flow-gate-check
Orchestrate SDLC phase gate validation with multi-agent review and comprehensive reporting
What this skill does
# SDLC Gate Check Orchestration
**You are the Core Orchestrator** for SDLC phase gate validation.
## Your Role
**You orchestrate multi-agent workflows. You do NOT execute bash scripts.**
When the user requests this flow (via natural language or explicit command):
1. **Interpret the request** and confirm understanding
2. **Read this template** as your orchestration guide
3. **Extract agent assignments** and workflow steps
4. **Launch agents via Task tool** in correct sequence
5. **Synthesize results** and finalize artifacts
6. **Report completion** with summary
## Natural Language Triggers
Users may say:
- "Can we transition to {phase}?"
- "Are we ready for {phase}?"
- "Validate gate criteria"
- "Check if we can proceed"
- "Gate validation for {phase}"
- "Check {phase} readiness"
- "Is the {milestone} complete?"
- "Run gate check for {phase}"
- "Validate our readiness to move forward"
You recognize these as requests for this orchestration flow.
## Parameter Handling
### Phase/Gate Identification
**Supported Gates**:
**Phase Milestones**:
- `inception` / `LOM` - Lifecycle Objective Milestone
- `elaboration` / `ABM` - Architecture Baseline Milestone
- `construction` / `IOC` - Initial Operational Capability
- `transition` / `PR` - Product Release
**Workflow Gates**:
- `discovery` - Discovery Track Definition of Ready
- `delivery` - Delivery Track Definition of Done
- `security` - Security validation
- `reliability` - Performance and SLO compliance
- `test-coverage` - Test coverage thresholds
- `documentation` - Documentation completeness
- `traceability` - Requirements → code → tests
- `12-factor` - 12-factor app methodology compliance (opt-in, cloud-native targets)
**Special Gates**:
- `all` - Run all applicable gates
- `pre-deploy` - Pre-deployment readiness
- `orr` - Operational Readiness Review
### --guidance Parameter
**Purpose**: User provides upfront direction to tailor validation priorities
**Examples**:
```
--guidance "Focus on security compliance, HIPAA critical"
--guidance "Time-constrained, prioritize minimum viable gates"
--guidance "Enterprise deployment, need full compliance validation"
```
**How to Apply**:
- Parse guidance for keywords: security, compliance, timeline, quality
- Adjust validation depth (comprehensive vs. essential)
- Influence agent assignments (add specialized validators)
- Modify reporting detail level
### --interactive Parameter
**Purpose**: You ask 3-5 strategic questions to understand context
**Questions to Ask** (if --interactive):
```
I'll ask strategic questions to tailor the gate validation:
Q1: What's your primary concern for this gate check?
(e.g., compliance readiness, technical quality, team preparedness)
Q2: Are there any known issues or gaps you're concerned about?
(Help me focus validation on problem areas)
Q3: What's your timeline for passing this gate?
(Influences whether to report quick-fixes vs. comprehensive remediation)
Q4: Who needs to sign off on this gate?
(Helps identify which specialized reviewers to involve)
Q5: What happens if the gate doesn't pass?
(Helps determine how strict validation should be)
```
## Multi-Agent Orchestration Workflow
### Step 1: Determine Gate Context
**Purpose**: Identify which gate to validate and current project state
**Your Actions**:
1. **Parse Gate Parameter**:
```
Map user input to gate type:
- "inception" | "LOM" → Lifecycle Objective Milestone
- "elaboration" | "ABM" → Architecture Baseline Milestone
- "construction" | "IOC" → Initial Operational Capability
- "transition" | "PR" → Product Release
- Others → Workflow or special gates
```
2. **Scan Project State**:
```
Use Glob to check for phase indicators:
- .aiwg/intake/* → Likely in Inception
- .aiwg/architecture/software-architecture-doc.md → Likely post-Elaboration
- .aiwg/testing/test-results/* → Likely in Construction
- .aiwg/deployment/production-deploy.md → Likely in Transition
```
**Communicate Progress**:
```
✓ Gate identified: {gate-name}
⏳ Scanning project state...
