@ -1,18 +1,15 @@
 ---
-description: Browse and load SpecWeave living docs (public, internal, architecture, ADRs). Use when saying "show docs", "browse docs", "find docs about", "what docs exist", "load docs", "read ADR", "architecture docs", "troubleshooting docs". Args: [topic] [--public] [--internal] [--adr] [--list].
+description: Browse and load SpecWeave living docs (public, internal, architecture, ADRs). Use when saying "show docs", "browse docs", "find docs about", "load docs", or "read ADR".
+argument-hint: "[topic] [--public] [--internal] [--adr] [--list]"
 ---
 
 # Living Docs Browser
 
-Browse, search, and load SpecWeave living documentation into the conversation.
-
-## Project-Specific Learnings
+## Project Overrides
 
-Before starting work, check for project-specific learnings:
+!`s="docs"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
 
-```bash
-cat .specweave/skill-memories/docs.md 2>/dev/null || echo "No project learnings yet"
-```
+Browse, search, and load SpecWeave living documentation into the conversation.
 
 ## Documentation Structure
 

package/plugins/specweave/skills/docs-updater/SKILL.md

@@ -5,6 +5,10 @@ user-invocable: false
 
 # Documentation Updater
 
+## Project Overrides
+
+!`s="docs-updater"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 Updates product documentation (.specweave/docs/) based on implementation progress.
 
 ## When to Use
@@ -60,14 +64,4 @@ Updates product documentation (.specweave/docs/) based on implementation progres
 - Keep examples in sync with actual code
 - Don't over-document - focus on what users need
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/docs-updater.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/done/SKILL.md

@@ -1,6 +1,6 @@
 ---
-disable-model-invocation: true
-description: Close increment with PM validation - checks tasks, tests, and docs before closing
+description: Close increment with PM 3-gate validation (tasks, tests, docs). Use when all tasks complete and saying "close increment", "we're done", or "finish up".
+argument-hint: "<increment-id>"
 hooks:
   Stop:
     - hooks:
@@ -10,6 +10,10 @@ hooks:
 
 # Close Increment (PM Validated)
 
+## Project Overrides
+
+!`s="done"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 **Product Manager-Led Closure**: PM validates tasks, tests, and docs before closing.
 
 You are acting as the Product Manager to validate increment completion before closure. You must check all 3 gates: tasks done, tests passing, and docs updated.
@@ -1506,7 +1510,6 @@ Check progress: /list-increments
 
 - `pm`: Product Manager agent (validates completion)
 - `sw-testing:qa-engineer`: QA Engineer agent (validates tests)
-- `tech-lead`: Tech Lead agent (validates code quality)
 - `docs-writer`: Documentation writer (validates docs)
 
 ---

package/plugins/specweave/skills/framework/SKILL.md

@@ -6,6 +6,10 @@ user-invocable: false
 
 # SpecWeave Framework Expert
 
+## Project Overrides
+
+!`s="framework"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 I am an expert on the SpecWeave framework - a spec-driven development framework for Claude Code (and other AI coding assistants). I have deep knowledge of its structure, rules, conventions, and best practices.
 
 ## Core Philosophy
@@ -524,14 +528,4 @@ I focus on **framework knowledge**. For **increment execution**, use the PM agen
 
 Let me help you understand and use SpecWeave correctly! 🚀
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/framework.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/grill/SKILL.md

@@ -1,11 +1,16 @@
 ---
-description: Critical code review and quality interrogation before increment completion. Use when finishing a feature, before /sw:done, or when saying "grill the code", "review my work", "critique implementation". Acts as a demanding senior engineer who finds issues before users do.
+description: Critical code review and quality interrogation before increment completion. Use when finishing a feature, before /sw:done, or when saying "grill the code", "review my work", "critique implementation".
+argument-hint: "[increment-id]"
 allowed-tools: Read, Grep, Glob, Bash
 context: fork
 ---
 
 # Code Grill Expert
 
+## Project Overrides
+
+!`s="grill"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 I'm a demanding senior engineer who stress-tests your implementation before it ships. My job is to find issues NOW, before users do. I'm not here to validate - I'm here to CHALLENGE.
 
