@softspark/ai-toolkit 3.5.0 → 3.5.1

package/AGENTS.md

@@ -446,20 +446,20 @@ Specialized agent personas — apply their expertise for relevant tasks:
 
 Skills are invocable commands or auto-loaded knowledge sources:
 
-- **a11y-validate**: Accessibility validator for WCAG 2.1 AA, EN 301 549, EAA. Covers ARIA, contrast, keyboard, forms, media. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard nav, screen reader.
+- **a11y-validate**: Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard, screen reader.
 - **agent-creator**: Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent, create agent, agent scaffold, specialized agent.
 - **analyze**: Analyzes code quality, complexity, patterns across codebase. Triggers: quality report, hotspot scan, code analysis, architecture signal.
-- **api-patterns**: REST/GraphQL API design: naming, versioning, pagination, idempotency, OpenAPI. Triggers: API design, REST, GraphQL, endpoint, OpenAPI, Swagger, pagination, idempotency key, rate limit.
-- **app-builder**: App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter, Unity. Triggers: scaffold, bootstrap, new project, starter, build app, landing page, dashboard, mobile app.
-- **architecture-audit**: Audits codebase for architectural friction and shallow modules, proposes deepening refactors as RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling. Codex-adapted: uses native subagents and plan tracking.
+- **api-patterns**: REST/GraphQL API design: naming, versioning, pagination, idempotency, OpenAPI. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, idempotency, rate limit.
+- **app-builder**: App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter. Triggers: scaffold, bootstrap, new project, starter, dashboard, mobile app.
+- **architecture-audit**: Audits codebase for architectural friction, shallow modules; proposes RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling. Codex-adapted: uses native subagents and plan tracking.
 - **architecture-decision**: Architecture decisions in ADR/RFC/RFD format: context, constraints, options, recommendation. Triggers: ADR, RFC, RFD, trade-offs, design choice, pick between, evaluate approach.
-- **biz-scan**: Scans codebase (schemas, endpoints, events, flags) for revenue opportunities, missing KPIs, monetization gaps. Triggers: business metrics, KPI coverage, analytics gaps, monetization, revenue opportunity.
+- **biz-scan**: Scans codebase for revenue opportunities, KPIs, monetization gaps. Triggers: business metrics, KPI, analytics gaps, monetization, revenue.
 - **brand-voice**: Direct technical voice for docs, README, user-facing text. Concise/strict modes. Triggers: documentation, README, content, output-mode, voice, prose style.
 - **briefing**: Executive daily briefing aggregating reports from all agents into decision-focused summary. Triggers: briefing, daily summary, status across system, executive update.
 - **build**: Builds project with auto-detected toolchain (npm, poetry, cargo, go, flutter, Docker). Triggers: build, compile, bundle, produce artifacts.
 - **chaos**: Injects controlled faults for resilience testing on non-prod. Triggers: chaos, fault injection, latency injection, dependency kill, resilience test.
 - **ci**: Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI). Triggers: CI setup, build pipeline, GitHub Actions config, debug CI, GitLab CI.
-- **ci-cd-patterns**: CI/CD: GitHub Actions, GitLab CI, Jenkins, caching, blue-green, canary, rollback gates. Triggers: CI, CD, pipeline, GitHub Actions, workflow YAML, release, artifact, canary, rollout.
+- **ci-cd-patterns**: CI/CD: GitHub Actions, GitLab CI, Jenkins, caching, blue-green, canary. Triggers: CI, CD, pipeline, GitHub Actions, workflow YAML, release, canary, rollout.
 - **clean-code**: Code quality: meaningful names, SRP, DRY, small functions, guard clauses, refactoring. Triggers: clean code, naming, code smell, SRP, DRY, long function, god class, dead code.
 - **command-creator**: Creates new Claude Code slash commands with frontmatter and validation. Triggers: new slash command, create command, command scaffold.
 - **commit**: Creates Conventional Commits with pre-commit validation. Triggers: commit, conventional commit, git commit, message.
@@ -474,24 +474,24 @@ Skills are invocable commands or auto-loaded knowledge sources:
 - **debug**: Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
 - **debugging-tactics**: RCA debugging: investigation, hypothesis, validation, fix. No fix without RCA. Triggers: bug, error, exception, stack trace, intermittent, flaky, crash, regression, broken after.
 - **deploy**: Deploys with pre-flight checks and health verification. Triggers: deploy, deployment, ship, release, push to prod.
-- **design-an-interface**: Generates multiple alternative interface designs in parallel and compares them (Ousterhout 'Design It Twice'). Triggers: design API, interface options, compare modules, design it twice. Codex-adapted: uses native subagents and plan tracking.
+- **design-an-interface**: Generates and compares parallel interface designs (Ousterhout 'Design It Twice'). Triggers: design API, interface options, compare modules, design it twice. Codex-adapted: uses native subagents and plan tracking.
 - **design-engineering**: UI craftsmanship: animation rules, easing, micro-interactions, state polish. Triggers: animation, transition, ease-out, motion, micro-interaction, hover, loading state, UI polish.
-- **docker-devops**: Docker/K8s/DevOps: Dockerfile, multi-stage builds, compose, manifests, Helm, image hardening. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod, deployment yaml.
