@techwavedev/agi-agent-kit 1.6.1 → 1.6.3

package/templates/skills/extended/other/acceptance-orchestrator/SKILL.md

@@ -0,0 +1,152 @@
+---
+name: acceptance-orchestrator
+description: Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
+risk: safe
+source: community
+date_added: "2026-03-12"
+---
+
+# Acceptance Orchestrator
+
+## Overview
+
+Orchestrate coding work as a state machine that ends only when acceptance criteria are verified with evidence or the task is explicitly escalated.
+
+Core rule: **do not optimize for "code changed"; optimize for "DoD proven".**
+
+## Required Sub-Skills
+
+- `create-issue-gate`
+- `closed-loop-delivery`
+- `verification-before-completion`
+
+Optional supporting skills:
+- `deploy-dev`
+- `pr-watch`
+- `pr-review-autopilot`
+- `git-ship`
+
+## Inputs
+
+Require these inputs:
+- issue id or issue body
+- issue status
+- acceptance criteria (DoD)
+- target environment (`dev` default)
+
+Fixed defaults:
+- max iteration rounds = `2`
+- PR review polling = `3m -> 6m -> 10m`
+
+## State Machine
+
+- `intake`
+- `issue-gated`
+- `executing`
+- `review-loop`
+- `deploy-verify`
+- `accepted`
+- `escalated`
+
+## Workflow
+
+1. **Intake**
+   - Read issue and extract task goal + DoD.
+
+2. **Issue gate**
+   - Use `create-issue-gate` logic.
+   - If issue is not `ready` or execution gate is not `allowed`, stop immediately.
+   - Do not implement anything while issue remains `draft`.
+
+3. **Execute**
+   - Hand off to `closed-loop-delivery` for implementation and local verification.
+
+4. **Review loop**
+   - If PR feedback is relevant, batch polling windows as:
+     - wait `3m`
+     - then `6m`
+     - then `10m`
+   - After the `10m` round, stop waiting and process all visible comments together.
+
+5. **Deploy and runtime verification**
+   - If DoD depends on runtime behavior, deploy only to `dev` by default.
+   - Verify with real logs/API/Lambda behavior, not assumptions.
+
+6. **Completion gate**
+   - Before any claim of completion, require `verification-before-completion`.
+   - No success claim without fresh evidence.
+
+## Stop Conditions
+
+Move to `accepted` only when every acceptance criterion has matching evidence.
+
+Move to `escalated` when any of these happen:
+- DoD still fails after `2` full rounds
+- missing secrets/permissions/external dependency blocks progress
+- task needs production action or destructive operation approval
+- review instructions conflict and cannot both be satisfied
+
+## Human Gates
+
+Always stop for human confirmation on:
+- prod/stage deploys beyond agreed scope
+- destructive git/data operations
+- billing or security posture changes
+- missing user-provided acceptance criteria
+
+## Output Contract
+
+When reporting status, always include:
+- `Status`: intake / executing / accepted / escalated
+- `Acceptance Criteria`: pass/fail checklist
+- `Evidence`: commands, logs, API results, or runtime proof
+- `Open Risks`: anything still uncertain
+- `Need Human Input`: smallest next decision, if blocked
+
+Do not report "done" unless status is `accepted`.
+
+---
+
+<!-- AGI-INTEGRATION-START -->
+
+## AGI Framework Integration
+
+> **Adapted for [@techwavedev/agi-agent-kit](https://www.npmjs.com/package/@techwavedev/agi-agent-kit)**
+> Original source: [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills)
+
+### Memory-First Protocol
+
+Retrieve prior deployment configurations, rollback procedures, and incident post-mortems. Avoid re-discovering infrastructure patterns.
+
+```bash
+# Check for prior infrastructure context before starting
+python3 execution/memory_manager.py auto --query "deployment configuration and patterns for Acceptance Orchestrator"
+```
+
+### Storing Results
+
+After completing work, store infrastructure decisions for future sessions:
+
+```bash
+python3 execution/memory_manager.py store \
+  --content "Deployment pipeline: configured blue-green deployment with health checks on port 8080" \
+  --type technical --project <project> \
+  --tags acceptance-orchestrator devops
+```
+
+### Multi-Agent Collaboration
+
+Broadcast deployment changes so frontend and backend agents update their configurations accordingly.