 ## When to Use This Skill
@@ -24,7 +29,7 @@ Call me when you need to:
 This skill is the **PRE-SHIP quality gate**. Focuses on: correctness, edge cases, performance issues, error handling.
 
 - For deep security audits → use `/sw:security`
-- For design pattern guidance → use `/sw:tech-lead`
+- For design pattern guidance → use `/sw:architect`
 - For code style/clarity → use `/sw:code-simplifier`
 
 ## My Mindset: The Demanding Reviewer
@@ -321,13 +326,3 @@ The grill is uncomfortable. That's the point. Better to sweat here than in front
 
 ---
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/grill.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development.

package/plugins/specweave/skills/increment/SKILL.md

@@ -1,6 +1,7 @@
 ---
 disable-model-invocation: true
 description: Plan new Product Increment. Use when starting new features, hotfixes, or development work that needs specification.
+argument-hint: "<feature-description>"
 hooks:
   PreToolUse:
     - matcher: Write
@@ -18,6 +19,10 @@ hooks:
 
 # Plan Product Increment
 
+## Project Overrides
+
+!`s="increment"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 **Orchestrator for increment planning** - handles pre-flight checks, then delegates to `sw:increment-planner` skill.
 
 ## Workflow

package/plugins/specweave/skills/increment-planner/SKILL.md

@@ -19,6 +19,10 @@ hooks:
 
 # Increment Planner Skill
 
+## Project Overrides
+
+!`s="increment-planner"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 **Self-contained increment planning for ANY user project after `specweave init`.**
 