+- **docker-devops**: Docker/K8s: Dockerfile, multi-stage, compose, manifests, Helm. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod.
 - **docs**: Generates/updates README, API docs, architecture notes. Triggers: docs, README, API docs, architecture note, documentation.
 - **documentation-standards**: KB conventions: YAML frontmatter, 5-category taxonomy (reference/howto/procedures/troubleshooting/best-practices). Triggers: kb/, SOP, runbook, howto, frontmatter, knowledge base.
 - **ecommerce-patterns**: E-commerce: cart, checkout, payments (Stripe/Adyen), order state, inventory, promos, tax. Triggers: cart, checkout, SKU, payment, Stripe, Shopify, Medusa, Magento, coupon, refund.
 - **evaluate**: Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
-- **evolve**: Analyzes failure patterns in agents/skills and drafts targeted prompt/permission improvements. Triggers: improve agent, refine skill, update system prompt, optimize agent, fix failure pattern.
+- **evolve**: Analyzes agent/skill failures, drafts prompt/permission fixes. Triggers: improve agent, refine skill, system prompt, optimize agent.
 - **explain**: Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
 - **explore**: Explores codebase structure, stack, and architecture. Triggers: explore codebase, project structure, stack overview, architecture map.
 - **fix**: Applies targeted fix to known bug/lint error, verifies with same command that surfaced it. Triggers: fix, apply fix, fix bug, fix lint, targeted fix.
-- **flutter-patterns**: Flutter/Dart: widget composition, state mgmt (Riverpod/Bloc/Provider), navigation, platform channels. Triggers: Flutter, Dart, widget, Riverpod, Bloc, pubspec, Navigator, hot reload.
-- **git-mastery**: Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, history rewriting, LFS. Triggers: git rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree, submodule.
+- **flutter-patterns**: Flutter/Dart: widgets, state mgmt (Riverpod/Bloc), navigation, platform channels. Triggers: Flutter, Dart, widget, Riverpod, Bloc, pubspec, hot reload.
+- **git-mastery**: Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree.
 - **golang-rules**: Go coding rules: style, patterns, security, testing. Triggers: .go, go.mod, go.sum, Gin, Echo, Gorilla, testing, gofmt.
 - **grill-me**: Stress-tests a plan via Socratic questioning down each decision branch. Triggers: stress-test, grill me, validate assumptions, challenge plan, socratic review. Codex-adapted: uses native subagents and plan tracking.
 - **health**: Service/infra health via liveness/readiness checks, resource usage, quick diagnostics. Triggers: health check, services up, system status, infra health, degraded service.
 - **hipaa-validate**: HIPAA validator: PHI exposure, audit logging, encryption, access control, BAA refs. Triggers: HIPAA, PHI, healthcare compliance, audit log, BAA.
-- **hive-mind**: Multi-agent swarm: consensus voting, output aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, team of agents, agent voting.
+- **hive-mind**: Multi-agent swarm: consensus voting, aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, agent voting.
 - **hook-creator**: Create new Claude Code lifecycle hook (PreToolUse/PostToolUse/Stop/SessionStart) with bash + hooks.json. Triggers: create hook, lifecycle hook, PreToolUse, PostToolUse, hook event.
 - **index**: Reindexes KB for semantic search via vector store (Qdrant). Triggers: reindex KB, rebuild index, vector reindex, refresh embeddings.
 - **instinct-review**: Reviews/promotes/removes instincts from `.claude/instincts/*.md`. Triggers: instinct review, curate instincts, manage instincts, promote instinct.
@@ -503,22 +503,22 @@ Skills are invocable commands or auto-loaded knowledge sources:
 - **kotlin-rules**: Kotlin coding rules: style, patterns, security, testing. Triggers: .kt, .kts, build.gradle.kts, Ktor, Jetpack Compose, coroutines, kotlinx.
 - **lint**: Runs linter+typechecker with auto-detected toolchain (ruff/mypy, eslint/tsc, phpstan, golangci-lint, clippy). Triggers: lint, typecheck, static analysis.
 - **mcp-builder**: Builds production MCP servers via 4-phase methodology: research, implement, test, evaluate. Triggers: build MCP, new MCP, MCP integration, MCP server scaffold.
-- **mcp-patterns**: MCP server design: tool schemas, resources, stdio/SSE transports, capability negotiation. Triggers: MCP, Model Context Protocol, MCP server, JSON-RPC, stdio, SSE, Claude Desktop config.
+- **mcp-patterns**: MCP server design: tool schemas, resources, stdio/SSE, capability negotiation. Triggers: MCP, Model Context Protocol, JSON-RPC, stdio, SSE, Claude Desktop.
 - **medplum-rules**: Medplum (FHIR healthcare) coding rules: style, patterns, security, testing. Triggers: medplum.config.mts, medplum.config.ts, FHIR, Medplum, Bot, Subscription, Questionnaire.
 - **mem-search**: Searches past coding sessions for observations, decisions, context. Triggers: mem-search, recall session, past work, prior decisions, session history.
-- **migrate**: Run/create DB migrations with detected tool (Alembic, Prisma, Laravel, Django, Flyway, Drizzle), checks backup. Triggers: apply migration, rollback, generate migration, db migration.
-- **migration-patterns**: Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green schema. Triggers: migration, schema change, zero-downtime, backfill, ALTER TABLE, online DDL, safe deploy.
+- **migrate**: Run/create DB migrations (Alembic, Prisma, Laravel, Django, Flyway, Drizzle); checks backup. Triggers: apply migration, rollback, generate migration.