+
+```bash
+python3 execution/cross_agent_context.py store \
+  --agent "<your-agent>" \
+  --action "Deployed infrastructure changes — updated CI/CD pipeline with new health check endpoints" \
+  --project <project>
+```
+
+### Playbook Integration
+
+Use the `ship-saas-mvp` or `full-stack-deploy` playbook to sequence this skill with testing, documentation, and deployment verification.
+
+<!-- AGI-INTEGRATION-END -->

package/templates/skills/extended/other/antigravity-skill-orchestrator/README.md

@@ -0,0 +1,32 @@
+# antigravity-skill-orchestrator
+
+A meta-skill package for the Antigravity IDE ecosystem.
+
+## Overview
+
+The `antigravity-skill-orchestrator` is an intelligent meta-skill that enhances an AI agent's ability to handle complex, multi-domain tasks. It provides strict guidelines and workflows enabling the agent to:
+
+1. **Evaluate Task Complexity**: Implementing guardrails to prevent the overuse of specialized skills on simple, straightforward tasks.
+2. **Dynamically Select Skills**: Identifying the best combination of skills for a given complex problem.
+3. **Track Skill Combinations**: Utilizing the `agent-memory-mcp` skill to store, search, and retrieve successful skill combinations for future reference, building institutional knowledge over time.
+
+## Installation
+
+This skill is designed to be used within the Antigravity IDE and integrated alongside the existing suite of AWESOME skills.
+
+Make sure you have the `agent-memory-mcp` skill installed and running to take full advantage of the combination tracking feature.
+
+## Usage
+
+When executing a prompt with an AI assistant via the Antigravity IDE, you can invoke this skill:
+
+```bash
+@antigravity-skill-orchestrator Please build a comprehensive dashboard integrating fetching live data, an interactive UI, and performance optimizations.
+```
+
+The agent will then follow the directives in the `SKILL.md` to break down the task, search memory for similar challenges, assemble the right team of skills (e.g., `@react-patterns` + `@nodejs-backend-patterns`), and execute the task without over-complicating it.
+
+---
+
+**Author:** [Wahid](https://github.com/wahidzzz)  
+**Source:** [antigravity-skill-orchestrator](https://github.com/wahidzzz/antigravity-skill-orchestrator)

package/templates/skills/extended/other/antigravity-skill-orchestrator/SKILL.md

@@ -0,0 +1,169 @@
+---
+name: antigravity-skill-orchestrator
+description: "A meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations using agent-memory-mcp, and prevents skill overuse for simple tasks."
+category: meta
+risk: safe
+source: community
+tags: "[orchestration, meta-skill, agent-memory, task-evaluation]"
+date_added: "2026-03-13"
+---
+
+# antigravity-skill-orchestrator
+
+## Overview
+
+The `skill-orchestrator` is a meta-skill designed to enhance the AI agent's ability to tackle complex problems. It acts as an intelligent coordinator that first evaluates the complexity of a user's request. Based on that evaluation, it determines if specialized skills are needed. If they are, it selects the right combination of skills, explicitly tracks these combinations using `@agent-memory-mcp` for future reference, and guides the agent through the execution process. Crucially, it includes strict guardrails to prevent the unnecessary use of specialized skills for simple tasks that can be solved with baseline capabilities.
+
+## When to Use This Skill
+
+- Use when tackling a complex, multi-step problem that likely requires multiple domains of expertise.
+- Use when you are unsure which specific skills are best suited for a given user request, and need to discover them from the broader ecosystem.
+- Use when the user explicitly asks to "orchestrate", "combine skills", or "use the best tools for the job" on a significant task.
+- Use when you want to look up previously successful combinations of skills for a specific type of problem.