 ## Workflow Overview
@@ -196,10 +200,3 @@ Skill({ skill: "sw:increment-planner", args: "--description=\"Add auth\"" })
 /sw:increment "Add user authentication"
 ```
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-cat .specweave/skill-memories/increment-planner.md 2>/dev/null || echo "No project learnings yet"
-```

package/plugins/specweave/skills/increment-work-router/SKILL.md

@@ -531,14 +531,4 @@ Users can override auto-routing with explicit instructions:
 
 This skill bridges planning → execution by auto-detecting implementation intent.
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/increment-work-router.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/judge-llm/SKILL.md

@@ -132,17 +132,6 @@ Progress is **always logged** to `.specweave/logs/judge-llm.log`.
 3. Increase timeout with `--timeout` if legitimately slow
 4. Result will show `timedOut: true` if aborted
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/judge-llm.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development.
-
 ## Related
 
 - `/sw:grill` - Confidence-scored pre-ship quality gate (in-session)

package/plugins/specweave/skills/lsp/SKILL.md

@@ -8,6 +8,10 @@ user-invocable: false
 
 # LSP Code Intelligence
 
+## Project Overrides
+
+!`s="lsp"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 Semantic code navigation and analysis.
 
 ## Current Status (v2.1.0+)
@@ -200,13 +204,3 @@ Features:
 3. Provides real semantic analysis
 4. Works in any environment (CI/CD, Claude Code, scripts)
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/lsp.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.

package/plugins/specweave/skills/multi-project-spec-mapper/SKILL.md

@@ -420,14 +420,4 @@ Project Distribution:
 
 Based on: Increment 0020-multi-project-intelligent-sync
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/multi-project-spec-mapper.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/next/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Smart increment transition - auto-close current if ready, intelligently suggest next work (backlog or new feature)
+description: Close current increment if ready and suggest next work. Use when saying "what's next", "next increment", or "move on".
 ---
 
 # Next Increment (Smart Workflow Transition)

package/plugins/specweave/skills/plan/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Generate plan.md and tasks.md for PLANNING increment using Architect Agent
+description: Generate plan.md and tasks.md for increment. Use when saying "create plan", "generate tasks", or "plan the increment".
 ---
 
 # /sw:plan - Generate Implementation Plan

package/plugins/specweave/skills/pm/SKILL.md

@@ -1,5 +1,6 @@
 ---
-description: Product Manager for spec-driven development with SpecWeave conventions. Use when writing user stories, defining acceptance criteria, planning MVPs, or prioritizing features. Creates specs with proper AC-IDs, manages requirements, and maintains product roadmaps.
+description: Product Manager for spec-driven development. Use when saying "write specs", "define requirements", "plan MVP", or "prioritize features".
+argument-hint: "[topic]"
 allowed-tools: Read, Write, Grep, Glob
 context: fork
 model: opus
@@ -7,6 +8,10 @@ model: opus
 
 # Product Manager Skill
 
+## Project Overrides
+
+!`s="pm"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 ## Overview
 
 You are a Product Manager with expertise in spec-driven development. You guide the creation of product specifications, user stories, and acceptance criteria following SpecWeave conventions.
@@ -114,14 +119,4 @@ This skill auto-activates when you mention:
 - Prioritization (RICE, MoSCoW)
 - PRD, product specs, story mapping
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/pm.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/pm-closure-validation/SKILL.md

@@ -539,14 +539,4 @@ When approving closure, summarize what was delivered:
 
 **Remember**: I'm here to ensure quality, not to block progress. If an increment isn't ready, I'll tell you exactly what needs fixing and how long it will take. My goal is to ship high-quality increments that deliver real value.
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/pm-closure-validation.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/progress/SKILL.md

@@ -1,10 +1,14 @@
 ---
-description: Show detailed progress for active increments with task/AC completion, priority, and type
+description: Show progress for active increments with task/AC completion. Use when saying "show progress", "status", or "how far along".
 argument-hint: "[incrementId]"
 ---
 
 # Increment Progress
 
+## Project Overrides
+
+!`s="progress"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 Shows detailed progress information for active increments including:
 - **Task completion** with progress bars
 - **Acceptance Criteria (AC)** completion percentages

package/plugins/specweave/skills/progress-sync/SKILL.md

@@ -1,5 +1,6 @@
 ---
-description: Comprehensive progress sync - tasks.md to living docs to external tools (GitHub/JIRA/ADO). AUTO-CREATES missing external issues. Use when syncing progress, saying "sync progress", "update all systems", or "push progress to GitHub". Args: [INCREMENT_ID] [--dry-run] [--no-create] [--no-github] [--no-jira].
+description: Sync progress from tasks.md to living docs and external tools (GitHub/JIRA/ADO). Use when saying "sync progress" or "push progress".
+argument-hint: "[INCREMENT_ID] [--dry-run] [--no-create] [--no-github] [--no-jira]"
 ---
 
