@caddis/cli 0.4.34 → 0.4.36

package/bundles/antigravity-plugin/skills/tech-explainer/SKILL.md

@@ -2,18 +2,13 @@
 name: tech-explainer
 context: fork
 description: >-
-  Write a plain-language technical explainer for a smart reader who did NOT do the investigation — a
-  manager, an infra colleague, a stakeholder, the person whose recommendation you are answering.
-  Layered Mermaid diagrams that rank causes by SIZE OF EFFECT, a controlled-vocabulary table,
-  Simplified Technical English, published withdrawn results, and questions back to the reader. Use
-  this skill whenever the user says "explain this to X", "explainer", "write this up for someone
-  non-technical", "plain English", "simplified technical english", "STE", "explain our findings",
-  "write up the benchmark results", "answer my manager's recommendations", "why is it slow — document
-  it", "make a doc with diagrams explaining the stack", or is about to summarise an investigation, a
-  benchmark, a postmortem, an architecture, or a disagreement for a reader who will not read the raw
-  data. NOT for handing off work to be BUILT by a vendor or another team (use explainer-doc for that —
-  it produces an actionable spec); NOT for READMEs or API docs (use technical-writing). This one
-  produces UNDERSTANDING: the reader must finish able to argue with you on the merits.
+  Plain-language explainer, with ranked Mermaid diagrams and Simplified Technical English, for a
+  reader who did NOT do the investigation (manager, stakeholder). Use when the user says "explain
+  this to X", "explainer", "write this up for someone non-technical", "plain English", "simplified
+  technical english", "STE", "explain our findings", "write up the benchmark results", "answer my
+  manager's recommendations", "why is it slow — document it", "make a doc with diagrams explaining
+  the stack", or summarises an investigation for a reader who won't read the raw data. Not for build
+  hand-offs (explainer-doc) or READMEs.
 ---
 
 # tech-explainer — make a stranger understand, and able to push back

package/bundles/antigravity-plugin/skills/technical-writing/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: technical-writing
 context: fork
-description: Technical documentation best practices for READMEs, API docs, architecture docs, runbooks, and developer guides. Use when writing or reviewing documentation, creating onboarding guides, or establishing documentation standards.
+description: Documentation best practices for READMEs, API docs, architecture docs, runbooks and developer guides. Use when writing or reviewing docs or setting documentation standards.
 ---
 
 # Technical Writing Skill

package/bundles/antigravity-plugin/skills/test-strategy/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: test-strategy
 context: fork
-description: Test planning and strategy for projects of any size. Use when defining what to test, choosing test types, setting coverage goals, building test pyramids, or planning quality gates. Produces TEST-STRATEGY.md with prioritized test plan. Routes to Tester agent for execution.
+description: "Plan what to test: test types, coverage goals, test pyramid, quality gates. Produces a prioritized TEST-STRATEGY.md for the Tester agent."
 ---
 
 # Test Strategy Skill

package/bundles/antigravity-plugin/skills/ui-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ui-review
-description: Review UI implementations against design requirements, accessibility standards (WCAG 2.2 AA), and brand guidelines. Use when reviewing designs or validating UI before release.
+description: Review a UI against design requirements, WCAG 2.2 AA and brand guidelines. Use when validating UI before release.
 ---
 
 # UI Review Skill

package/bundles/antigravity-plugin/skills/using-git-worktrees/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: using-git-worktrees
-description: Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
+description: "Use when starting feature work that needs isolation from the current workspace, or before executing an implementation plan: creates an isolated git worktree safely."
 ---
 
 # Using Git Worktrees

package/bundles/antigravity-plugin/skills/warm-editorial-ui/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: warm-editorial-ui
-description: Apply the "Warm Editorial Refinement" design system — a sophisticated, executive-grade aesthetic with warm cream surfaces (light mode) and warm charcoal surfaces (dark mode), Bahnschrift + Plus Jakarta Sans typography, generous rounded corners, multi-layer shadows, and a warm neutral palette. Supports both light and dark themes via CSS custom properties and the `.dark` class. Use this skill whenever the user wants to build an app, dashboard, component, or web UI using the abc-project visual style. Trigger on phrases like "use our design system", "apply our template", "make it look like abc-project", "use the warm editorial style", "use our brand template", "add dark mode", or any request to build a new tool/app/dashboard for XYZ Brand or similar contexts. This is the canonical design template for all new frontend builds.
+description: Apply the "Warm Editorial Refinement" design system (warm cream/charcoal surfaces, Bahnschrift + Plus Jakarta Sans, layered shadows), the canonical template for new frontend builds. Use for apps, dashboards or UI in the abc-project style, or on "use our design system", "apply our template", "make it look like abc-project", "use the warm editorial style", "use our brand template", "add dark mode", or a new tool for XYZ Brand.
 ---
 
 # Warm Editorial Refinement — Design System

package/bundles/antigravity-plugin/skills/webapp-testing/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: webapp-testing
 context: fork
-description: Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
+description: "Test local web apps with Playwright: verify frontend behavior, debug UI, capture screenshots and browser logs."
 license: Complete terms in LICENSE.txt
 ---
 

package/bundles/antigravity-plugin/skills/windows-deployment/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: windows-deployment
-description: "Deploy FastAPI + React/Vite apps to Windows Server with NSSM services, reverse proxy (IIS or nginx), and git-pull workflow. Use when deploying any web app to a Windows prod server, setting up NSSM services, configuring IIS or nginx reverse proxy, making code environment-aware for dev/prod, or troubleshooting prod deployment issues."
+description: "Deploy FastAPI + React/Vite apps to Windows Server with NSSM services, IIS or nginx reverse proxy and git-pull. Use for Windows prod deploys, NSSM, reverse proxy setup, dev/prod config, or prod troubleshooting."
 ---
 
 # Windows Server Deployment Skill

package/bundles/antigravity-plugin/warm_start_agy.py

@@ -91,38 +91,97 @@ def _first_existing(paths: list[str]) -> str:
     return ""
 