+
+## Core Concepts
+
+### Task Evaluation Guardrails
+Not every task requires a specialized skill. For straightforward issues (e.g., small CSS fixes, simple script writing, renaming a variable), **DO NOT USE** specialized skills. Over-engineering simple tasks wastes tokens and time. 
+
+Additionally, the orchestrator is strictly forbidden from creating new skills. Its sole purpose is to combine and use existing skills provided by the community or present in the current environment.
+
+Before invoking any skills, evaluate the task:
+1. **Is the task simple/contained?** Solve it directly using the agent's ordinary file editing, search, and terminal capabilities available in the current environment.
+2. **Is the task complex/multi-domain?** Only then should you proceed to orchestrate skills.
+
+### Skill Selection & Combinations
+When a task is deemed complex, identify the necessary domains (e.g., frontend, database, deployment). Search available skills in the current environment to find the most relevant ones. If the required skills are not found locally, consult the master skill catalog.
+
+### Master Skill Catalog
+The Antigravity ecosystem maintains a master catalog of highly curated skills at `https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md`. When local skills are insufficient, fetch this catalog to discover appropriate skills across the 9 primary categories:
+- `architecture`
+- `business`
+- `data-ai`
+- `development`
+- `general`
+- `infrastructure`
+- `security`
+- `testing`
+- `workflow`
+
+### Memory Integration (`@agent-memory-mcp`)
+To build institutional knowledge, the orchestrator relies on the `agent-memory-mcp` skill to record and retrieve successful skill combinations.
+
+## Step-by-Step Guide
+
+### 1. Task Evaluation & Guardrail Check
+[Triggered when facing a new user request that might need skills]
+1. Read the user's request.
+2. Ask yourself: "Can I solve this efficiently with just basic file editing and terminal commands?"
+3. If YES: Proceed without invoking specialized skills. Stop the orchestration here.
+4. If NO: Proceed to step 2.
+
+### 2. Retrieve Past Knowledge
+[Triggered if the task is complex]
+1. Use the `memory_search` tool provided by `agent-memory-mcp` to search for similar past tasks.
+   - Example query: `memory_search({ query: "skill combination for react native and firebase", type: "skill_combination" })`
+2. If a working combination exists, read the details using `memory_read`.
+3. If no relevant memory exists, proceed to Step 3.
+
+### 3. Discover and Select Skills
+[Triggered if no past knowledge covers this task]
+1. Analyze the core requirements (e.g., "needs a React UI, a Node.js backend, and a PostgreSQL database").
+2. Query the locally available skills using the current environment's skill list or equivalent discovery mechanism to find the best match for each requirement.
+3. **If local skills are insufficient**, fetch the master catalog with the web or command-line retrieval tools available in the current environment: `https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md`.
+4. Scan the catalog's 9 main categories to identify the appropriate skills to bring into the current context.
+5. Select the minimal set of skills needed. **Do not over-select.**
+
+### 4. Apply Skills and Track the Combination
+[Triggered after executing the task using the selected skills]
+1. Assume the task was completed successfully using a new combination of skills (e.g., `@react-patterns` + `@nodejs-backend-patterns` + `@postgresql`).
+2. Record this combination for future use using `memory_write` from `agent-memory-mcp`.
+   - Ensure the type is `skill_combination`.
+   - Provide a descriptive key and content detailing why these skills worked well together.
+
+## Examples
+
+### Example 1: Handling a Simple Task (The Guardrail in Action)
+**User Request:** "Change the color of the submit button in `index.css` to blue."
+**Action:** The skill orchestrator evaluates the task. It determines this is a "simple/contained" task. It **does not** invoke specialized skills. It directly edits `index.css`.
+
+### Example 2: Recording a New Skill Combination
+```javascript
+// Using the agent-memory-mcp tool after successfully building a complex feature
+memory_write({ 
+  key: "combination-ecommerce-checkout", 
+  type: "skill_combination", 
+  content: "For e-commerce checkouts, using @stripe-integration combined with @react-state-management and @postgresql effectively handles the full flow from UI state to payment processing to order recording.",
+  tags: ["ecommerce", "checkout", "stripe", "react"]
+})
+```
+
+### Example 3: Retrieving a Combination
+```javascript
+// At the start of a new e-commerce task
+memory_search({ 
+  query: "ecommerce checkout", 
+  type: "skill_combination" 
+})
+// Returns the key "combination-ecommerce-checkout", which you then read:
+memory_read({ key: "combination-ecommerce-checkout" })
+```
+
+## Best Practices
+
+- ✅ **Do:** Always evaluate task complexity *before* looking for skills.