+- **migration-patterns**: Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green. Triggers: migration, schema change, backfill, ALTER TABLE, online DDL.
 - **model-routing-patterns**: Multi-model pipelines (Haiku/Sonnet/Opus): cost routing, escalation, fallback chains. Triggers: model routing, Haiku, Sonnet, Opus, escalation, fallback chain.
 - **night-watch**: Autonomous maintenance (dep updates, dead code, small refactors) in isolated branch, off-hours. Triggers: night watch, autonomous maintenance, dep updates.
-- **observability-patterns**: Observability: structured logs, metrics (RED/USE), tracing (OpenTelemetry), SLO/SLI. Triggers: logging, metrics, Prometheus, Grafana, OpenTelemetry, trace, span, monitoring, alerting.
+- **observability-patterns**: Observability: structured logs, metrics (RED/USE), tracing, SLO/SLI. Triggers: logging, metrics, Prometheus, Grafana, OpenTelemetry, trace, monitoring.
 - **onboard**: Sets up ai-toolkit in a project: symlinks, CLAUDE.md, intent interview. Triggers: onboard, setup project, install ai-toolkit, migrate project.
 - **orchestrate**: Coordinates multiple specialized agents in parallel. Triggers: orchestrate, multi-agent, parallel agents, coordinate agents. Codex-adapted: uses native subagents and plan tracking.
 - **panic**: Emergency kill switch — halts all agents via lockfile gate. Triggers: panic, stop everything, kill switch, halt agents, agents looping.
-- **performance-profiling**: Performance: golden signals (latency/traffic/errors/saturation), p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, load test, memory leak.
+- **performance-profiling**: Performance: golden signals, p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, memory leak.
 - **persona**: Switches engineering persona at runtime. Triggers: persona, switch role, backend-lead, frontend-lead, devops-eng, junior-dev.
 - **php-rules**: PHP coding rules: style, patterns, security, testing. Triggers: .php, composer.json, Laravel, Symfony, PHPUnit, PSR-12, Composer.
 - **plan**: Breaks features/goals into phased plans with task lists, agent assignments, dependencies. Triggers: plan feature, implementation roadmap, break down task, project phases.
-- **plan-writing**: Implementation plans + pre-mortems: phases, success criteria, risks, rollback, acceptance tests. Triggers: implementation plan, pre-mortem, phased plan, task breakdown, risk register.
+- **plan-writing**: Implementation plans + pre-mortems: phases, success criteria, risks, rollback. Triggers: implementation plan, pre-mortem, phased plan, task breakdown.
 - **plugin-creator**: Creates opt-in plugin packs with manifests + module scaffolding for Claude/Codex. Triggers: new plugin, plugin pack, plugin scaffold.
 - **pr**: Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
 - **prd-to-issues**: Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items.
@@ -531,7 +531,7 @@ Skills are invocable commands or auto-loaded knowledge sources:
 - **refactor**: Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.
 - **refactor-plan**: Creates detailed refactor plan with tiny commits via interview, files as GitHub RFC. Triggers: refactor plan, refactoring RFC, incremental refactor, safe steps. Codex-adapted: uses native subagents and plan tracking.
 - **repeat**: Runs prompt/slash command on recurring interval until done or limit. Triggers: repeat, recurring task, poll status, run every N minutes, interval. Codex-adapted: uses native subagents and plan tracking.
-- **research-mastery**: Hierarchical retrieval: KB first (smart_query/crag_search), then MCP/Context7, then web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, investigate, cite sources.
+- **research-mastery**: Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources.
 - **review**: Reviews code for quality, security, correctness. Triggers: code review, quality review, security review, review PR, review branch.
 - **rollback**: Rolls back git commit, DB migration, or deploy to known-good with safety + health checks. Triggers: rollback, revert deploy, revert migration, rollback commit, git revert.
 - **ruby-patterns**: Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
@@ -552,7 +552,7 @@ Skills are invocable commands or auto-loaded knowledge sources:
 - **test**: Runs project test suite with coverage, auto-detects framework (pytest, vitest, jest, flutter, go, cargo, phpunit). Triggers: run tests, test suite, coverage report.
 - **testing-patterns**: Testing strategy: pyramid, AAA, mocks/fakes/stubs, flaky tests, coverage. Triggers: test, fixture, mock, stub, e2e, TDD, Playwright, Cypress, flaky, coverage, property-based.
 - **triage-issue**: Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report. Codex-adapted: uses native subagents and plan tracking.
-- **typescript-patterns**: TypeScript type safety: generics, conditional types, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, type narrowing, strict mode.
+- **typescript-patterns**: TypeScript types: generics, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, strict mode.
 - **typescript-rules**: TypeScript/JavaScript coding rules: style, patterns, security, testing. Triggers: .ts, .tsx, .js, .jsx, package.json, tsconfig.json, React, Next.js, Vue, Vite, Vitest, Jest, ESLint.
 - **ubiquitous-language**: Extracts DDD ubiquitous language glossary, flags ambiguities, saves to UBIQUITOUS_LANGUAGE.md. Triggers: define domain terms, build glossary, harden terminology, DDD, domain model.
 - **verification-before-completion**: Forces verification commands before success claims. Evidence before assertions. Triggers: complete, fixed, passing, done, ready, verified.