 
-def _branch_slug(root: str) -> str:
-    """Filesystem-safe current branch name, or "" when it can't be determined (best-effort)."""
+def scan_relays(root: str) -> list[tuple[str, dict]]:
+    results: list[tuple[str, dict]] = []
+    try:
+        from caddis_frontmatter import parse
+    except Exception:
+        _here = os.path.dirname(os.path.abspath(__file__))
+        for p in (
+            # Source tree: caddis_frontmatter.py is authored in claude-harness/scripts/.
+            os.path.join(os.path.dirname(_here), "scripts"),
+            # agy plugin: this file sits at the plugin root; scripts are in <plugin>/scripts/.
+            os.path.join(_here, "scripts"),
+            # Source tree, top-level scripts/ (harmless if the module is not there).
+            os.path.join(os.path.dirname(os.path.dirname(_here)), "scripts"),
+        ):
+            if os.path.isdir(p) and p not in sys.path:
+                sys.path.insert(0, p)
+        try:
+            from caddis_frontmatter import parse
+        except Exception:
+            def parse(t): return {}
+
+    for d in _ARTIFACT_DIRS:
+        relay_dir = os.path.join(root, d, "relay")
+        if not os.path.isdir(relay_dir):
+            continue
+        try:
+            entries = list(os.scandir(relay_dir))  # exhausting it closes the handle
+        except OSError:
+            continue
+        for entry in entries:
+            if entry.is_file() and entry.name.endswith(".md"):
+                try:
+                    with open(entry.path, encoding="utf-8", errors="ignore") as handle:
+                        text = handle.read()
+                    meta = parse(text)
+                    results.append((entry.path, meta))
+                except Exception:
+                    continue
+    return results
+
+
+def resolve_relay(root: str, session_id: str = "") -> tuple[str, str | None]:
+    """First existing relay doc for `root` and matched workstream name, else ("", None).
+
+    1. Session ID match takes precedence (matching meta['session_id'] with session_id).
+    2. Otherwise, if current branch is non-default, match relays by branch/workstream name.
+       If exactly 1 match: inject full relay.
+    3. If default branch or multiple/no matches: inject index (.caddis/relay.md).
+    """
+    relays = scan_relays(root)
+
+    # 1. Session ID match takes precedence
+    if session_id:
+        for path, meta in relays:
+            if meta.get("session_id") and str(meta.get("session_id")) == str(session_id):
+                ws = meta.get("workstream") or os.path.splitext(os.path.basename(path))[0]
+                return path, ws
+
+    # 2. Branch lookup (best-effort)
     try:
         branch = subprocess.run(
             ["git", "-C", root, "rev-parse", "--abbrev-ref", "HEAD"],
             capture_output=True, text=True, timeout=3,
         ).stdout.strip()
     except Exception:
-        return ""
-    if not branch or branch == "HEAD":
-        return ""
-    return "".join(c if (c.isalnum() or c in "-_.") else "-" for c in branch)
-
-
-def resolve_relay(root: str) -> str:
-    """First existing relay doc for `root`, else "".
-
-    Preference order mirrors inject_relay.py:
-      1. .caddis/relay/<branch>.md          (per-branch team mode)
-      2. .caddis/relay.md                   (solo/default)
-      3. .claude/relay/<branch>.md          (legacy per-branch)
-      4. relay.md                           (legacy repo root)
-    """
-    slug = _branch_slug(root)
-    candidates: list[str] = []
-    if slug:
-        candidates += [os.path.join(root, d, "relay", f"{slug}.md") for d in _ARTIFACT_DIRS]
-    candidates += [os.path.join(root, d, "relay.md") for d in _ARTIFACT_DIRS]
-    if slug:
-        candidates.append(os.path.join(root, ".claude", "relay", f"{slug}.md"))
-    candidates.append(os.path.join(root, "relay.md"))
-    return _first_existing(candidates)
+        branch = ""
+
+    default_branches = {"main", "master", "trunk", "develop", "HEAD", ""}
+    slug = ""  # set below for a non-default branch; also read by the legacy fallback
+    if branch and branch not in default_branches:
+        slug = "".join(c if (c.isalnum() or c in "-_.") else "-" for c in branch)
+        matched = []
+        for path, meta in relays:
+            ws = meta.get("workstream")
+            b = meta.get("branch")
+            stem = os.path.splitext(os.path.basename(path))[0]
+            if (b and b in (branch, slug)) or (ws and ws in (branch, slug)) or stem in (branch, slug):
+                matched.append((path, ws or stem))
+        if len(matched) == 1:
+            return matched[0]
+
+    # 3. Fallback: index (.caddis/relay.md) or legacy files
+    # Index, then the legacy per-branch .claude/relay/<branch>.md, then a root relay.md --
+    # the order used before workstream relays existed.
+    legacy_branch = []
+    if branch and branch not in default_branches:
+        legacy_branch = [os.path.join(root, ".claude", "relay", f"{slug}.md")]
+    candidates = ([os.path.join(root, d, "relay.md") for d in _ARTIFACT_DIRS] + legacy_branch
+                  + [os.path.join(root, "relay.md")])
+    idx_path = _first_existing(candidates)
+    return idx_path, None
 
 
 def truncate_relay(text: str) -> str:
@@ -270,25 +329,60 @@ def main() -> None:
         conversation = str(data.get("conversationId") or "").strip()
 