+- ✅ **Do:** Keep the number of orchestrated skills as small as possible.
+- ✅ **Do:** Use highly descriptive keys when running `memory_write` so they are easy to search later.
+- ❌ **Don't:** Use this skill for simple bug fixes or UI tweaks.
+- ❌ **Don't:** Combine skills that have overlapping and conflicting instructions without a clear plan to resolve the conflict.
+- ❌ **Don't:** Attempt to construct, generate, or create new skills. Only combine what is available.
+
+## Related Skills
+
+- `@agent-memory-mcp` - Essential for this skill to function. Provides the persistent storage for skill combinations.
+
+---
+
+<!-- AGI-INTEGRATION-START -->
+
+## AGI Framework Integration
+
+> **Adapted for [@techwavedev/agi-agent-kit](https://www.npmjs.com/package/@techwavedev/agi-agent-kit)**
+> Original source: [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills)
+
+### Memory-First Protocol
+
+Retrieve prior design decisions (color palettes, typography, spacing scales) to maintain visual consistency across sessions. Cache generated design tokens.
+
+```bash
+# Check for prior frontend/design context before starting
+python3 execution/memory_manager.py auto --query "design system decisions and component patterns for Antigravity Skill Orchestrator"
+```
+
+### Storing Results
+
+After completing work, store frontend/design decisions for future sessions:
+
+```bash
+python3 execution/memory_manager.py store \
+  --content "Design system: adopted 8px grid, Inter font family, HSL color tokens with dark mode support" \
+  --type decision --project <project> \
+  --tags antigravity-skill-orchestrator frontend
+```
+
+### Multi-Agent Collaboration
+
+Share design decisions with backend agents (API contract changes) and QA agents (visual regression baselines).
+
+```bash
+python3 execution/cross_agent_context.py store \
+  --agent "<your-agent>" \
+  --action "Implemented UI components — new design system with accessibility compliance (WCAG 2.1 AA)" \
+  --project <project>
+```
+
+### Design Memory Persistence
+
+Store design system tokens and component decisions in Qdrant so any agent on any platform (Claude, Gemini, Cursor) can retrieve and apply consistent styling.
+
+<!-- AGI-INTEGRATION-END -->

package/templates/skills/extended/other/closed-loop-delivery/SKILL.md

@@ -0,0 +1,163 @@
+---
+name: closed-loop-delivery
+description: Use when a coding task must be completed against explicit acceptance criteria with minimal user re-intervention across implementation, review feedback, deployment, and runtime verification.
+risk: safe
+source: community
+date_added: "2026-03-12"
+---
+
+# Closed-Loop Delivery
+
+## Overview
+
+Treat each task as incomplete until acceptance criteria are verified in evidence, not until code is merely changed.
+
+Core rule: **deliver against DoD (Definition of Done), not against code diff size.**
+
+## When to Use
+
+Use this skill when:
+- user gives a coding/fix task and expects end-to-end completion
+- task spans code + tests + PR comments + dev deploy + runtime checks
+- repeated manual prompts like "now test", "now deploy", "now re-check PR" should be avoided
+
+Do not use this skill for:
+- pure Q&A/explanations
+- prod deploy requests without explicit human approval
+- tasks blocked by missing secrets/account access that cannot be inferred
+
+## Required Inputs
+
+Before execution, define these once:
+- task goal
+- acceptance criteria (DoD)
+- target environment (`dev` by default)
+- max iteration rounds (default `2`)
+
+If acceptance criteria are missing, request them once. If user does not provide, propose a concrete default and proceed.
+
+## Issue Gate Dependency
+
+Before execution, prefer using `create-issue-gate`.
+
+- If issue status is `ready` and execution gate is `allowed`, continue.