package/CHANGELOG.md

@@ -7,6 +7,26 @@ Versioning follows [Semantic Versioning](https://semver.org/).
 
 ---
 
+## v3.5.1 — Description trim follow-up + GEMINI/Copilot drift fix (2026-05-06)
+
+Patch release. Continues v3.5.0 condensation on 20 skills and re-syncs platform artifacts that v3.5.0 forgot to regenerate.
+
+### Changed
+
+- **20 skills with further trimmed descriptions** — `a11y-validate`, `api-patterns`, `app-builder`, `architecture-audit`, `biz-scan`, `ci-cd-patterns`, `design-an-interface`, `docker-devops`, `evolve`, `flutter-patterns`, `git-mastery`, `hive-mind`, `mcp-patterns`, `migrate`, `migration-patterns`, `observability-patterns`, `performance-profiling`, `plan-writing`, `research-mastery`, `typescript-patterns`. Drops redundant trigger keywords already implied by the summary.
+- **`AGENTS.md`, `llms-full.txt`** regenerated to match the new descriptions.
+
+### Fixed
+
+- **`GEMINI.md` and `.github/copilot-instructions.md`** were not regenerated by the v3.5.0 release commit — they still carried pre-v3.5.0 verbose descriptions. Both now refreshed via `npm run generate:all`.
+- **`/audit.sarif`** added to `.gitignore` so output from `audit_skills.py --ci` does not pollute `git status`.
+
+### Why
+
+Drift in two generated platform files was visible only after running `npm run generate:all` on a clean v3.5.0 checkout. The fix is mechanical and contains no behavior change beyond the description tweaks.
+
+---
+
 ## v3.5.0 — Skill description condensation: 33% smaller, consistent pattern (2026-05-06)
 
 Minor release. All 112 skill descriptions rewritten into a single consistent pattern: short summary, then `Triggers: <comma-separated keywords>.` Drops the verbose "Load when..." tail entirely. Consequence: Claude Code's skill listing fits in ~2% context budget without truncation, and the trigger lists stay intact for accurate auto-loading.

package/README.md

@@ -14,14 +14,13 @@
 
 ---
 
-## What's New in v3.5.0
+## What's New in v3.5.1
 
-Minor release. All 112 skill descriptions rewritten into a single consistent pattern.
+Patch release. Continues v3.5.0 description condensation on 20 skills and fixes generator drift in `GEMINI.md` / `.github/copilot-instructions.md` that was missed by the v3.5.0 release.
 
-- **33% reduction in skill listing size** — 26 465 → 17 837 chars (~2 157 tokens saved). All 112 skills now fit in Claude Code's 2% `skillListingBudgetFraction` budget without truncation.
-- **Consistent description pattern** — every skill follows `<short summary>. Triggers: <comma-separated keywords>.` Verbose "Load when..." tails dropped.
-- **Trigger keywords preserved** — auto-loading on the same keywords as before, no behavior change.
-- **Generator template updated** — `scripts/generate_language_rules_skills.py` emits the new pattern, so `<lang>-rules` skills stay consistent on regeneration.
+- **20 skills further trimmed** — `a11y-validate`, `api-patterns`, `app-builder`, `architecture-audit`, `biz-scan`, `ci-cd-patterns`, `design-an-interface`, `docker-devops`, `evolve`, `flutter-patterns`, `git-mastery`, `hive-mind`, `mcp-patterns`, `migrate`, `migration-patterns`, `observability-patterns`, `performance-profiling`, `plan-writing`, `research-mastery`, `typescript-patterns`. Removes redundant trigger keywords already implied by the summary.
+- **Platform artifacts re-synced** — `AGENTS.md`, `llms-full.txt`, `GEMINI.md`, `.github/copilot-instructions.md` regenerated to match the condensed source descriptions.
+- **`/audit.sarif` ignored** — build artifact from `audit_skills.py --ci` no longer pollutes `git status`.
 
 See [CHANGELOG.md](CHANGELOG.md) for full history.
 

package/app/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ai-toolkit",
   "description": "Professional-grade Claude Code toolkit with persona presets, skill security auditor, expanded lifecycle hooks, experimental opt-in plugin packs, benchmark harvesting, and multi-tool support.",
-  "version": "3.5.0",
+  "version": "3.5.1",
   "author": {
     "name": "SoftSpark",
     "url": "https://github.com/softspark"

package/app/skills/a11y-validate/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: a11y-validate
-description: "Accessibility validator for WCAG 2.1 AA, EN 301 549, EAA. Covers ARIA, contrast, keyboard, forms, media. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard nav, screen reader."
+description: "Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard, screen reader."
 user-invocable: true
 effort: medium
 disable-model-invocation: true

package/app/skills/api-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: api-patterns
-description: "REST/GraphQL API design: naming, versioning, pagination, idempotency, OpenAPI. Triggers: API design, REST, GraphQL, endpoint, OpenAPI, Swagger, pagination, idempotency key, rate limit."
+description: "REST/GraphQL API design: naming, versioning, pagination, idempotency, OpenAPI. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, idempotency, rate limit."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/app-builder/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: app-builder
-description: "App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter, Unity. Triggers: scaffold, bootstrap, new project, starter, build app, landing page, dashboard, mobile app."
+description: "App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter. Triggers: scaffold, bootstrap, new project, starter, dashboard, mobile app."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/architecture-audit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: architecture-audit
-description: "Audits codebase for architectural friction and shallow modules, proposes deepening refactors as RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling."
+description: "Audits codebase for architectural friction, shallow modules; proposes RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling."
 user-invocable: true
 effort: high
 argument-hint: "[area to audit or 'full codebase']"