         blocks = []
+        open_work_blocks = []
         for root in roots:
-            relay = resolve_relay(root)
-            if not relay:
+            if conversation and _already_injected(root, conversation):
                 continue
+            relay, matched_ws = resolve_relay(root, conversation)
+            text = ""
+            if relay:
+                try:
+                    with open(relay, encoding="utf-8") as handle:
+                        text = handle.read().strip()
+                except Exception as _exc:
+                    _hook_note("agy relay read", _exc, root)
+            if text:
+                # Label the block ONLY when there is more than one root. A single-root session
+                # must produce byte-identical output to before this change.
+                if len(roots) > 1:
+                    blocks.append("relay for " + os.path.basename(root.rstrip("/\\")) + ":")
+                blocks.append(truncate_relay(text))
+
+            # Open-work rows as plain text without seeding instruction. Shown with or without a
+            # relay: to-dos and plan phases exist before the first handoff writes one.
+            shown_open_work = False
             try:
-                text = open(relay, encoding="utf-8").read().strip()
+                from pathlib import Path as _Path
+                # agy plugin: warm_start_agy.py sits at the plugin root, scripts in <plugin>/scripts.
+                # Source tree: claude-harness/agy -> <repo>/scripts, where caddis_todo.py is authored.
+                _here = os.path.dirname(os.path.abspath(__file__))
+                for _sc in (os.path.join(os.path.dirname(os.path.dirname(_here)), "scripts"),
+                            os.path.join(_here, "scripts")):
+                    if os.path.isdir(_sc) and _sc not in sys.path:
+                        sys.path.insert(0, _sc)
+                import caddis_todo
+                open_items = caddis_todo.open_work(_Path(root), matched_ws)
+                if open_items:
+                    # Same budget as the Claude Code hook: next 5 phases, 5 ad-hoc items.
+                    phases = [r for r in open_items if r.get("kind") == "phase"][:5]
+                    todos = [r for r in open_items if r.get("kind") != "phase"][:5]
+                    shown = phases + todos
+                    ow_lines = ["## Open work"]
+                    if len(open_items) > len(shown):
+                        ow_lines.append(f"(+{len(open_items) - len(shown)} more open items — run /catchup to see them.)")
+                    for row in shown:
+                        ow_lines.append(f"- {row['id']} [{row['kind']}] {' '.join(str(row['title']).split())[:100]}")
+                    if len(roots) > 1:
+                        open_work_blocks.append("open work for " + os.path.basename(root.rstrip("/\\")) + ":\n" + "\n".join(ow_lines))
+                    else:
+                        open_work_blocks.append("\n".join(ow_lines))
+                    shown_open_work = True
             except Exception as _exc:
-                _hook_note("agy relay read", _exc, root)
-                continue
-            if not text:
-                continue
-            if conversation and _already_injected(root, conversation):
-                continue
-            # Label the block ONLY when there is more than one root. A single-root session
-            # must produce byte-identical output to before this change.
-            if len(roots) > 1:
-                blocks.append("relay for " + os.path.basename(root.rstrip("/\\")) + ":")
-            blocks.append(truncate_relay(text))
-            if conversation:
+                _hook_note("agy open work injection", _exc, root)
+
+            # A relay that exists but failed to read must not be marked injected just because
+            # open work was shown: the next invocation retries the relay.
+            if conversation and (text or (not relay and shown_open_work)):
                 _mark_injected(root, conversation)
 
         # agy has no SessionStart event, so this first invocation is also where the freshness
@@ -298,12 +392,14 @@ def main() -> None:
         for root in roots:
             fresh.extend(freshness_lines(root))
 
-        if not blocks and not fresh:
+        if not blocks and not fresh and not open_work_blocks:
             return
         parts = []
         if blocks:
             parts.append(RELAY_FRAME_HEADER + "\n" + "\n\n".join(blocks)
                          + "\n\n" + RELAY_FRAME_FOOTER)
+        if open_work_blocks:
+            parts.append("\n\n".join(open_work_blocks))
         if fresh:
             parts.append("\n".join(fresh))
         payload = json.dumps({"injectSteps": [{"ephemeralMessage": "\n\n".join(parts)}]})

package/bundles/antigravity-plugin-extras/plugin.json

@@ -1,5 +1,5 @@
 {
   "name": "caddis-extras",
-  "version": "1.3.39",
+  "version": "1.3.40",
   "description": "caddis-extras — the long-tail skills for the Antigravity (agy) caddis plugin; install alongside caddis for the full set."
 }

package/bundles/antigravity-plugin-extras/skills/_registry.md

@@ -11,10 +11,10 @@
 
 | Skill | Path | When to Use |
 |-------|------|-------------|
-| Aws Agentic Ai | `aws-agentic-ai/` | AWS Bedrock AgentCore comprehensive expert for deploying and managing all AgentCore services. Use when working with Gateway, Runtime, Memory, Identity, or any AgentCore component. Covers MCP target deployment, credential management, schema optimization, runtime configuration, memory management, and identity services. |
-| Aws Cdk Development | `aws-cdk-development/` | AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure programmatically. Covers CDK app structure, construct patterns, stack composition, and deployment workflows. |
-| Aws Cost Operations | `aws-cost-operations/` | This skill provides AWS cost optimization, monitoring, and operational best practices with integrated MCP servers for billing analysis, cost estimation, observability, and security assessment. |
-| Aws Serverless Eda | `aws-serverless-eda/` | AWS serverless and event-driven architecture expert based on Well-Architected Framework. Use when building serverless APIs, Lambda functions, REST APIs, microservices, or async workflows. Covers Lambda with TypeScript/Python, API Gateway (REST/HTTP), DynamoDB, Step Functions, EventBridge, SQS, SNS, and serverless patterns. Essential when user mentions serverless, Lambda, API Gateway, event-driven, async processing, queues, pub/sub, or wants to build scalable serverless applications with AWS best practices. |
+| Aws Agentic Ai | `aws-agentic-ai/` | AWS Bedrock AgentCore expert: deploy and manage Gateway, Runtime, Memory, Identity, MCP targets and credentials. Use when working with any AgentCore component. |
+| Aws Cdk Development | `aws-cdk-development/` | AWS CDK infrastructure as code in TypeScript/Python: stacks, constructs, deployment. Use when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure in code. |
+| Aws Cost Operations | `aws-cost-operations/` | AWS cost optimization, monitoring and operations, with MCP servers for billing analysis, cost estimation, observability and security assessment. |
+| Aws Serverless Eda | `aws-serverless-eda/` | AWS serverless and event-driven architecture. Use when the user mentions serverless, Lambda, API Gateway, DynamoDB, Step Functions, EventBridge, SQS, SNS, event-driven, async processing, queues or pub/sub. |
 | Building Ai Agent On Cloudflare | `building-ai-agent-on-cloudflare/` | | |
 | Building Mcp Server On Cloudflare | `building-mcp-server-on-cloudflare/` | | |
 