 # Progress Sync (Multi-System)
@@ -461,14 +462,4 @@ Ask me:
 - "Why did my GitHub sync fail?"
 - "When should I use --dry-run?"
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/progress-sync.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/save/SKILL.md

@@ -1,10 +1,15 @@
 ---
 disable-model-invocation: true
-description: SMART save - auto-generates commit messages, handles git pull/merge/rebase automatically, resolves divergent branches, stashes dirty work. Works for single repos and umbrella multi-repo setups. Run with no args for fully automatic save.
+description: Smart auto-commit with remote sync (handles pull/rebase/stash, auto-generates messages, supports multi-repo).
+argument-hint: "[message]"
 ---
 
 # /sw:save - Smart Save with Auto-Sync
 
+## Project Overrides
+
+!`s="save"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 **SMART SAVE** - Handles everything automatically: commit message generation, remote sync (pull/rebase), branch setup, and push. Just run `/sw:save` and it figures out what to do!
 
 ## ⚠️ MANDATORY: Nested Repository Scanning (SpecWeave-Specific)

package/plugins/specweave/skills/security/SKILL.md

@@ -4,13 +4,9 @@ description: Security engineer for vulnerability assessment, penetration testing
 
 # Security Review
 
-## Project-Specific Learnings
+## Project Overrides
 
-Before starting work, check for project-specific learnings:
-
-```bash
-cat .specweave/skill-memories/security.md 2>/dev/null || echo "No project learnings yet"
-```
+!`s="security"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
 
 ## Security Assessment
 

package/plugins/specweave/skills/security-patterns/SKILL.md

@@ -6,6 +6,10 @@ user-invocable: false
 
 # Security Pattern Detector Skill
 
+## Project Overrides
+
+!`s="security-patterns"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 ## Overview
 
 This skill provides real-time security pattern detection based on Anthropic's official security-guidance plugin. It identifies potentially dangerous coding patterns BEFORE they're committed.
@@ -191,14 +195,4 @@ Some patterns may be false positives:
 
 Always check the context before blocking.
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/security-patterns.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/smart-reopen-detector/SKILL.md

@@ -242,14 +242,4 @@ I'm successful when:
 **Commands**: `/sw:reopen`, `/sw:status`
 **Related Skills**: `increment-planner`, `tdd-workflow`
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/smart-reopen-detector.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/spec-generator/SKILL.md

@@ -671,14 +671,4 @@ With project-scoped stories:
 
 Based on: Flexible Spec Generator (V2) - context-aware, non-rigid templates
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/spec-generator.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/tdd-cycle/SKILL.md

@@ -1,9 +1,13 @@
 ---
-description: Execute comprehensive TDD workflow with strict red-green-refactor discipline. Orchestrates test-first development with automated validation gates at each phase.
+description: Execute full TDD red-green-refactor cycle with validation gates. Use when saying "TDD cycle", "test-driven development", or "full TDD workflow".
 ---
 
 # TDD Cycle - Comprehensive Test-Driven Development
 
+## Project Overrides
+
+!`s="tdd-cycle"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 Execute a comprehensive Test-Driven Development (TDD) workflow with strict red-green-refactor discipline:
 
 [Extended thinking: This workflow enforces test-first development through coordinated agent orchestration. Each phase of the TDD cycle is strictly enforced with fail-first verification, incremental implementation, and continuous refactoring. The workflow supports both single test and test suite approaches with configurable coverage thresholds.]

package/plugins/specweave/skills/tdd-green/SKILL.md

@@ -1,9 +1,13 @@
 ---
-description: Implement minimal code to make failing tests pass in TDD green phase. Focuses on simplicity and making tests green without over-engineering.
+description: Write minimal code to make failing tests pass. Use when saying "TDD green", "make tests pass", or "implement for tests".
 ---
 
 # TDD Green Phase - Make Tests Pass
 
+## Project Overrides
+
+!`s="tdd-green"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 Implement minimal code to make failing tests pass in TDD green phase:
 
 [Extended thinking: This tool uses the test-automator agent to implement the minimal code necessary to make tests pass. It focuses on simplicity, avoiding over-engineering while ensuring all tests become green.]

package/plugins/specweave/skills/tdd-orchestrator/SKILL.md

@@ -6,6 +6,10 @@ user-invocable: false
 
 # TDD Orchestrator Skill
 
+## Project Overrides
+
+!`s="tdd-orchestrator"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 ## Overview
 
 You are an expert TDD orchestrator specializing in comprehensive test-driven development coordination, modern TDD practices, and multi-agent workflow management. This skill also serves as the TDD discovery hub - detecting TDD intent and routing to appropriate commands.
@@ -221,14 +225,4 @@ tdd:
 **Skills**:
 - `sw-testing:qa-engineer` - Test strategy overlaps with TDD principles
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/tdd-orchestrator.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/tdd-red/SKILL.md

@@ -1,9 +1,13 @@
 ---
-description: Write comprehensive failing tests following TDD red phase principles. Generates failing tests that properly define expected behavior.