package/app/skills/biz-scan/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: biz-scan
-description: "Scans codebase (schemas, endpoints, events, flags) for revenue opportunities, missing KPIs, monetization gaps. Triggers: business metrics, KPI coverage, analytics gaps, monetization, revenue opportunity."
+description: "Scans codebase for revenue opportunities, KPIs, monetization gaps. Triggers: business metrics, KPI, analytics gaps, monetization, revenue."
 effort: medium
 disable-model-invocation: true
 argument-hint: "[area]"

package/app/skills/ci-cd-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ci-cd-patterns
-description: "CI/CD: GitHub Actions, GitLab CI, Jenkins, caching, blue-green, canary, rollback gates. Triggers: CI, CD, pipeline, GitHub Actions, workflow YAML, release, artifact, canary, rollout."
+description: "CI/CD: GitHub Actions, GitLab CI, Jenkins, caching, blue-green, canary. Triggers: CI, CD, pipeline, GitHub Actions, workflow YAML, release, canary, rollout."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/design-an-interface/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: design-an-interface
-description: "Generates multiple alternative interface designs in parallel and compares them (Ousterhout 'Design It Twice'). Triggers: design API, interface options, compare modules, design it twice."
+description: "Generates and compares parallel interface designs (Ousterhout 'Design It Twice'). Triggers: design API, interface options, compare modules, design it twice."
 user-invocable: true
 effort: high
 argument-hint: "[module or interface to design]"

package/app/skills/docker-devops/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: docker-devops
-description: "Docker/K8s/DevOps: Dockerfile, multi-stage builds, compose, manifests, Helm, image hardening. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod, deployment yaml."
+description: "Docker/K8s: Dockerfile, multi-stage, compose, manifests, Helm. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/evolve/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: evolve
-description: "Analyzes failure patterns in agents/skills and drafts targeted prompt/permission improvements. Triggers: improve agent, refine skill, update system prompt, optimize agent, fix failure pattern."
+description: "Analyzes agent/skill failures, drafts prompt/permission fixes. Triggers: improve agent, refine skill, system prompt, optimize agent."
 effort: medium
 disable-model-invocation: true
 context: fork

package/app/skills/flutter-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: flutter-patterns
-description: "Flutter/Dart: widget composition, state mgmt (Riverpod/Bloc/Provider), navigation, platform channels. Triggers: Flutter, Dart, widget, Riverpod, Bloc, pubspec, Navigator, hot reload."
+description: "Flutter/Dart: widgets, state mgmt (Riverpod/Bloc), navigation, platform channels. Triggers: Flutter, Dart, widget, Riverpod, Bloc, pubspec, hot reload."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/git-mastery/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: git-mastery
-description: "Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, history rewriting, LFS. Triggers: git rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree, submodule."
+description: "Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree."
 effort: medium
 user-invocable: false
 allowed-tools: Read, Grep, Glob

package/app/skills/hive-mind/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: hive-mind
-description: "Multi-agent swarm: consensus voting, output aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, team of agents, agent voting."
+description: "Multi-agent swarm: consensus voting, aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, agent voting."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/mcp-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: mcp-patterns
-description: "MCP server design: tool schemas, resources, stdio/SSE transports, capability negotiation. Triggers: MCP, Model Context Protocol, MCP server, JSON-RPC, stdio, SSE, Claude Desktop config."
+description: "MCP server design: tool schemas, resources, stdio/SSE, capability negotiation. Triggers: MCP, Model Context Protocol, JSON-RPC, stdio, SSE, Claude Desktop."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/migrate/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: migrate
-description: "Run/create DB migrations with detected tool (Alembic, Prisma, Laravel, Django, Flyway, Drizzle), checks backup. Triggers: apply migration, rollback, generate migration, db migration."
+description: "Run/create DB migrations (Alembic, Prisma, Laravel, Django, Flyway, Drizzle); checks backup. Triggers: apply migration, rollback, generate migration."
 effort: medium
 disable-model-invocation: true
 argument-hint: "[direction]"

package/app/skills/migration-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: migration-patterns
-description: "Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green schema. Triggers: migration, schema change, zero-downtime, backfill, ALTER TABLE, online DDL, safe deploy."
+description: "Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green. Triggers: migration, schema change, backfill, ALTER TABLE, online DDL."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/observability-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: observability-patterns
-description: "Observability: structured logs, metrics (RED/USE), tracing (OpenTelemetry), SLO/SLI. Triggers: logging, metrics, Prometheus, Grafana, OpenTelemetry, trace, span, monitoring, alerting."
+description: "Observability: structured logs, metrics (RED/USE), tracing, SLO/SLI. Triggers: logging, metrics, Prometheus, Grafana, OpenTelemetry, trace, monitoring."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/performance-profiling/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: performance-profiling
-description: "Performance: golden signals (latency/traffic/errors/saturation), p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, load test, memory leak."
+description: "Performance: golden signals, p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, memory leak."
 effort: medium
 allowed-tools: Read, Grep
 user-invocable: false

package/app/skills/plan-writing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: plan-writing
-description: "Implementation plans + pre-mortems: phases, success criteria, risks, rollback, acceptance tests. Triggers: implementation plan, pre-mortem, phased plan, task breakdown, risk register."
+description: "Implementation plans + pre-mortems: phases, success criteria, risks, rollback. Triggers: implementation plan, pre-mortem, phased plan, task breakdown."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/research-mastery/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: research-mastery
-description: "Hierarchical retrieval: KB first (smart_query/crag_search), then MCP/Context7, then web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, investigate, cite sources."
+description: "Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/app/skills/typescript-patterns/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: typescript-patterns
-description: "TypeScript type safety: generics, conditional types, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, type narrowing, strict mode."
+description: "TypeScript types: generics, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, strict mode."
 effort: medium
 user-invocable: false
 allowed-tools: Read