@@ -23,15 +23,15 @@
 | Skill | Path | When to Use |
 |-------|------|-------------|
 | Anchor Review | `anchor-review/` | Single-model adversarial review technique — 3-lens analysis with confidence scoring and self-challenge |
-| Api Client Patterns | `api-client-patterns/` | Typed API client patterns for consuming REST APIs and tRPC. Use for typed fetch wrappers, zod response validation, API client factory, auth injection, TanStack Query (useQuery, useMutation, infinite queries, optimistic updates), tRPC end-to-end types, error handling with discriminated unions, OpenAPI client codegen, or pagination envelopes. Complements backend-development (server side) with client-side consumption patterns. |
+| Api Client Patterns | `api-client-patterns/` | Typed client-side API consumption: fetch wrappers, zod validation, auth injection, TanStack Query (useQuery, useMutation, optimistic updates), tRPC, OpenAPI codegen, pagination. Use when consuming REST or tRPC APIs. |
 | Architecture Design | `architecture-design/` | Design application architecture and system diagrams with layered patterns, Mermaid C4 diagrams, SQL Server data platform, and on-premise deployment considerations. |
-| Backend To Frontend Handoff Docs | `backend-to-frontend-handoff/` | Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'. |
+| Backend To Frontend Handoff Docs | `backend-to-frontend-handoff/` | Document a finished backend API for frontend integration. Use when the user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'. |
 | Caching Patterns | `caching-patterns/` | Caching strategies for Streamlit and FastAPI applications |
-| Code Explainer | `code-explainer/` | Explain code with visual diagrams, analogies, and step-by-step walkthroughs. Use when explaining how code works, teaching about a codebase, or answering "how does this work? |
-| Cross Review | `cross-review/` | Cross-vendor code review — have a different vendor's model (DeepSeek/GLM/any OpenAI-compatible endpoint) review the current diff to catch bugs a same-vendor reviewer misses. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff. |
-| Llm Application Dev | `llm-application-dev/` | Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation. |
-| Mcp Builder | `mcp-builder/` | Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). |
-| Observability | `observability/` | Structured logging, OpenTelemetry distributed tracing, metrics (RED method), health checks, and error tracking with Sentry. Use for structured logs, correlation IDs, PII redaction, OpenTelemetry setup, distributed tracing, metrics counters/histograms/gauges, SLO-based alerting, liveness/readiness probes, or Sentry integration. Dual Python/TypeScript examples throughout. |
+| Code Explainer | `code-explainer/` | Explain code with diagrams, analogies and step-by-step walkthroughs. Use when teaching a codebase or answering "how does this work?" |
+| Cross Review | `cross-review/` | Have a different vendor's model (DeepSeek, GLM, any OpenAI-compatible endpoint) review the current diff. Use after a phase is green and before commit/merge, or for a second opinion on a risky diff. |
+| Llm Application Dev | `llm-application-dev/` | LLM applications: prompt engineering, RAG and LLM integration. Use for AI-powered features, chatbots or LLM automation. |
+| Mcp Builder | `mcp-builder/` | Build high-quality MCP (Model Context Protocol) servers that let LLMs use external APIs and services, in Python (FastMCP) or Node/TypeScript (MCP SDK). |
+| Observability | `observability/` | Structured logging, correlation IDs, PII redaction, OpenTelemetry tracing, metrics (RED), SLO alerting, health probes and Sentry, in Python and TypeScript. Use when adding logs, traces, metrics or error tracking. |
 | Understand Anything | `understand-anything/` | > |
 
 ### Data
@@ -39,68 +39,68 @@
 | Skill | Path | When to Use |
 |-------|------|-------------|
 | Data Analysis | `data-analysis/` | Analyze datasets and generate insights with a systematic 5-phase workflow. Use when user provides data for analysis, asks about patterns, or needs visualizations. |
-| Data Loader | `data-loader/` | Load data from files (Excel, JSON, CSV) into databases. Use when user needs to import data files into any database system. Database-agnostic - supports SQL Server, PostgreSQL, MySQL, SQLite, and others. |
-| Data Validation | `data-validation/` | Data quality and validation patterns for ETL pipelines, API inputs, and data processing. Use when defining validation rules, building data quality checks, implementing schema validation, or designing data contracts. Covers Pydantic, Great Expectations patterns, and SQL-level constraints. |
+| Data Loader | `data-loader/` | Load Excel, JSON or CSV files into any database (SQL Server, PostgreSQL, MySQL, SQLite and others). Use when importing data files into a database. |
+| Data Validation | `data-validation/` | Data quality and validation for ETL, API inputs and pipelines: validation rules, schema validation, data contracts, Pydantic, Great Expectations, SQL constraints. |
 | Db Testing | `db-testing/` | Test, debug, and validate database connectivity and queries. Use when diagnosing connection errors, testing configurations, or validating queries before deployment. |
-| Schema Migration | `schema-migration/` | Migrate an application's data access layer from one database schema to another. Use when tables are renamed, consolidated, split, or columns change — and the app's queries, mappings, and abstraction layer must be updated without data loss. Read-only against the database. |
+| Schema Migration | `schema-migration/` | Migrate an app's data access layer when tables or columns are renamed, merged or split: update queries, mappings and abstractions without data loss. Read-only against the database. |
 
