by PromptSpace
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
Free
One-time purchase
## Verification - Passed: Unit tests, linting - Failed: 0 - Environment Delta: Node v18 -> v20 - Dependency Scan: Clean ## Summary Report - Commits pending push: [a1b2c3d, e4f5g6h] - Status: Verified & Awaiting human push. Agent did not push to remote.
by PromptSpace
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
Free
One-time purchase
⚡ Skill ready to install in Claude Code, Gemini CLI, or any MCP-compatible client. Read the install guides →
## Verification - Passed: Unit tests, linting - Failed: 0 - Environment Delta: Node v18 -> v20 - Dependency Scan: Clean ## Summary Report - Commits pending push: [a1b2c3d, e4f5g6h] - Status: Verified & Awaiting human push. Agent did not push to remote.
The Agentic Workflow is a language-agnostic, risk-aware protocol designed to prevent the four most common AI agent failures: silent assumptions, scope creep, untested deployments, and credential leakage. It transforms vague requests into evidence-based execution by enforcing a multi-stage engineering lifecycle similar to a senior dev's mental model.
Prompting an AI often results in "hallucinated" progress or unexpected side effects. This skill forces your agent to follow a structured discipline of research, planning, safety-gating, and verification. It is better than raw prompting because it includes built-in guardrails like cascading failure detection, secret scanning, and an absolute "never push" rule for production stability.
Instead of just code, you receive an audit-ready closure report including a Risk Class assessment, a Verification Matrix (Passed/Failed/Unstable), a Scope Check (Planned vs. Actual changes), and a Rollback Strategy. It ensures all work is staged, verified, and ready for human approval.
mkdir -p ~/.claude/skills/agentic-workflow && curl -s -X POST 'https://api.promptspace.in/api/skills/agentic-workflow/install' | python3 -c "import sys,json; sys.stdout.write(json.load(sys.stdin).get('installInstructions') or '')" > ~/.claude/skills/agentic-workflow/SKILL.mdFree skills install directly. Paid skills require purchase - use the download button above after buying.
Security Scanned
Passed automated security review
No special permissions declared or detected
OpenClaw, Cursor, Claude Code, Codex CLI
PromptSpace
We build AI agent skill packages for content creators. Specializing in Chinese social media automation.