package/llms-full.txt

@@ -66,20 +66,20 @@
 
 ## Skills
 
-- **a11y-validate**: Accessibility validator for WCAG 2.1 AA, EN 301 549, EAA. Covers ARIA, contrast, keyboard, forms, media. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard nav, screen reader.
+- **a11y-validate**: Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG, EAA, ARIA, contrast, keyboard, screen reader.
 - **agent-creator**: Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent, create agent, agent scaffold, specialized agent.
 - **analyze**: Analyzes code quality, complexity, patterns across codebase. Triggers: quality report, hotspot scan, code analysis, architecture signal.
-- **api-patterns**: REST/GraphQL API design: naming, versioning, pagination, idempotency, OpenAPI. Triggers: API design, REST, GraphQL, endpoint, OpenAPI, Swagger, pagination, idempotency key, rate limit.
-- **app-builder**: App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter, Unity. Triggers: scaffold, bootstrap, new project, starter, build app, landing page, dashboard, mobile app.
-- **architecture-audit**: Audits codebase for architectural friction and shallow modules, proposes deepening refactors as RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling.
+- **api-patterns**: REST/GraphQL API design: naming, versioning, pagination, idempotency, OpenAPI. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, idempotency, rate limit.
+- **app-builder**: App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter. Triggers: scaffold, bootstrap, new project, starter, dashboard, mobile app.
+- **architecture-audit**: Audits codebase for architectural friction, shallow modules; proposes RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling.
 - **architecture-decision**: Architecture decisions in ADR/RFC/RFD format: context, constraints, options, recommendation. Triggers: ADR, RFC, RFD, trade-offs, design choice, pick between, evaluate approach.
-- **biz-scan**: Scans codebase (schemas, endpoints, events, flags) for revenue opportunities, missing KPIs, monetization gaps. Triggers: business metrics, KPI coverage, analytics gaps, monetization, revenue opportunity.
+- **biz-scan**: Scans codebase for revenue opportunities, KPIs, monetization gaps. Triggers: business metrics, KPI, analytics gaps, monetization, revenue.
 - **brand-voice**: Direct technical voice for docs, README, user-facing text. Concise/strict modes. Triggers: documentation, README, content, output-mode, voice, prose style.
 - **briefing**: Executive daily briefing aggregating reports from all agents into decision-focused summary. Triggers: briefing, daily summary, status across system, executive update.
 - **build**: Builds project with auto-detected toolchain (npm, poetry, cargo, go, flutter, Docker). Triggers: build, compile, bundle, produce artifacts.
 - **chaos**: Injects controlled faults for resilience testing on non-prod. Triggers: chaos, fault injection, latency injection, dependency kill, resilience test.
 - **ci**: Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI). Triggers: CI setup, build pipeline, GitHub Actions config, debug CI, GitLab CI.
-- **ci-cd-patterns**: CI/CD: GitHub Actions, GitLab CI, Jenkins, caching, blue-green, canary, rollback gates. Triggers: CI, CD, pipeline, GitHub Actions, workflow YAML, release, artifact, canary, rollout.
+- **ci-cd-patterns**: CI/CD: GitHub Actions, GitLab CI, Jenkins, caching, blue-green, canary. Triggers: CI, CD, pipeline, GitHub Actions, workflow YAML, release, canary, rollout.
 - **clean-code**: Code quality: meaningful names, SRP, DRY, small functions, guard clauses, refactoring. Triggers: clean code, naming, code smell, SRP, DRY, long function, god class, dead code.
 - **command-creator**: Creates new Claude Code slash commands with frontmatter and validation. Triggers: new slash command, create command, command scaffold.
 - **commit**: Creates Conventional Commits with pre-commit validation. Triggers: commit, conventional commit, git commit, message.
@@ -94,24 +94,24 @@
 - **debug**: Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
 - **debugging-tactics**: RCA debugging: investigation, hypothesis, validation, fix. No fix without RCA. Triggers: bug, error, exception, stack trace, intermittent, flaky, crash, regression, broken after.
 - **deploy**: Deploys with pre-flight checks and health verification. Triggers: deploy, deployment, ship, release, push to prod.
-- **design-an-interface**: Generates multiple alternative interface designs in parallel and compares them (Ousterhout 'Design It Twice'). Triggers: design API, interface options, compare modules, design it twice.
+- **design-an-interface**: Generates and compares parallel interface designs (Ousterhout 'Design It Twice'). Triggers: design API, interface options, compare modules, design it twice.
 - **design-engineering**: UI craftsmanship: animation rules, easing, micro-interactions, state polish. Triggers: animation, transition, ease-out, motion, micro-interaction, hover, loading state, UI polish.
-- **docker-devops**: Docker/K8s/DevOps: Dockerfile, multi-stage builds, compose, manifests, Helm, image hardening. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod, deployment yaml.
+- **docker-devops**: Docker/K8s: Dockerfile, multi-stage, compose, manifests, Helm. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod.
 - **docs**: Generates/updates README, API docs, architecture notes. Triggers: docs, README, API docs, architecture note, documentation.
 - **documentation-standards**: KB conventions: YAML frontmatter, 5-category taxonomy (reference/howto/procedures/troubleshooting/best-practices). Triggers: kb/, SOP, runbook, howto, frontmatter, knowledge base.