 ### Devops
 
 | Skill | Path | When to Use |
 |-------|------|-------------|
-| Changelog Generator | `changelog-generator/` | Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation. |
-| Deploy Local | `deploy-local/` | End-to-end local deployment loop for Gitea-hosted projects. Use when the user wants to commit on dev, push to remote, monitor the golden CI/build/deploy workflow, validate prod on the configured prod host, and fix lint/test/pipeline failures until deployment is healthy. |
-| Monorepo | `monorepo/` | Monorepo management with Turborepo and pnpm workspaces. Use for Turborepo setup, turbo.json task dependencies, remote caching, pnpm workspace protocol, shared packages (ui-library, config, types), affected-only CI/CD builds, or monorepo structure (apps/ vs packages/). Covers pitfalls like circular deps, version drift, and hoisting issues. |
-| Safe Cleanup | `safe-cleanup/` | Use BEFORE deleting any directory tree, clearing a scratchpad, removing git worktrees, or "tidying up" generated folders - especially on Windows, where a recursive delete that meets a junction or symlink destroys the link's TARGET. Also use when verifying that a Python venv or node_modules survived a cleanup, because pip check and file counts both report healthy on a half-deleted environment. |
-| Update Readme | `update-readme/` | Detect feature commits and update README sections (Features, API, Usage) with accurate repo-aware changes, then stage only README for a docs commit. Use when users add features/routes/components and want README maintained automatically. |
+| Changelog Generator | `changelog-generator/` | Create user-facing changelogs and release notes from git commit history, grouping changes and rewriting technical commits in plain language. |
+| Deploy Local | `deploy-local/` | Local deployment loop for Gitea-hosted projects: commit on dev, push, watch the golden CI/build/deploy workflow, check prod, and fix lint/test/pipeline failures until the deploy is healthy. |
+| Monorepo | `monorepo/` | Turborepo and pnpm workspaces: turbo.json tasks, remote caching, shared packages, affected-only CI, apps/ vs packages/ layout, and pitfalls like circular deps, version drift and hoisting. |
+| Safe Cleanup | `safe-cleanup/` | Use BEFORE deleting a directory tree, scratchpad or git worktree, or "tidying up" generated folders, especially on Windows, where deleting through a junction or symlink destroys its target; and to verify a venv or node_modules survived. |
+| Update Readme | `update-readme/` | Detect feature commits and update README sections (Features, API, Usage) to match, then stage only the README. Use when features, routes or components were added. |
 
 ### Docs
 
 | Skill | Path | When to Use |
 |-------|------|-------------|
-| Architecture Document | `architecture-document/` | Generate professional enterprise-grade HLD and LLD documents from the living Architecture.md. Outputs DOCX (editable) or PPTX (executive summary) using existing document skills. |
+| Architecture Document | `architecture-document/` | Generate enterprise HLD and LLD documents from the living Architecture.md, as DOCX (editable) or PPTX (executive summary). |
 | Data Lineage | `data-lineage/` | Generates End-to-End Data Lineage and Telemetry Specifications linking UI pages, API routes, database datasets, and ETL/SP producers for watch-sight observability. |
-| Doc Coauthoring | `doc-coauthoring/` | Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. |
-| Documentation Analyzer | `documentation-analyzer/` | Analyze codebases, explain code functionality, and generate comprehensive documentation. Use when documenting a project, creating README files, or understanding complex code. |
-| Hld | `hld/` | Generates High-Level Design (HLD) Markdown documentation and converts to Confluence Storage Format XHTML with native PlantUML diagrams and auto-generated legends. |
-| Lld | `lld/` | Generates Lower-Level Design (LLD) Markdown documentation and converts to Confluence Storage Format XHTML with native PlantUML diagrams and auto-generated legends. |
+| Doc Coauthoring | `doc-coauthoring/` | Structured workflow for co-authoring documentation: transfer context, refine by iteration, test it on readers. Use when the user is writing docs, proposals, technical specs or decision docs. |
+| Documentation Analyzer | `documentation-analyzer/` | Analyze a codebase, explain what the code does, and generate documentation such as README files. |
+| Hld | `hld/` | Generate High-Level Design (HLD) Markdown and convert it to Confluence Storage Format XHTML with PlantUML diagrams and legends. |
+| Lld | `lld/` | Generate Lower-Level Design (LLD) Markdown and convert it to Confluence Storage Format XHTML with PlantUML diagrams and legends. |
 | Naming Analyzer | `naming-analyzer/` | Suggest better variable, function, and class names based on context and conventions. |
-| Prd To Code | `prd-to-code/` | Transform PRD documents into working application code using a systematic 6-phase methodology. Use when starting projects from requirements or converting specs to implementation. |
+| Prd To Code | `prd-to-code/` | Turn a PRD into working application code with a 6-phase method. Use when starting a project from requirements or specs. |
 