+- If issue status is `draft`, do not execute implementation/deploy/review loops.
+- Require user-provided, testable acceptance criteria before starting execution.
+
+## Default Workflow
+
+1. **Define DoD**
+   - Convert request into testable criteria.
+   - Example: checkout task DoD = "checkout endpoint returns a valid, openable third-party payment URL in dev".
+
+2. **Implement minimal change**
+   - Keep scope tight to task goal.
+
+3. **Verify locally**
+   - Run focused tests first, then broader checks if needed.
+
+4. **Review loop**
+   - Fetch PR comments/reviews.
+   - Classify valid vs non-actionable.
+   - Fix valid items, re-run verification.
+
+5. **Dev deploy + runtime verification**
+   - Deploy to `dev` when runtime behavior matters.
+   - Verify via real API/Lambda/log evidence against DoD.
+
+6. **Completion decision**
+   - Only report "done" when all DoD checks pass.
+   - Otherwise continue loop until pass or stop condition.
+
+## PR Comment Polling Policy
+
+Avoid noisy short polling by default. Use batched windows:
+
+- **Round 1:** wait `3m`, collect delta comments/reviews
+- **Round 2:** wait `6m`, collect delta again
+- **Final round:** wait `10m`, collect all remaining visible comments/reviews
+
+At each round:
+- process all new comments in one batch
+- avoid immediate re-poll after each single comment
+- after the `10m` round, stop waiting and proceed with all comments visible at that point
+
+If CI is still running, align polling to check completion boundaries instead of fixed rapid polling.
+
+## Human Gate Rules (Must Ask)
+
+Require explicit user confirmation for:
+- production/staging deploy beyond agreed scope
+- destructive operations (history rewrite, force push, data-destructive ops)
+- actions with billing/security posture changes
+- secret values not available in repo/runtime
+- ambiguous DoD that materially changes outcome
+
+## Iteration/Stop Conditions
+
+Stop and escalate with a concise blocker report when:
+- DoD still fails after max rounds (`2` default)
+- external dependency blocks progress (provider outage, missing creds, account permission)
+- conflicting review instructions cannot both be satisfied
+
+Escalation report must include:
+- what passed
+- what failed
+- evidence (commands/logs/API result)
+- smallest decision needed from user
+
+## Output Contract
+
+When claiming completion, always include:
+- acceptance criteria checklist with pass/fail
+- commands/tests run
+- runtime evidence (endpoint/Lambda/log key lines)
+- PR status (new actionable comments count)
+
+Do not claim success without evidence.
+
+---
+
+<!-- AGI-INTEGRATION-START -->
+
+## AGI Framework Integration
+
+> **Adapted for [@techwavedev/agi-agent-kit](https://www.npmjs.com/package/@techwavedev/agi-agent-kit)**
+> Original source: [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills)
+
+### Memory-First Protocol
+
+Retrieve prior deployment configurations, rollback procedures, and incident post-mortems. Avoid re-discovering infrastructure patterns.
+
+```bash
+# Check for prior infrastructure context before starting
+python3 execution/memory_manager.py auto --query "deployment configuration and patterns for Closed Loop Delivery"
+```
+
+### Storing Results
+
+After completing work, store infrastructure decisions for future sessions:
+
+```bash
+python3 execution/memory_manager.py store \
+  --content "Deployment pipeline: configured blue-green deployment with health checks on port 8080" \
+  --type technical --project <project> \
+  --tags closed-loop-delivery devops
+```
+
+### Multi-Agent Collaboration
+
+Broadcast deployment changes so frontend and backend agents update their configurations accordingly.
+
+```bash
+python3 execution/cross_agent_context.py store \
+  --agent "<your-agent>" \
+  --action "Deployed infrastructure changes — updated CI/CD pipeline with new health check endpoints" \
+  --project <project>
+```
+
+### Playbook Integration
+
+Use the `ship-saas-mvp` or `full-stack-deploy` playbook to sequence this skill with testing, documentation, and deployment verification.
+
+<!-- AGI-INTEGRATION-END -->