@techwavedev/agi-agent-kit 1.5.0 → 1.5.2

package/templates/base/.agent/rules/core_rules.md

@@ -0,0 +1,69 @@
+---
+description: Core system rules and behavior requirements for all AI agents
+---
+
+# 🤖 Agent Core Rules (MANDATORY)
+
+You are operating within the `AGI Agent Kit` deterministic framework.
+
+## 1. Zero Tolerance Probabilistic Execution
+
+- Do NOT perform complex, multi-step data transformations using inline code snippets if an `execution/` script exists for it.
+- **You are the orchestrator.** Rely on the `execution/` scripts to handle logic, files, and queries deterministically.
+
+## 2. Memory is Mandatory (Qdrant & Ollama)
+
+You are REQUIRED to actively use Qdrant Semantic Memory during EVERY task.
+Failure to call these scripts is strictly considered a bug.
+
+### Before Beginning A Complex Task
+
+You MUST retrieve context to save tokens and reuse past logic:
+
+```bash
+python3 execution/memory_manager.py auto --query "<summary of user request>"
+```
+
+- If it returns `cache_hit: true`, use the cache.
+- If it returns `source: memory`, inject those context chunks securely into your answer.
+
+### After Delivering A Task or Making a Decision (REQUIRED)
+
+You MUST store key learnings for future sessions:
+
+```bash
+python3 execution/memory_manager.py store \
+  --content "<what was decided, patterned, or solved>" \
+  --type decision \
+  --project "<project-name>" \
+  --tags <relevant-tags>
+```
+
+**Types:** `decision`, `code`, `error`, `technical`, `conversation`
+
+## 3. Self-Annealing Pattern
+
+If a script fails with an error:
+
+1. Do NOT crash or immediately give up.
+2. Read the script output (which contains structured JSON error messages).
+3. Attempt to fix parameters, read the docs, and try again.
+4. If it's a new failure mode you figured out, **store it in memory** using `memory_manager.py` so you remember next time.
+
+## 4. Workflows and Playbooks
+
+- You can execute multi-step playbooks using the workflow engine:
+  ```bash
+  python3 execution/workflow_engine.py status
+  ```
+- Before suggesting complex pipelines, check `.agent/workflows/` or the Workflow Engine for pre-existing playbooks.
+
+## 5. Prove Your Work
+
+The user expects you to leave an auditable trail of memory usage.
+
+```bash
+python3 execution/memory_usage_proof.py --check --since 60
+```
+
+Run this to ensure your `store` command actually succeeded!

package/templates/skills/SKILLS_CATALOG.md

@@ -118,7 +118,7 @@
 | `typescript-advanced-types`                      | 🟡 Full   | Master TypeScript's advanced type system including generics, conditional types,  |
 | `ui-skills`                                      | 🟡 Full   | Opinionated, evolving constraints to guide agents when building interfaces       |
 | `ui-ux-designer`                                 | 🟡 Full   | Create interface designs, wireframes, and design systems. Masters                |
-| `ui-ux-pro-max`                                  | 🟡 Full   | UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts,  |
+| `ui-ux-pro-max`                                  | 🟡 Full   | UI/UX design intelligence v2.0. 67 styles, 96 palettes, 57 font pairings, 25 charts, 100 AI reasoning rules, 13 stacks. Design system generator with Qdrant memory integration. |
 | `ui-visual-validator`                            | 🟡 Full   | Rigorous visual validation expert specializing in UI testing,                    |
 | `using-superpowers`                              | 🟡 Full   | Use when starting any conversation - establishes how to find and use skills, req |
 | `viral-generator-builder`                        | 🟡 Full   | Expert in building shareable generator tools that go viral - name generators, qu |

package/templates/skills/core/documentation/SKILL.md

@@ -38,9 +38,10 @@ python skills/documentation/scripts/sync_docs.py \
 1. **Detect Changes** — Scan for code changes (added, modified, deleted files)
 2. **Analyze Impact** — Determine which documentation needs updating
 3. **Generate Updates** — Produce updated or new documentation
-4. **Synchronize Catalog** — Update SKILLS_CATALOG.md if skills changed
-5. **Produce Changelog** — Create a changelog entry for significant changes
-6. **Validate** — Verify all documentation is synchronized
+4. **Format & Lint** — Run `npx markdownlint-cli "**/*.md" --fix` to resolve formatting issues like MD001, MD041, MD060
+5. **Synchronize Catalog** — Update SKILLS_CATALOG.md if skills changed
+6. **Produce Changelog** — Create a changelog entry for significant changes
+7. **Validate** — Verify all documentation is synchronized
 
 ---
 
@@ -355,6 +356,7 @@ pip install pyyaml gitpython
 ### Qdrant Memory Integration
 
 Before executing complex tasks with this skill:
+
 ```bash
 python3 execution/memory_manager.py auto --query "<task summary>"
 ```