pivanov/architect-workflow
skills/architect-workflow/SKILL.md
Deterministic AI engineering workflow with multi-agent teams. Triggers: architect mode, consistency sweep, pipeline audit, team workflow
$ install --global
skillsauthnpx skillsauth add pivanov/ai-skills architect-workflowInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:34 PM0.5s1 file scanned
SKILL.md
- name:
- architect-workflow
- description:
- Deterministic AI engineering workflow with multi-agent teams. Triggers: architect mode, consistency sweep, pipeline audit, team workflow
Architect Workflow
Professional team-based workflows for AI software engineering. Includes deterministic planning frameworks, consistency verification, and pipeline auditing.
What's Included
1. Architect Mode (Command + Team)
A 6-phase framework for rigorous software engineering:
- Phase 1-2: Deconstruction & Research (no code)
- Phase 3-4: Planning & Approval gates
- Phase 5: Delegated implementation with enforced review loops
- Phase 6: Integration & completion report
Use when: Complex features, architectural changes, anything >3 files
Trigger: /architect-workflow [goal]
2. Consistency Sweep Team
4 specialized agents verify docs, config, and architecture stay in sync:
- Docs Verifier: Compare documentation against actual code
- Dashboard Verifier: Match UI components to backend config
- Config Verifier: Validate defaults, constants, schemas
- Architecture Verifier: Check structural docs match reality
Use when: After major refactors, before releases, maintaining large codebases
3. Pipeline Health Team
4 auditors investigate content generation pipelines for bugs and performance:
- Draft Phase Auditor: End-to-end draft flow analysis
- Critique Phase Auditor: Critique/re-draft loop verification
- Validator Auditor: Check validators and enforcers
- Orchestration Auditor: State machine and phase coordination
Use when: Debugging complex pipelines, performance tuning, quality audits
Installation
This skill installs files to:
.claude/commands/architect-workflow.md- The /architect-workflow command.claude/teams/architect.md- Architect Mode team workflow.claude/teams/consistency-sweep.md- Consistency verification team.claude/teams/pipeline-perf.md- Pipeline health audit team
Quick Start
After installation:
# Launch architect mode
/architect-workflow "Add user authentication with JWT tokens"
# Or paste team definitions directly into Claude
# See team files in .claude/teams/
Architect Mode Process
- Deconstruct: Break down goals into objectives + research questions
- Research: Spawn parallel Explore agents for codebase investigation
- Plan: Write PLAN.md with tasks, sandboxes, success criteria
- Approve: User reviews plan before any code is written
- Execute: Implementers (Opus) + Reviewers (Sonnet) with accept/reject loops
- Integrate: Final checks, cleanup temp files, completion report
Key Feature: NO CODE until Phase 5 approval - prevents "ready, fire, aim" loops
Team Scaling
| Scope | Researchers | Implementers | Reviewers | |-------|-------------|--------------|-----------| | Small (≤3 files) | Skip (Quick Mode) | 1 Opus | 1 Sonnet | | Medium (4-10 files) | 2 Explore | 2-3 Opus | 1 Sonnet | | Large (10+ files) | 3 Explore | 3-4 Opus | 1-2 Sonnet |
When to Use What
Architect Mode: Building new features, refactoring, architectural changes Consistency Sweep: Post-refactor verification, release prep, doc maintenance Pipeline Health: Debugging multi-stage flows, performance investigation, quality audits
Philosophy
These workflows enforce discipline:
- Research before planning
- Planning before implementation
- Review before merging
- Measurable success criteria
- Explicit file sandboxes
- No code outside scope
Result: Higher quality, fewer bugs, better architecture decisions.
Related Skills
pivanov/split-tasks
data-ai
VerifiedTrustedCommunity
Split 3+ independent tasks across parallel agents. Triggers: run in parallel, split tasks, do these at once
2SKILL.mdUpdated Apr 24, 2026
pivanov/ask-json
testing
VerifiedTrustedCommunity
USE THIS SKILL whenever you need validated typed JSON from a sub-agent call -- classification, extraction, triage, routing decisions, scored ranking, enum labeling. Returns schema-validated data you can JSON.parse immediately, not prose to regex. Triggers: classify, classify into enum, extract structured, extract records, triage, rank with scores, typed output, schema-validated output, routing decision, parse to schema, return JSON, structured extraction, typed subagent result, avoid prose parsing
2SKILL.mdUpdated Apr 24, 2026
steipete/skill-creator
testing
VerifiedTrustedCommunity
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
356,423SKILL.mdUpdated Apr 13, 2026
steipete/healthcheck
testing
VerifiedTrustedCommunity
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
356,423SKILL.mdUpdated Apr 13, 2026