 ### Frontend
 
 | Skill | Path | When to Use |
 |-------|------|-------------|
-| Algorithmic Art | `algorithmic-art/` | Create browser-based visual art using p5.js — generative art, interactive visualizations, animations, 3D scenes (WebGL), audio-reactive visuals, and data visualizations. 7 production modes with export to HTML, PNG, GIF, MP4, SVG. Use for generative art, algorithmic art, flow fields, particle systems, creative coding, or any p5.js visual. |
-| Artifacts Builder | `artifacts-builder/` | Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts. |
-| Banner Design | `banner-design/` | Design banners for social media, ads, website heroes, and print. Multiple art direction options across 22 styles (minimalist, gradient, bold typography, glassmorphism, 3D, neon, etc.) for Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, and print. |
-| Brand Design | `brand-design/` | Comprehensive brand design: logo generation (55 styles), corporate identity program (50 deliverables, CIP mockups), icon design (15 styles, SVG), and social photos (HTML-to-screenshot, multi-platform). Use for logo, CIP, icon, or social media visual design tasks. |
-| Brand Guidelines | `brand-guidelines/` | Apply brand colors and typography to artifacts. Use when brand colors, style guidelines, visual formatting, or company design standards apply. Ensures consistency across branded content. |
-| Brand Voice | `brand-voice/` | Brand voice, visual identity, messaging frameworks, asset management, and brand consistency. Use for branded content, tone of voice, marketing assets, brand compliance, and style guide work. |
-| Canvas Design | `canvas-design/` | Create beautiful visual art in .png and .pdf documents using design philosophy. Use when the user asks to create a poster, piece of art, design, or other static visual piece. Creates original visual designs. |
-| Design Md | `design-md/` | Google's open DESIGN.md specification for describing visual identities to coding agents. YAML tokens + Markdown rationale + npx CLI for WCAG validation and W3C DTCG/Tailwind export. Use for formal, agent-consumable design system documentation. |
-| Design System Tokens | `design-system-tokens/` | Token architecture and component specifications. Three-layer tokens (primitive → semantic → component), CSS variables, spacing/typography scales, and component state definitions. Use for design token creation and systematic design. |
-| Enterprise Dashboard Aesthetic System | `enterprise-dashboard-aesthetic-system/` | Use when: upgrading React/Vite enterprise dashboards, harmonizing dashboard pages, improving executive analytics UI aesthetics, creating cohesive dashboard design systems, adding tasteful motion, or turning data-heavy pages into a polished narrative cockpit. Applies to RevSight-style FastAPI + React + Tailwind + shadcn dashboards. |
-| Nextjs App Router | `nextjs-app-router/` | Next.js 13+ App Router conventions, Server vs Client Components, Server Actions, Middleware, data fetching, Metadata API, and route handlers. Use for Next.js App Router directory structure, Server Actions, SSR/RSC patterns, generateMetadata, layout/page/error/loading.tsx conventions, route groups, parallel routes, or hydration issues. Companion to react-dev and react-best-practices. |
-| Popular Web Designs | `popular-web-designs/` | 54 real-world design systems (Stripe, Linear, Vercel, Supabase, Apple, Notion, Cursor, etc.) as ready-to-use HTML/CSS reference. Exact color palettes, typography hierarchies, component specs, spacing, shadow systems, and font substitutions. Use when building UI that should match a specific company's aesthetic. |
-| React Useeffect | `react-useeffect/` | React useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives. |
+| Algorithmic Art | `algorithmic-art/` | Generative and algorithmic art with p5.js: flow fields, particle systems, animations, WebGL, audio-reactive visuals; exports HTML, PNG, GIF, MP4, SVG. Use for creative coding or any p5.js visual. |
+| Artifacts Builder | `artifacts-builder/` | Build elaborate multi-component claude.ai HTML artifacts with React, Tailwind CSS and shadcn/ui. Use for complex artifacts with state or routing, not simple single-file HTML. |
+| Banner Design | `banner-design/` | Design banners for social media, ads, website heroes and print, in 22 styles, sized for Facebook, X, LinkedIn, YouTube, Instagram and Google Display. |
+| Brand Design | `brand-design/` | Brand design: logos, corporate identity (CIP) mockups, SVG icons and social media visuals. Use for logo, CIP, icon or social visual design tasks. |
+| Brand Guidelines | `brand-guidelines/` | Apply brand colors and typography to artifacts. Use when brand colors, style guidelines or company design standards apply. |
+| Brand Voice | `brand-voice/` | Brand voice, tone, messaging frameworks and brand consistency. Use for branded content, marketing assets, brand compliance and style guides. |
+| Canvas Design | `canvas-design/` | Create original static visual art as .png or .pdf from a design philosophy. Use when the user asks for a poster, piece of art, design or other static visual. |
+| Design Md | `design-md/` | Google's DESIGN.md spec for describing a visual identity to coding agents: YAML tokens, Markdown rationale, CLI for WCAG checks and DTCG/Tailwind export. Use for agent-readable design system docs. |
+| Design System Tokens | `design-system-tokens/` | Design token architecture (primitive → semantic → component), CSS variables, spacing and type scales, component state specs. Use when creating design tokens. |
+| Enterprise Dashboard Aesthetic System | `enterprise-dashboard-aesthetic-system/` | Use when upgrading or harmonizing React/Vite enterprise dashboards: executive analytics UI, cohesive dashboard design systems, tasteful motion, polished data-heavy pages (FastAPI + React + Tailwind + shadcn). |
+| Nextjs App Router | `nextjs-app-router/` | Next.js App Router: Server vs Client Components, SSR/RSC, Server Actions, Middleware, data fetching, generateMetadata, route handlers, layout/page/error/loading.tsx, route groups, parallel routes, hydration issues. |
+| Popular Web Designs | `popular-web-designs/` | 54 real-world design systems (Stripe, Linear, Vercel, Apple, Notion and more) as HTML/CSS reference: colors, type, components, spacing. Use when UI should match a specific company's look. |
+| React Useeffect | `react-useeffect/` | React useEffect best practices from the official docs: when NOT to use an Effect, derived state, data fetching, synchronization. Use when writing or reviewing useEffect. |
 | Responsive Mobile Native | `responsive-mobile-native/` | > |
-| Shadcn Radix | `shadcn-radix/` | shadcn/ui component library, Radix UI primitives, theming with CSS variables, react-hook-form + zod forms, TanStack Table data tables, and cva variant composition. Use for shadcn setup, shadcn add, components.json, shadcn theming, Radix accessible components, shadcn form patterns, data tables, command palette, date picker, combobox, or drawer/sheet. References css-architecture for tokens and react-best-practices for structure. |
-| Sketch | `sketch/` | Generate 2-3 interactive HTML design variants to explore UI directions side-by-side before committing to production code. Use for early-stage design exploration, comparing layout approaches, or when asked to "sketch this screen" or "show me variants". |
+| Shadcn Radix | `shadcn-radix/` | shadcn/ui and Radix UI: setup (shadcn add, components.json), theming, react-hook-form + zod forms, TanStack Table data tables, cva variants, command palette, date picker, combobox, drawer/sheet. |
+| Sketch | `sketch/` | Generate 2-3 interactive HTML design variants to compare UI directions before production code. Use for early design exploration or when asked to "sketch this screen" or "show me variants". |
 | Slides | `slides/` | Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies. |
-| Streamlit Dev | `streamlit-dev/` | Build production-ready Streamlit dashboards with best-practice patterns, caching, components, and theming. Use when implementing any Streamlit page, component, chart, or UI feature. |
-| Theme Factory | `theme-factory/` | Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly. |
-| Ui Styling Patterns | `ui-styling-patterns/` | Create accessible user interfaces with shadcn/ui components (Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use for responsive layouts, accessible components, theme customization, dark mode, and consistent styling patterns. |
-| Ui Ux Intelligence | `ui-ux-intelligence/` | UI/UX design intelligence with CSV knowledge bases: 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types. Use when making design decisions that need data-backed palettes, font pairing lookups, or style-specific implementation guidance. |
+| Streamlit Dev | `streamlit-dev/` | Build production Streamlit dashboards: caching, components, theming. Use for any Streamlit page, component, chart or UI feature. |
+| Theme Factory | `theme-factory/` | Style artifacts (slides, docs, reports, HTML pages) with one of 10 preset themes or a newly generated theme. |
+| Ui Styling Patterns | `ui-styling-patterns/` | Accessible UIs with shadcn/ui, Radix and Tailwind CSS: responsive layouts, theming, dark mode and consistent styling. |
+| Ui Ux Intelligence | `ui-ux-intelligence/` | Data-backed UI/UX decisions from CSV knowledge bases: 50+ styles, 161 palettes, 57 font pairings, UX guidelines, chart types. Use to look up palettes, font pairs or style guidance. |
 | Webapp Development | `webapp-development/` | End-to-end web application development workflow with brand theming and standard patterns |
-| Word Cloud | `word-cloud/` | Generate beautiful word clouds — static or animated — from any input source. Handles text extraction from PDF, DOCX, XLSX, PPTX, HTML, CSV, TXT and produces production-ready components. Includes light/dark theming, sentiment/POS color coding, shape masking, and multiple animation modes. |
+| Word Cloud | `word-cloud/` | Generate static or animated word clouds from any text source (PDF, DOCX, XLSX, PPTX, HTML, CSV, TXT), with theming, sentiment coloring and shape masks. |
 
