maestria-co/task-plan-phase-architecture
skills/task-plan-phase-architecture/SKILL.md
Load when the task's primary concern is structural decisions — new modules, shared library changes, new external integrations, schema changes, or cross-service boundaries.
development
Updated Apr 26, 2026
$ install --global
skillsauthnpx skillsauth add maestria-co/ai-playbook task-plan-phase-architectureInstall 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 26, 2026, 6:39 AM53.7s1 file scanned
SKILL.md
- name:
- task-plan-phase-architecture
- description:
- Load when the task's primary concern is structural decisions — new modules, shared library changes, new external integrations, schema changes, or cross-service boundaries.
- user-invocable:
- false
Phase: Architecture
Load this skill when the task's dominant focus addresses structural evaluation or decision-making. For implementation tasks encountering structural queries mid-execution, use task-plan-phase-implementation — it supplies guidance on @architect engagement for structural concerns emerging during coding. This skill addresses tasks where architectural determinations constitute primary effort, not intermediate checkpoints.
Architect Consultation Matrix
| Trigger | Required? | |---------|-------------| | Fresh module or bounded context | Required | | Shared/core library alterations | Required | | External API or service connection | Required | | Database schema modifications | Required | | Authentication or authorization alterations | Required | | Novel design pattern introduction | Required | | Substantial cross-module refactoring | Required | | Dependency addition with extensive transitive footprint | Required | | Moderate isolated-module refactoring | Discretionary | | Pattern replication from extant examples | Discretionary | | Isolated component alteration, presentation-exclusive change | Omit | | Straightforward remediation following documented patterns | Omit |
@architect Delegation Structure
All architect dispatches require these elements:
Proposed alteration: [Plan's advocated methodology]
Current architectural context:
- [Relevant fact from .context/architecture/]
- [Applicable pattern from .context/standards/]
Targeted queries:
- [Module structure compatibility query]
- [Coupling or dependency footprint query]
- [Testability or risk query]
Constraints:
- [Non-negotiable requirements from user or .context/decisions.md]
Applying Architect Output
Following architect evaluation:
- Archive determination in
plan.md## Decisionssection:- Verdict (Approve / Approve with alterations / Reject)
- Pre-implementation alterations demanded
- Identified risks with mitigation strategies
- On conditional approval: revise plan's implementation steps before @coder dispatch.
- On rejection: return to @planner with architect rationale for methodology revision.
- On approval: advance to implementation with architectural guidance archived in
plan.md.
Skill Interdependencies
design-first: The @architect agent internally engagesdesign-first. Direct engagement unnecessary.task-plan: Archive all architectural determinations inplan.mdviatask-plan.task-plan-phase-implementation: Load post-approval when primary effort transitions to code generation.
Excluded scope: investigation, @coder orchestration, tests, task closure.
Related Skills
maestria-co/writing-tests
development
VerifiedTrustedCommunity
Writes and runs a test suite for a piece of code, covering happy path, edge cases, error cases, and security cases. Use when: implementation is complete and needs test coverage, a bug needs a reproduction test and fix validation, or code needs coverage before a refactor. Do not use when: the code under test is not yet implemented, or the spec is still unclear.
SKILL.mdUpdated Apr 26, 2026
maestria-co/writing-skills
testing
VerifiedTrustedCommunity
Use when creating a new skill, editing an existing skill, or helping a user author a skill for this system. Covers structure, discoverability, quality, and discipline hardening.
SKILL.mdUpdated Apr 26, 2026
maestria-co/verification-checklist
development
VerifiedTrustedCommunity
Evidence-based verification process to run before marking any task complete. Use this skill every time you're about to report that work is done — for features, bug fixes, refactoring, or any code change. This catches the most common failure mode: declaring "done" without proof. If you're finishing up and about to tell the user the task is complete, run this checklist first.
SKILL.mdUpdated Apr 26, 2026
maestria-co/using-skills
development
VerifiedTrustedCommunity
Teaches agents how to discover, select, and invoke skills from the skill library. Use this skill whenever you're uncertain which skill applies to a task, when composing multiple skills for complex work, or when you need to understand what skills are available. This is your go-to when facing an ambiguous task and need to figure out the right approach before diving into implementation.
SKILL.mdUpdated Apr 26, 2026