workflow-challenger
Critical review and gap analysis skill that can be invoked at any workflow stage. Use to challenge decisions, identify missing specifications, verify coherence, and surface unaddressed questions in CDC, findings, plans, or any deliverable. Acts as a devil's advocate by deeply analyzing codebase, project documentation ([DOC]-* folders), and context.
What this skill does
# Workflow Challenger Skill
## Purpose
Act as a critical reviewer and devil's advocate at any stage of the feature workflow. This skill performs deep analysis to:
- Challenge assumptions and decisions
- Identify gaps and missing specifications
- Surface unanswered questions
- Verify coherence between documents and codebase
- Ensure nothing has been overlooked
**Key principle:** Better to surface issues early than discover them during implementation or testing.
## When to Use This Skill
Use this skill:
- After completing CDC.md to verify specification completeness
- After research to challenge technical decisions
- After planning to verify plan coherence with requirements
- Before implementation to catch missing details
- After test failures to understand root causes
- Anytime something feels incomplete or uncertain
- When user wants a second opinion on approach
## IMPORTANT: User Interaction
**Use the `request_user_input` tool when clarification is needed on identified gaps.**
After analysis, use request_user_input to:
- Confirm critical issues need resolution
- Get user input on ambiguous findings
- Prioritize which gaps to address first
```
request_user_input:
questions:
- question: "I found that the CDC doesn't address error handling. How should we proceed?"
header: "Gap Found"
options:
- label: "Add to CDC now"
description: "Update the specification before continuing"
- label: "Note for later"
description: "Document as known gap, address during implementation"
- label: "Not needed"
description: "This case won't occur in practice"
multiSelect: false
```
This ensures:
- User is aware of identified issues
- Clear decision-making on how to proceed
- Gaps are explicitly acknowledged or resolved
## Analysis Sources
The challenger analyzes multiple sources to build comprehensive context:
### 1. Project Documentation
```
Look for documentation folders at project root:
- [DOC]-{ProjectName}/
- docs/
- documentation/
- .doc/
- wiki/
```
Read all relevant documentation to understand:
- Project architecture
- Business rules
- Existing conventions
- Historical decisions
### 2. Codebase Analysis
```
Analyze existing code to understand:
- Current implementation patterns
- Data models and schemas
- API contracts
- Service dependencies
- Configuration patterns
```
### 3. Workflow Deliverables
```
Review current workflow documents:
- CDC.md (specification)
- findings.md (research)
- Plan.md (implementation plan)
- test-plan.md (test strategy)
```
### 4. Obsidian/Knowledge Base
```
If Obsidian MCP is available:
- Search for related notes
- Find linked concepts
- Discover historical context
```
## Challenge Workflow
### Phase 1: Context Gathering
1. **Identify current stage** - What deliverable is being challenged?
2. **Read the deliverable** - Understand what has been documented
3. **Explore project docs** - Find [DOC]-* folders and read relevant files
4. **Analyze codebase** - Understand existing patterns and constraints
5. **Build mental model** - Synthesize all information
```
Example context gathering:
1. Read CDC.md for "email notifications" feature
2. Found [DOC]-Backend/ with architecture.md
3. Found existing NotificationService in codebase
4. Found EmailTemplate component already exists
5. Mental model: Feature partially exists, CDC doesn't mention this
```
### Phase 2: Gap Analysis
Systematically check for gaps in each category:
**2.1 Missing Requirements**
- Are all user stories covered?
- Are edge cases addressed?
- Are error scenarios defined?
- Are non-functional requirements specified?
**2.2 Unclear Specifications**
- Are there ambiguous terms?
- Are there assumptions not validated?
- Are there "TBD" or placeholder sections?
- Are acceptance criteria measurable?
**2.3 Incoherence Detection**
- Does the document contradict itself?
- Does it contradict project documentation?
- Does it contradict existing codebase?
- Does it contradict other workflow documents?
**2.4 Missing Context**
- Is existing functionality acknowledged?
- Are dependencies identified?
- Are integration points clear?
- Is the scope realistic?
See `references/gap-analysis-guide.md` for detailed checklist.
### Phase 3: Challenge Formulation
For each identified issue, formulate a clear challenge:
**Structure:**
```
## Challenge: [Title]
**Type:** Gap / Ambiguity / Incoherence / Missing Context
**Severity:** Critical / Major / Minor
**Location:** [Document section or code location]
**Observation:**
[What was found or missing]
**Question:**
[Specific question to resolve the issue]
**Recommendation:**
[Suggested resolution or investigation]
```
**Example:**
```
## Challenge: Existing Email System Not Addressed
**Type:** Missing Context
**Severity:** Critical
**Location:** CDC.md Section 4 (Functional Requirements)
**Observation:**
The CDC specifies creating an EmailService, but the codebase already
has `src/services/NotificationService.ts` with email capabilities.
The CDC doesn't mention whether to extend, replace, or ignore it.
**Question:**
Should we extend the existing NotificationService or create a
separate EmailService? What happens to existing email functionality?
**Recommendation:**
Update CDC to explicitly address the existing NotificationService.
Consider extending it rather than creating parallel functionality.
```
### Phase 4: Coherence Verification
Cross-check between documents and reality:
**CDC vs Codebase:**
- Are referenced components real?
- Do proposed integrations make sense?
- Are technology choices consistent?
**CDC vs Project Docs:**
- Does it follow documented architecture?
- Does it respect documented constraints?
- Is terminology consistent?
**Findings vs CDC:**
- Does research address all CDC requirements?
- Are POC results aligned with specifications?
- Are chosen patterns appropriate?
**Plan vs Findings:**
- Does plan implement research recommendations?
- Are dependencies correctly sequenced?
- Is scope consistent?
### Phase 5: Report Generation
Compile findings into a structured report:
```markdown
# Challenge Report: [Deliverable Name]
**Date:** [Date]
**Stage:** [Specification / Research / Planning / etc.]
**Challenger:** Codex
## Summary
[Brief overview of findings]
- **Critical Issues:** X
- **Major Issues:** X
- **Minor Issues:** X
## Critical Issues
[Must be resolved before proceeding]
## Major Issues
[Should be resolved, but not blocking]
## Minor Issues
[Nice to address, low impact]
## Coherence Check
| Source A | Source B | Status | Notes |
|----------|----------|--------|-------|
| CDC | Codebase | ⚠️ | [Issue] |
| CDC | Project Docs | ✅ | Aligned |
## Questions for User
1. [Question 1]
2. [Question 2]
## Recommendations
1. [Recommendation 1]
2. [Recommendation 2]
## Conclusion
[Overall assessment and suggested next steps]
```
## Challenge by Stage
### Challenging CDC.md (Specification)
Focus on:
- Requirement completeness
- Scope clarity
- Acceptance criteria measurability
- Alignment with project architecture
- Existing functionality conflicts
Key questions:
- "Is this already partially implemented?"
- "Does this conflict with existing features?"
- "Are all personas addressed?"
- "What happens in failure scenarios?"
### Challenging findings.md (Research)
Focus on:
- Technical decision rationale
- Alternative evaluation completeness
- POC validity
- Integration feasibility
- Risk identification
Key questions:
- "Why this approach over alternatives?"
- "Was the POC representative?"
- "Are performance implications understood?"
- "What could go wrong?"
### Challenging Plan.md (Implementation)
Focus on:
- Step granularity appropriateness
- Dependency correctness
- Parallelization opportunities
- Missing steps
- Validation criteria clarity
Key questions:
- "Is this step too vague to implement?"
- "What if step X fails?"
- "Can these steps run in parallel?"
- "How do we know this step is complete?"Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.