 ### Media
 
 | Skill | Path | When to Use |
 |-------|------|-------------|
-| Architecture Diagram | `architecture-diagram/` | Generate dark-themed technical architecture diagrams as self-contained HTML/SVG files. No external libraries or render tools needed — just a browser. Use for software system architecture, cloud infrastructure, microservice topologies, and deployment diagrams. |
-| Ascii Art | `ascii-art/` | Create text-based ASCII art using the right tool for the job — banners, borders, image conversion, pre-made art, and LLM-generated custom art. Decision-routing framework across pyfiglet, cowsay, TOIlet, boxes, and more. |
+| Architecture Diagram | `architecture-diagram/` | Dark-themed architecture diagrams as self-contained HTML/SVG, no external tools. Use for system, cloud, microservice and deployment diagrams. |
+| Ascii Art | `ascii-art/` | Create ASCII art (banners, borders, image conversion, custom art), choosing between pyfiglet, cowsay, TOIlet, boxes and more. |
 | Excalidraw | `excalidraw/` | Brand-themed Excalidraw diagrams for project documentation |
 | Plantuml | `plantuml/` | Brand-themed PlantUML diagrams for project documentation |
 | Svg Create | `svg-create/` | Brand-themed SVG diagrams with consistent color palette and accessible design |
@@ -110,31 +110,31 @@
 | Skill | Path | When to Use |
 |-------|------|-------------|
 | Github Issues | `github-issues/` | Create well-structured GitHub issues with proper labels, descriptions, and acceptance criteria. Use when creating bug reports, feature requests, or tracking tasks. |
-| Internal Comms | `internal-comms/` | Write internal communications using company formats. Use when writing status reports, leadership updates, company newsletters, FAQs, incident reports, project updates, or any internal communications. |
-| Jira Issues | `jira-issues/` | Create, update, and manage Jira issues from natural language. Use when the user wants to log bugs, create tickets, update issue status, or manage their Jira backlog. |
+| Internal Comms | `internal-comms/` | Write internal communications in company formats: status reports, leadership updates, newsletters, FAQs, incident reports, project updates. |
+| Jira Issues | `jira-issues/` | Create, update and manage Jira issues from natural language: log bugs, create tickets, update status, manage the backlog. |
 
 ### Testing
 
 | Skill | Path | When to Use |
 |-------|------|-------------|
-| Component Testing | `component-testing/` | React component testing with Vitest, Testing Library, MSW, and renderHook. Use for Vitest setup, jsdom/happy-dom config, Testing Library queries, userEvent, component unit tests, testing React hooks, MSW API mocking, snapshot testing, or testing loading/error states. Complements playwright (E2E) and tdd-workflow (methodology). |
-| Performance Testing | `performance-testing/` | Performance testing, load testing, and benchmarking for APIs, databases, and web applications. Use when planning load tests, setting performance budgets, profiling bottlenecks, or validating scalability. Covers Locust, k6, pytest-benchmark, browser performance, and database query profiling. |
+| Component Testing | `component-testing/` | React component tests with Vitest, Testing Library, userEvent, renderHook and MSW: setup, queries, hooks, API mocking, snapshots, loading/error states. E2E is playwright; method is tdd-workflow. |
+| Performance Testing | `performance-testing/` | Performance and load testing for APIs, databases and web apps: budgets, profiling, scalability, with Locust, k6 and pytest-benchmark. |
 | Ui Testing | `ui-testing/` | Create automated UI tests using Playwright for Streamlit and web applications. Use when writing end-to-end tests, automating UI testing, or testing new features. |
 