✓ Current phase detected: {phase}
```
### Step 2: Phase Gate Validation (LOM/ABM/IOC/PR)
#### 2.1: Inception Gate (LOM) Validation
**When**: User requests "inception", "LOM", or system detects Inception phase
**Launch Validation Agents**:
```
# Primary Validator
Task(
subagent_type="project-manager",
description="Validate Lifecycle Objective Milestone criteria",
prompt="""
Read gate criteria from: $AIWG_ROOT/agentic/code/frameworks/sdlc-complete/flows/gate-criteria-by-phase.md
Check for required Inception artifacts:
- .aiwg/intake/project-intake.md (COMPLETE)
- .aiwg/requirements/vision-*.md (APPROVED)
- .aiwg/planning/business-case-*.md (APPROVED)
- .aiwg/risks/risk-list.md (BASELINED)
- .aiwg/security/data-classification.md (COMPLETE)
Validate LOM criteria:
- Vision document APPROVED (stakeholder signoff ≥75%)
- Business case APPROVED (funding secured)
- Risk list BASELINED (5-10 risks, top 3 have mitigation)
- Data classification COMPLETE
- Initial architecture documented
- Executive Sponsor approval obtained
Generate validation report:
- Status: PASS | FAIL | CONDITIONAL
- Missing artifacts list
- Failed criteria with reasons
- Signoff status
- Remediation actions
Save to: .aiwg/gates/lom-validation-report.md
"""
)
# Parallel Specialized Reviewers
Task(
subagent_type="business-analyst",
description="Validate business readiness for LOM",
prompt="""
Review business artifacts:
- Business case viability
- Stakeholder alignment
- Funding adequacy
- Vision clarity
Report business readiness: READY | GAPS | BLOCKED
Save to: .aiwg/gates/lom-business-review.md
"""
)
Task(
subagent_type="security-architect",
description="Validate security readiness for LOM",
prompt="""
Review security artifacts:
- Data classification completeness
- Initial threat assessment
- Compliance requirements identified
- Security risks documented
Report security readiness: READY | GAPS | BLOCKED
Save to: .aiwg/gates/lom-security-review.md
"""
)
```
#### 2.2: Elaboration Gate (ABM) Validation
**When**: User requests "elaboration", "ABM", or system detects Elaboration phase
**Launch Validation Agents**:
```
# Primary Validator
Task(
subagent_type="project-manager",
description="Validate Architecture Baseline Milestone criteria",
prompt="""
Read gate criteria from: $AIWG_ROOT/agentic/code/frameworks/sdlc-complete/flows/gate-criteria-by-phase.md
Check for required Elaboration artifacts:
- .aiwg/architecture/software-architecture-doc.md (BASELINED)
- .aiwg/architecture/adr/*.md (3-5 ADRs)
- .aiwg/requirements/supplemental-specification.md (COMPLETE)
- .aiwg/testing/master-test-plan.md (APPROVED)
- .aiwg/risks/risk-retirement-report.md
Check for Layer 3 behavioral specifications:
- .aiwg/requirements/realizations/DES-UCR-*.md (use case realizations)
- .aiwg/architecture/state-machines/DES-SM-*.md (state machine specs)
- .aiwg/architecture/decision-tables/DES-DT-*.md (decision tables)
- .aiwg/architecture/method-contracts/DES-MIC-*.md (method interface contracts)
- .aiwg/architecture/activity-diagrams/DES-ACT-*.md (activity diagrams)
Validate ABM criteria:
- Architecture BASELINED and peer-reviewed
- ADRs documented (3-5 major decisions)
- Risks ≥70% retired or mitigated
- Requirements baseline established
- Test strategy approved
- Development case tailored
- Behavioral spec coverage ≥80% of architecturally significant use cases
- Every behavioral spec has a completeness checklist satisfied
- Traceability: UC → behavioral spec IDs present in realizations
Generate validation report:
- List each use case and whether it has a behavioral spec (realization)
- RepoRelated 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.