+description: Write failing tests that define expected behavior. Use when saying "TDD red", "write failing tests", or "test first".
 ---
 
 # TDD Red Phase - Write Failing Tests
 
+## Project Overrides
+
+!`s="tdd-red"; for d in .specweave/skill-memories .claude/skill-memories "$HOME/.claude/skill-memories"; do p="$d/$s.md"; [ -f "$p" ] && awk '/^## Learnings$/{ok=1;next}/^## /{ok=0}ok' "$p" && break; done 2>/dev/null`
+
 Write comprehensive failing tests following TDD red phase principles.
 
 [Extended thinking: Generates failing tests that properly define expected behavior using test-automator agent.]

package/plugins/specweave/skills/tdd-refactor/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Refactor code with confidence using comprehensive test safety net. Applies design patterns, improves code quality, and optimizes performance while keeping all tests green.
+description: Refactor code with test safety net to improve quality. Use when saying "TDD refactor", "refactor with tests", or "improve code quality".
 ---
 
 # TDD Refactor Phase - Improve Code Quality

package/plugins/specweave/skills/team-build/SKILL.md

@@ -91,7 +91,7 @@ Three specialized reviewers examine the codebase simultaneously from different a
 | # | Role | Skill(s) | Owns | Responsibility |
 |---|------|----------|------|----------------|
 | 1 | Security | `sw:security` + `sw:security-patterns` | All files (read-only analysis) | Audit for vulnerabilities, injection vectors, auth flaws, secrets exposure, dependency CVEs |
-| 2 | Quality | `sw:grill` + `sw:tech-lead` + `sw:code-simplifier` | All files (read-only analysis) | Review code quality, complexity, naming, duplication, SOLID violations, performance anti-patterns |
+| 2 | Quality | `sw:grill` + `sw:code-simplifier` | All files (read-only analysis) | Review code quality, complexity, naming, duplication, SOLID violations, performance anti-patterns |
 | 3 | Docs | `sw:docs-updater` | All files (read-only analysis) | Check doc coverage, stale comments, missing JSDoc, README accuracy, spec-to-code alignment |
 
 #### Execution Chain

package/plugins/specweave/skills/team-lead/SKILL.md

@@ -1,5 +1,5 @@
 ---
-description: Orchestrate multi-agent parallel development using Claude Code Agent Teams. Spawns domain-specialized agents (frontend, backend, database, testing, security, DevOps, mobile, ML) with contract-first coordination. Activates for: team setup, parallel agents, multi-repo work, team lead, agent teams.
+description: Orchestrate multi-agent parallel development with domain-specialized agents. Use when saying "team setup", "parallel agents", "team lead", or "agent teams".
 ---
 
 # Team Lead
@@ -42,7 +42,7 @@ Analyze the feature request and map affected domains to SpecWeave skills.
 | **Frontend** | `sw-frontend:frontend-architect` | `sw-frontend:nextjs`, `sw-frontend:frontend-design` | UI components, pages, client-side state |
 | **Backend** | `sw:architect` | `sw-infra:devops` | API endpoints, services, business logic |
 | **Database** | `sw:architect` | | Schema design, migrations, seed data |
-| **Shared/Types** | `sw:architect` | `sw:tech-lead` | TypeScript interfaces, shared constants, API contracts |
+| **Shared/Types** | `sw:architect` | `sw:code-simplifier` | TypeScript interfaces, shared constants, API contracts |
 | **Testing** | `sw-testing:qa-engineer` | `sw-testing:e2e-testing`, `sw-testing:unit-testing` | Test strategy, E2E suites, integration tests |
 | **Security** | `sw:security` | `sw:security-patterns` | Auth, authorization, threat modeling, OWASP |
 | **DevOps** | `sw-infra:devops` | `sw-k8s:deployment-generate`, `sw-infra:observability` | CI/CD, Docker, K8s, monitoring |
@@ -646,7 +646,7 @@ Team Orchestration Plan (DRY RUN)
 Feature: Build checkout flow | Domains: 4
 
 Phase 1 (upstream):
-  1. shared-types -> sw:architect, sw:tech-lead  | Increment: 0200-checkout-shared
+  1. shared-types -> sw:architect, sw:code-simplifier  | Increment: 0200-checkout-shared
   2. database     -> sw:architect                 | Increment: 0201-checkout-database
 
 Phase 2 (downstream, parallel):

package/plugins/specweave/skills/test-aware-planner/SKILL.md

@@ -92,14 +92,4 @@ If umbrella.enabled in config:
 - [ ] Tasks grouped by User Story
 - [ ] Frontmatter has by_user_story map
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/test-aware-planner.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/umbrella-repo-detector/SKILL.md

@@ -298,14 +298,4 @@ All 4 repos will be committed and pushed with a single `/sw:save` command!
 4. **Cross-project stories get special handling** - Tagged and linked across repos
 5. **Use `/sw:save`** - Single command to save changes across all repos
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/umbrella-repo-detector.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.
 

package/plugins/specweave/skills/update-instructions/SKILL.md

@@ -79,14 +79,4 @@ This will be preserved during updates!
 - `CLAUDE.md` - Claude Code instruction file
 - `AGENTS.md` - Generic AI tool instruction file
 
-## Project-Specific Learnings
-
-**Before starting work, check for project-specific learnings:**
-
-```bash
-# Check if skill memory exists for this skill
-cat .specweave/skill-memories/update-instructions.md 2>/dev/null || echo "No project learnings yet"
-```
-
-Project learnings are automatically captured by the reflection system when corrections or patterns are identified during development. These learnings help you understand project-specific conventions and past decisions.