Overview
- Skill Key
- contrario/agent-architect
- Author
- contrario
- Source Repo
- openclaw/skills
- Version
- 1.0.4
- Source Path
- skills/contrario/agent-architect
- Latest Commit SHA
- b20ea22bf0d0109578c8d064e569ad0dcdbaa35b
Transforms your OpenClaw agent from a reactive question-answerer into a proactive autonomous executor. ARCHITECT takes any high-level goal, decomposes it into a dependency-aware task graph, executes each step with validation, self-corrects on failure, and delivers results — all without hand-holding. The missing execution layer for personal AI agents. Zero dependencies. Zero config. Works with any model. Pairs with apex-agent and agent-memoria for the complete autonomous agent stack.
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 architect 技能。 若已安装,则直接安装 architect 技能。
# ARCHITECT — Autonomous Goal Decomposition & Execution Engine You now operate as an autonomous executor. You confirm before irreversible actions but do not wait for step-by-step instructions. You receive a goal, build a plan, execute it, validate each step, self-correct when things break, and deliver a complete result. This is the difference between a tool and an agent. --- ## THE ARCHITECT PRINCIPLE Every agent has three layers: ``` LAYER 1 — COGNITION (how to think) → apex-agent LAYER 2 — MEMORY (what to remember) → agent-memoria LAYER 3 — EXECUTION (how to act) → architect ← YOU ARE HERE ``` Without all three, an agent is incomplete. ARCHITECT is the execution layer. It transforms goals into reality. --- ## CORE EXECUTION LOOP When you receive a high-level goal, run this loop autonomously: ``` ┌─────────────────────────────────────────────────────┐ │ ARCHITECT LOOP │ │ │ │ 1. PARSE → Extract the real goal │ │ 2. DECOMPOSE → Build the task dependency graph │ │ 3. SEQUENCE → Order tasks by dependency │ │ 4. EXECUTE → Run each task with full focus │ │ 5. VALIDATE → Check output meets criteria │ │ 6. ADAPT → Self-correct on failure │ │ 7. SYNTHESIZE → Combine outputs into final result │ │ 8. REFLECT → Log what worked and what didn't │ └─────────────────────────────────────────────────────┘ ``` Move between planning and analysis steps — the MISSION BRIEF is your checkpoint. Once the user approves the brief (after user types YES to confirm), proceed through research, planning, and content-generation steps autonomously. Always pause and ask before any irreversible or external action (see AUTONOMOUS DECISION FRAMEWORK below). If you hit a blocker you cannot resolve, report it clearly and offer alternatives. --- ## STEP 1 — PARSE: Extract the Real Goal The stated goal is r...
# ARCHITECT ⚙
**Your agent answers questions.**
**ARCHITECT makes it pursue goals.**
```bash
clawhub install architect
```
---
## The gap no one talks about
Every AI agent framework focuses on *thinking* and *remembering*.
Nobody solves *executing*.
You give your agent a goal. It asks you 12 follow-up questions.
You answer them. It gives you a plan. You have to execute the plan yourself.
That's not an agent. That's a very expensive to-do list generator.
ARCHITECT fixes this.
---
## What changes
**Without ARCHITECT:**
```
You: "Build me a competitive analysis for my SaaS"
Agent: "Sure! What competitors? What aspects? What format?
What length? What's your target audience? What's your..."
You: [gives up, does it manually]
```
**With ARCHITECT:**
```
You: "Build me a competitive analysis for my SaaS"
⚙ ARCHITECT — MISSION BRIEF
Goal: Competitive analysis for your SaaS
Success: Actionable positioning insights
Estimated: 5 tasks · MED complexity
Proceeding with execution.
[T01 · RESEARCH] ✓ Done — 4 competitors identified and profiled
[T02 · FEATURES] ✓ Done — feature matrix built across all competitors
[T03 · PRICING] ✓ Done — pricing tiers mapped and compared
[T04 · GAPS] ✓ Done — 3 clear positioning opportunities identified
[T05 · STRATEGY] ✓ Done — recommended positioning + go-to-market angle
⚙ MISSION COMPLETE — 5/5 tasks
[Full competitive analysis delivered]
```
No follow-up questions. Just results.
---
## The ARCHITECT Loop
```
1. PARSE → Extract the real goal (not just what you said)
2. DECOMPOSE → Build a dependency-aware task graph
3. SEQUENCE → Order tasks correctly, parallelize where possible
4. EXECUTE → Run each task with full focus and depth
5. VALIDATE → Check every output meets criteria
6. ADAPT → Self-correct on failure (up to 3 attempts)
7. SYNTHESIZE → Combine everything into the final result
8. REFLECT → Log insights for future executions
```
---
## 5 execution modes (auto-detected)...
openstockdata
OpenClaw Skill for stock data analysis
capt-marbles
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.
capgoblin
Access unsecured credit lines for AI agents on the Arc Network using the Credex Protocol. Use for borrowing USDC against reputation, repaying debt to grow credit limits, providing liquidity as an LP, or managing cross-chain USDC via Circle Bridge. Triggers on "borrow from credex", "repay debt", "deposit to pool", "check credit status", "provide liquidity", or any credit/lending task on Arc.
capt-marbles
Control PhantomBuster automation agents via API. List agents, launch automations, get output/results, check status, and abort running agents. Use when the user needs to run LinkedIn scraping, Twitter automation, lead generation phantoms, or any PhantomBuster workflow.
camelsprout
DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".
camohiddendj
DuckDuckGo HTML search scraper CLI with JSON, CSV, OpenSearch, markdown, and compact outputs.