 - **ecommerce-patterns**: E-commerce: cart, checkout, payments (Stripe/Adyen), order state, inventory, promos, tax. Triggers: cart, checkout, SKU, payment, Stripe, Shopify, Medusa, Magento, coupon, refund.
 - **evaluate**: Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). Triggers: measure RAG quality, knowledge gap, RAG eval, golden dataset.
-- **evolve**: Analyzes failure patterns in agents/skills and drafts targeted prompt/permission improvements. Triggers: improve agent, refine skill, update system prompt, optimize agent, fix failure pattern.
+- **evolve**: Analyzes agent/skill failures, drafts prompt/permission fixes. Triggers: improve agent, refine skill, system prompt, optimize agent.
 - **explain**: Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
 - **explore**: Explores codebase structure, stack, and architecture. Triggers: explore codebase, project structure, stack overview, architecture map.
 - **fix**: Applies targeted fix to known bug/lint error, verifies with same command that surfaced it. Triggers: fix, apply fix, fix bug, fix lint, targeted fix.
-- **flutter-patterns**: Flutter/Dart: widget composition, state mgmt (Riverpod/Bloc/Provider), navigation, platform channels. Triggers: Flutter, Dart, widget, Riverpod, Bloc, pubspec, Navigator, hot reload.
-- **git-mastery**: Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, history rewriting, LFS. Triggers: git rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree, submodule.
+- **flutter-patterns**: Flutter/Dart: widgets, state mgmt (Riverpod/Bloc), navigation, platform channels. Triggers: Flutter, Dart, widget, Riverpod, Bloc, pubspec, hot reload.
+- **git-mastery**: Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree.
 - **golang-rules**: Go coding rules: style, patterns, security, testing. Triggers: .go, go.mod, go.sum, Gin, Echo, Gorilla, testing, gofmt.
 - **grill-me**: Stress-tests a plan via Socratic questioning down each decision branch. Triggers: stress-test, grill me, validate assumptions, challenge plan, socratic review.
 - **health**: Service/infra health via liveness/readiness checks, resource usage, quick diagnostics. Triggers: health check, services up, system status, infra health, degraded service.
 - **hipaa-validate**: HIPAA validator: PHI exposure, audit logging, encryption, access control, BAA refs. Triggers: HIPAA, PHI, healthcare compliance, audit log, BAA.
-- **hive-mind**: Multi-agent swarm: consensus voting, output aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, team of agents, agent voting.
+- **hive-mind**: Multi-agent swarm: consensus voting, aggregation, file ownership, map-reduce. Triggers: swarm, hive mind, multi-agent, consensus, parallel agents, agent voting.
 - **hook-creator**: Create new Claude Code lifecycle hook (PreToolUse/PostToolUse/Stop/SessionStart) with bash + hooks.json. Triggers: create hook, lifecycle hook, PreToolUse, PostToolUse, hook event.
 - **index**: Reindexes KB for semantic search via vector store (Qdrant). Triggers: reindex KB, rebuild index, vector reindex, refresh embeddings.
 - **instinct-review**: Reviews/promotes/removes instincts from `.claude/instincts/*.md`. Triggers: instinct review, curate instincts, manage instincts, promote instinct.
@@ -123,22 +123,22 @@
 - **kotlin-rules**: Kotlin coding rules: style, patterns, security, testing. Triggers: .kt, .kts, build.gradle.kts, Ktor, Jetpack Compose, coroutines, kotlinx.
 - **lint**: Runs linter+typechecker with auto-detected toolchain (ruff/mypy, eslint/tsc, phpstan, golangci-lint, clippy). Triggers: lint, typecheck, static analysis.
 - **mcp-builder**: Builds production MCP servers via 4-phase methodology: research, implement, test, evaluate. Triggers: build MCP, new MCP, MCP integration, MCP server scaffold.
-- **mcp-patterns**: MCP server design: tool schemas, resources, stdio/SSE transports, capability negotiation. Triggers: MCP, Model Context Protocol, MCP server, JSON-RPC, stdio, SSE, Claude Desktop config.
+- **mcp-patterns**: MCP server design: tool schemas, resources, stdio/SSE, capability negotiation. Triggers: MCP, Model Context Protocol, JSON-RPC, stdio, SSE, Claude Desktop.
 - **medplum-rules**: Medplum (FHIR healthcare) coding rules: style, patterns, security, testing. Triggers: medplum.config.mts, medplum.config.ts, FHIR, Medplum, Bot, Subscription, Questionnaire.
 - **mem-search**: Searches past coding sessions for observations, decisions, context. Triggers: mem-search, recall session, past work, prior decisions, session history.
-- **migrate**: Run/create DB migrations with detected tool (Alembic, Prisma, Laravel, Django, Flyway, Drizzle), checks backup. Triggers: apply migration, rollback, generate migration, db migration.
-- **migration-patterns**: Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green schema. Triggers: migration, schema change, zero-downtime, backfill, ALTER TABLE, online DDL, safe deploy.
+- **migrate**: Run/create DB migrations (Alembic, Prisma, Laravel, Django, Flyway, Drizzle); checks backup. Triggers: apply migration, rollback, generate migration.
+- **migration-patterns**: Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green. Triggers: migration, schema change, backfill, ALTER TABLE, online DDL.
 - **model-routing-patterns**: Multi-model pipelines (Haiku/Sonnet/Opus): cost routing, escalation, fallback chains. Triggers: model routing, Haiku, Sonnet, Opus, escalation, fallback chain.
 - **night-watch**: Autonomous maintenance (dep updates, dead code, small refactors) in isolated branch, off-hours. Triggers: night watch, autonomous maintenance, dep updates.