 ### Workflow
 
 | Skill | Path | When to Use |
 |-------|------|-------------|
-| Agent Md Refactor | `agent-md-refactor/` | Refactor bloated agent instruction files (AGENTS.md, .cursorrules, .github/ files, etc.) to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation. |
-| Agent Orchestration | `agent-orchestration/` | End-to-end blueprint for orchestrating the full agent pipeline — from spec intake through planning, implementation, testing, and debugging — plus the multi-model fan-out rules (when a second model is worth it, the intent→model map, and the cost guardrails) |
+| Agent Md Refactor | `agent-md-refactor/` | Refactor bloated agent instruction files (AGENTS.md, .cursorrules, .github/ files) into linked, progressively disclosed docs. |
+| Agent Orchestration | `agent-orchestration/` | Blueprint for orchestrating the agent pipeline from spec to planning, implementation, testing and debugging, plus when a second model is worth it, the intent→model map and cost guardrails. |
 | Ask Questions If Underspecified | `asking-questions/` | Clarify requirements before implementing. Do not use automatically, only when invoked explicitly. |
-| Data Contract Pipeline | `data-contract-pipeline/` | **WORKFLOW SKILL** - Build, audit, and validate data-to-UI contracts for apps. Use whenever the user mentions data mapping, UI lineage, DB-to-UI, DisplayDTOs, source-to-screen mapping, data contracts, schema drift, typed API responses, frontend type alignment, mockup grounding, requirements-to-UI mapping, or asks whether a UI is backed by real DB/file data. Works for DBs, JSON, Markdown, CSV, XLSX, YAML, APIs, and UI mockups. |
-| Developer Growth Analysis | `developer-growth-analysis/` | Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs. |
-| File Organizer | `file-organizer/` | Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort. |
-| Game Changing Features | `game-changing-features/` | Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'. |
-| Golden Nuggets | `golden-nuggets/` | Extract durable tribal knowledge ('gold nuggets') from a codebase or a set of changed files and route each to its correct destination - instruction file, runbook, hub, or (in CI capture mode) a review inbox. This SKILL.md is the single source of truth for nugget categories, routing rules, write rules, inbox format, and verification gates. It is read by the knowledge-transfer agent (pipeline mode), by the /golden-nuggets prompt (independent mode), and referenced by the CI extraction script (capture mode). Use when capturing what was learned after a feature, fix, sprint, incident, or release. |
-| Golden Plan | `golden-plan/` | USE THIS SKILL whenever a user asks for a comprehensive implementation plan, a full-stack build plan, a UI+backend plan, or says 'create a plan for building X' where X spans multiple phases or systems. Also activate when the user says 'plan this project', 'I need a detailed plan', 'build plan', 'implementation plan', or attaches a mockup/wireframe and asks how to build it. Produces a zero-ambiguity, evidence-gated plan with self-contained per-phase prompts, exhaustive data binding tables, per-phase validation checklists, and a global quality gate. Evidence-gated: before writing phases, verify required artefacts (mockup, data sample, API contract, scaffold inventory); if any BLOCKER is missing, ask for it and wait before proceeding. Dual-mode: generic by default, junai-pipeline only when explicitly requested. Agent-agnostic - any agent with read/search/edit tools can use this skill. |
+| Data Contract Pipeline | `data-contract-pipeline/` | Build, audit and validate data-to-UI contracts. Use when the user mentions data mapping, UI lineage, DB-to-UI, DisplayDTOs, source-to-screen mapping, data contracts, schema drift, typed API responses, mockup grounding, or asks whether a UI is backed by real data. |
+| Developer Growth Analysis | `developer-growth-analysis/` | Analyze recent Claude Code chat history for coding patterns and gaps, find learning resources on HackerNews, and send a growth report to Slack DMs. |
+| File Organizer | `file-organizer/` | Organize files and folders by context: find duplicates, suggest better structures, automate cleanup. |
+| Game Changing Features | `game-changing-features/` | Find 10x product opportunities and high-leverage features. Use when the user mentions '10x', says 'what would make this 10x better', 'product strategy', or 'what should we build next'. |
+| Golden Nuggets | `golden-nuggets/` | Extract durable tribal knowledge ('gold nuggets') from a codebase or changed files and route each to an instruction file, runbook, hub or CI review inbox. Use after a feature, fix, sprint, incident or release. |
+| Golden Plan | `golden-plan/` | Use when the user asks for a comprehensive multi-phase plan (full-stack, UI + backend), says 'create a plan for building X', 'plan this project', 'I need a detailed plan', 'build plan', 'implementation plan', or attaches a mockup and asks how to build it. Produces an evidence-gated plan with self-contained phase prompts and validation gates. |
 | Intent Writer | `intent-writer/` | Structure freetext ideas, backlog items, or vague requirements into a formal Intent Document that preserves user intent across the entire agent pipeline chain. |
-| Receiving Code Review | `receiving-code-review/` | Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation |
-| Setup Project Ai | `setup-project-ai/` | Install or refresh the agent-agnostic development harness in a project — an AGENTS.md-canonical rules hierarchy (root + per-folder) with a CLAUDE.md @import shim beside each, lean subagents, slash commands, settings.json, and the frontend/python test env. USE THIS SKILL when setting up AI resources on a new or existing project, bootstrapping the rules files (AGENTS.md/CLAUDE.md), adding subagents/commands, or when the user says 'set up the harness', 'setup-project-ai', 'generate CLAUDE.md', 'onboard this project to Claude Code / Codex / agy', or runs /setup-project-ai. Combines a deterministic generator (scripts/setup_project_ai.py) for the must-not-vary mechanics with an AI enrichment step that curates project-specific AGENTS.md content. |
+| Receiving Code Review | `receiving-code-review/` | Use when receiving code review feedback, before implementing it, especially if it seems unclear or wrong: verify with technical rigor, no performative agreement or blind implementation. |
+| Setup Project Ai | `setup-project-ai/` | Install or refresh the agent-agnostic harness in a project: AGENTS.md rules with CLAUDE.md shims, subagents, commands and settings. Use when setting up AI resources on a project, or the user says 'set up the harness', 'setup-project-ai', 'generate CLAUDE.md', 'onboard this project to Claude Code / Codex / agy', or runs /setup-project-ai. |
 | Verification Loop | `verification-loop/` | Systematic code change verification — lint, test, type-check, review |

package/bundles/antigravity-plugin-extras/skills/agent-md-refactor/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-md-refactor
 context: fork
-description: Refactor bloated agent instruction files (AGENTS.md, .cursorrules, .github/ files, etc.) to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
+description: Refactor bloated agent instruction files (AGENTS.md, .cursorrules, .github/ files) into linked, progressively disclosed docs.
 license: MIT
 ---
 

package/bundles/antigravity-plugin-extras/skills/agent-orchestration/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agent-orchestration
-description: "End-to-end blueprint for orchestrating the full agent pipeline — from spec intake through planning, implementation, testing, and debugging — plus the multi-model fan-out rules (when a second model is worth it, the intent→model map, and the cost guardrails)"
+description: "Blueprint for orchestrating the agent pipeline from spec to planning, implementation, testing and debugging, plus when a second model is worth it, the intent→model map and cost guardrails."
 ---
 
 # Agent Orchestration Blueprint