gate-evaluation
Validate phase gate criteria with multi-agent review and generate pass/fail reports
What this skill does
<!-- AIWG-SKILL-CALLOUT -->
> **Skill access pattern (post-kernel-pivot, 2026.5+)**
>
> Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via:
>
> ```bash
> aiwg discover "<capability>"
> aiwg show skill <name>
> ```
>
> Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
# gate-evaluation
Validate phase gate criteria with multi-agent review and generate pass/fail reports.
## Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "LOM" / "LO check" → Inception exit gate (Lifecycle Objective Milestone)
- "LA" / "ABM" → Elaboration exit gate (Architecture Baseline Milestone)
- "IOC" → Construction exit gate (Initial Operational Capability)
- "PRM" → Transition exit gate (Product Release Milestone)
- "can we ship" → gate readiness shorthand
- "exit criteria for [phase]" → phase-specific gate check
## Purpose
This skill validates that all exit criteria for a phase are met before transitioning to the next phase. It orchestrates multiple validators to ensure comprehensive assessment.
## Behavior
When triggered, this skill:
1. **Identifies target gate**:
- Parse phase name or milestone
- Load gate criteria for that phase
- Map criteria to validator agents
2. **Inventories artifacts**:
- Check required artifacts exist
- Verify artifact status (baselined vs draft)
- Check version requirements
3. **Dispatches validators**:
- Launch parallel validators via `parallel-dispatch`
- Each validator checks their domain criteria
- Collect pass/fail per criterion
4. **Aggregates results**:
- Calculate gate score
- Identify blocking issues
- Generate recommendations
5. **Produces gate report**:
- Structured report with all criteria
- Clear pass/fail status
- Remediation guidance for failures
## Gate Definitions
### LOM - Lifecycle Objective Milestone (Inception Exit)
```yaml
gate: LOM
phase: inception
description: Validate problem, vision, and business case
criteria:
vision:
description: Vision document exists and is approved
artifacts: [".aiwg/requirements/vision.md"]
status: approved
validator: product-strategist
business_case:
description: Business case with ROI justification
artifacts: [".aiwg/management/business-case.md"]
status: approved
validator: executive-orchestrator
stakeholders:
description: Stakeholder agreement documented
artifacts: [".aiwg/management/stakeholder-agreement.md"]
status: approved
validator: project-manager
scope:
description: Initial scope and boundaries defined
artifacts: [".aiwg/requirements/scope.md"]
status: draft # can be draft at this stage
validator: requirements-analyst
risks:
description: Initial risk list with top 10 risks
artifacts: [".aiwg/risks/risk-register.md"]
min_risks: 10
validator: project-manager
architecture_sketch:
description: High-level architecture concept
artifacts: [".aiwg/architecture/architecture-sketch.md"]
status: draft
validator: architecture-designer
security_screening:
description: Initial security classification
artifacts: [".aiwg/security/data-classification.md"]
validator: security-architect
```
### ABM - Architecture Baseline Milestone (Elaboration Exit)
```yaml
gate: ABM
phase: elaboration
description: Architecture stable, major risks retired
criteria:
sad:
description: Software Architecture Document baselined
artifacts: [".aiwg/architecture/sad.md"]
status: baselined
validator: architecture-designer
adrs:
description: Key Architecture Decision Records
artifacts: [".aiwg/architecture/adr-*.md"]
min_count: 3
validator: architecture-designer
requirements_baseline:
description: Requirements documented and traced
artifacts:
- ".aiwg/requirements/use-cases/*.md"
- ".aiwg/requirements/supplementary-spec.md"
validator: requirements-analyst
risk_retirement:
description: Top risks retired or mitigated
artifacts: [".aiwg/risks/risk-register.md"]
check: risks_retired_percentage >= 60
validator: project-manager
test_strategy:
description: Test strategy defined
artifacts: [".aiwg/testing/test-strategy.md"]
status: approved
validator: test-architect
security_architecture:
description: Security architecture reviewed
artifacts: [".aiwg/security/threat-model.md"]
status: approved
validator: security-architect
```
### IOC - Initial Operational Capability (Construction Exit)
```yaml
gate: IOC
phase: construction
description: System functional, ready for deployment
criteria:
features_complete:
description: All planned features implemented
check: features_completion >= 100
validator: product-manager
tests_passing:
description: All automated tests pass
check: test_pass_rate >= 95
validator: test-architect
coverage:
description: Adequate test coverage
check: test_coverage >= 80
validator: test-architect
security_scan:
description: Security scan clean (no critical/high)
check: security_critical == 0 AND security_high == 0
validator: security-auditor
performance:
description: Performance meets NFRs
artifacts: [".aiwg/testing/performance-results.md"]
validator: performance-engineer
defects_triaged:
description: All defects triaged, no P0/P1 open
check: critical_defects == 0
validator: test-architect
deployment_plan:
description: Deployment plan approved
artifacts: [".aiwg/deployment/deployment-plan.md"]
status: approved
validator: deployment-manager
```
### PRM - Product Release Milestone (Transition Exit)
```yaml
gate: PRM
phase: transition
description: Product ready for production
criteria:
deployment_proven:
description: Deployment validated in staging
artifacts: [".aiwg/deployment/staging-validation.md"]
validator: devops-engineer
user_acceptance:
description: UAT passed
artifacts: [".aiwg/testing/uat-results.md"]
check: uat_pass_rate >= 100
validator: test-architect
support_ready:
description: Support team trained, runbooks ready
artifacts:
- ".aiwg/deployment/support-runbook.md"
- ".aiwg/deployment/training-completion.md"
validator: support-lead
rollback_plan:
description: Rollback procedure documented and tested
artifacts: [".aiwg/deployment/rollback-plan.md"]
validator: devops-engineer
monitoring:
description: Monitoring and alerting configured
artifacts: [".aiwg/deployment/monitoring-config.md"]
validator: reliability-engineer
compliance:
description: All compliance requirements met
validator: legal-liaison
```
## Validation Process
```
┌─────────────────────────────────────────────────────────┐
│ 1. LOAD GATE CRITERIA │
│ • Identify target gate (LOM, ABM, IOC, PRM) │
│ • Load criteria definitions │
│ • Map validators │
└─────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ 2. ARTIFACT INVENTORY │
│ • Check each required artifact exists │
│ • Verify artifact status (draft/approved/baselined) │
│ • Record missing or invalid artifacts │
└─────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ 3. PARALLRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.