-- **observability-patterns**: Observability: structured logs, metrics (RED/USE), tracing (OpenTelemetry), SLO/SLI. Triggers: logging, metrics, Prometheus, Grafana, OpenTelemetry, trace, span, monitoring, alerting.
+- **observability-patterns**: Observability: structured logs, metrics (RED/USE), tracing, SLO/SLI. Triggers: logging, metrics, Prometheus, Grafana, OpenTelemetry, trace, monitoring.
 - **onboard**: Sets up ai-toolkit in a project: symlinks, CLAUDE.md, intent interview. Triggers: onboard, setup project, install ai-toolkit, migrate project.
 - **orchestrate**: Coordinates multiple specialized agents in parallel. Triggers: orchestrate, multi-agent, parallel agents, coordinate agents.
 - **panic**: Emergency kill switch — halts all agents via lockfile gate. Triggers: panic, stop everything, kill switch, halt agents, agents looping.
-- **performance-profiling**: Performance: golden signals (latency/traffic/errors/saturation), p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, load test, memory leak.
+- **performance-profiling**: Performance: golden signals, p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, memory leak.
 - **persona**: Switches engineering persona at runtime. Triggers: persona, switch role, backend-lead, frontend-lead, devops-eng, junior-dev.
 - **php-rules**: PHP coding rules: style, patterns, security, testing. Triggers: .php, composer.json, Laravel, Symfony, PHPUnit, PSR-12, Composer.
 - **plan**: Breaks features/goals into phased plans with task lists, agent assignments, dependencies. Triggers: plan feature, implementation roadmap, break down task, project phases.
-- **plan-writing**: Implementation plans + pre-mortems: phases, success criteria, risks, rollback, acceptance tests. Triggers: implementation plan, pre-mortem, phased plan, task breakdown, risk register.
+- **plan-writing**: Implementation plans + pre-mortems: phases, success criteria, risks, rollback. Triggers: implementation plan, pre-mortem, phased plan, task breakdown.
 - **plugin-creator**: Creates opt-in plugin packs with manifests + module scaffolding for Claude/Codex. Triggers: new plugin, plugin pack, plugin scaffold.
 - **pr**: Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
 - **prd-to-issues**: Splits a PRD into vertical-slice GitHub issues with HITL/AFK tagging and dependencies. Triggers: PRD to issues, create tickets, break down PRD, work items.
@@ -151,7 +151,7 @@
 - **refactor**: Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.
 - **refactor-plan**: Creates detailed refactor plan with tiny commits via interview, files as GitHub RFC. Triggers: refactor plan, refactoring RFC, incremental refactor, safe steps.
 - **repeat**: Runs prompt/slash command on recurring interval until done or limit. Triggers: repeat, recurring task, poll status, run every N minutes, interval.
-- **research-mastery**: Hierarchical retrieval: KB first (smart_query/crag_search), then MCP/Context7, then web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, investigate, cite sources.
+- **research-mastery**: Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources.
 - **review**: Reviews code for quality, security, correctness. Triggers: code review, quality review, security review, review PR, review branch.
 - **rollback**: Rolls back git commit, DB migration, or deploy to known-good with safety + health checks. Triggers: rollback, revert deploy, revert migration, rollback commit, git revert.
 - **ruby-patterns**: Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
@@ -172,7 +172,7 @@
 - **test**: Runs project test suite with coverage, auto-detects framework (pytest, vitest, jest, flutter, go, cargo, phpunit). Triggers: run tests, test suite, coverage report.
 - **testing-patterns**: Testing strategy: pyramid, AAA, mocks/fakes/stubs, flaky tests, coverage. Triggers: test, fixture, mock, stub, e2e, TDD, Playwright, Cypress, flaky, coverage, property-based.
 - **triage-issue**: Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.
-- **typescript-patterns**: TypeScript type safety: generics, conditional types, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, type narrowing, strict mode.
+- **typescript-patterns**: TypeScript types: generics, discriminated unions, Zod, satisfies, branded types. Triggers: TypeScript, TS, generics, Zod, satisfies, strict mode.
 - **typescript-rules**: TypeScript/JavaScript coding rules: style, patterns, security, testing. Triggers: .ts, .tsx, .js, .jsx, package.json, tsconfig.json, React, Next.js, Vue, Vite, Vitest, Jest, ESLint.
 - **ubiquitous-language**: Extracts DDD ubiquitous language glossary, flags ambiguities, saves to UBIQUITOUS_LANGUAGE.md. Triggers: define domain terms, build glossary, harden terminology, DDD, domain model.
 - **verification-before-completion**: Forces verification commands before success claims. Evidence before assertions. Triggers: complete, fixed, passing, done, ready, verified.

package/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "3.5.0",
+  "version": "3.5.1",
   "components": {
     "agents": {
       "description": "44 specialized agents (orchestrator, backend, frontend, security, devops, etc.)",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@softspark/ai-toolkit",
-  "version": "3.5.0",
+  "version": "3.5.1",
   "description": "AI coding toolkit: 112 skills, 44 agents, 12-editor write-through (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo, Aider, Augment, Antigravity, Codex, opencode), machine-enforced safety constitution, SARIF audit, signed npm provenance.",
   "keywords": [
     "claude",