원클릭으로
conflict-detection
Conflict identification and resolution patterns for requirements, decisions, and plans
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Conflict identification and resolution patterns for requirements, decisions, and plans
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Interactively elicit, capture, and maintain software/system requirements as a living, traceable repository. Use whenever the user wants to gather, write, refine, or organize requirements — including producing or updating an SRS (software/system requirements specification), writing ADRs / architecture decision records, building a requirements traceability graph (DAG), or keeping a decision ledger. Trigger proactively when the working folder already holds requirements artifacts (a `requirements/` folder of YAML, `decisions/` ADRs, an `srs.md`, or `ledger.md`), or when the user shares documents that are clearly specs, RFCs, or feature briefs and wants them structured. Also use for phrases like "let's spec this out", "interview me about what we're building", "capture these requirements", "write a decision record", or "turn these notes into a spec". Not for project management, code review, application code, dependency manifests like requirements.txt, or hardware "system requirements" (RAM/CPU).
Use this skill whenever the user wants to create a bash script that drives an autonomous coding loop — scripts that run Claude Code on a schedule (cron, GitHub Actions, systemd timer) or on-demand to make repository improvements, execute plans, triage issues, or otherwise do agentic work with minimal human intervention. Triggers include phrases like "scout script", "autonomous script", "agent harness", "script that runs on a schedule", "script that implements a plan", ".scripts/*.sh", or any request for a bash script whose body is "run Claude Code with a prompt and commit the results". Always use this skill before writing such a script — it encodes the interview flow, the adversarial-reviewer pattern, and the locking/ledger conventions.
Task structure and atomic commit patterns for granular, verifiable work units
Context window management techniques for maintaining efficiency and preventing context bloat
Exploration map management for tracking discussed areas and uncharted territory during DISCUSS phase
Phase coordination, agent handoffs, and workflow state machine management
| name | conflict-detection |
| description | Conflict identification and resolution patterns for requirements, decisions, and plans |
| triggers | ["conflict","contradiction","inconsistency","incompatible"] |
This skill provides patterns for detecting and resolving conflicts between requirements, decisions, and plans throughout the workflow.
Two requirements that cannot both be satisfied.
Detection Point: DISCUSS phase Example: "User wants real-time updates AND offline mode"
Indicators:
A new decision contradicts an earlier decision.
Detection Point: DISCUSS phase Example: "Earlier said 'no database', now requesting PostgreSQL"
Indicators:
Proposed work conflicts with pending tasks.
Detection Point: PLAN phase Example: "This change conflicts with TASK-003 in current ITEM-XXX.md"
Indicators:
Requested features exceed achievable scope.
Detection Point: DISCUSS phase Example: "Features exceed what's achievable in stated timeline"
Indicators:
Chosen technology cannot support a requirement.
Detection Point: PLAN phase Example: "Chosen tech doesn't support requested feature"
Indicators:
┌─────────────────────────────────────────────────────────────────┐
│ CONFLICT DETECTION FLOW │
├─────────────────────────────────────────────────────────────────┤
│ │
│ 1. EXTRACT assertions from new input │
│ ├─ Requirements stated │
│ ├─ Decisions made │
│ ├─ Constraints imposed │
│ └─ Priorities expressed │
│ │
│ 2. SCAN for contradictions │
│ ├─ Compare against ITEM-XXX.md decisions │
│ ├─ Compare against ITEM-XXX.md requirements │
│ ├─ Compare against existing tasks in ITEM-XXX.md │
│ └─ Check implicit assumptions │
│ │
│ 3. IF CONFLICT DETECTED: │
│ ├─ STOP workflow immediately │
│ ├─ Document conflict in ITEM-XXX.md │
│ ├─ Present conflict clearly to user │
│ └─ Wait for resolution before continuing │
│ │
│ 4. IF NO CONFLICT: │
│ └─ Continue workflow normally │
│ │
└─────────────────────────────────────────────────────────────────┘
For each new assertion, check against:
| Compare Against | Looking For |
|---|---|
| Previous decisions | Contradictions |
| Stated requirements | Incompatibilities |
| Technical choices | Capability gaps |
| Implicit assumptions | Hidden conflicts |
| Pending tasks | Execution conflicts |
## Conflicts
### CONFLICT-001: [Descriptive Title]
**Status**: ACTIVE | RESOLVED | DEFERRED
**Detected**: [TIMESTAMP]
**Type**: Requirement | Decision | Plan | Technical | Scope
**What conflicts:**
- A: [First item with reference]
- B: [Second item with reference]
**Why they conflict:**
[Clear explanation of why both cannot coexist]
**Resolution options:**
1. [Option 1 - description and implications]
2. [Option 2 - description and implications]
3. [Option 3 - description and implications]
**User choice**: [PENDING | Option N]
**Rationale**: [Why user chose this option]
**Resolved**: [TIMESTAMP]
**Actions taken**: [What changed as a result]
The system MUST stop and present conflict when detecting:
Trigger: "You said X earlier, now saying not-X"
Example: "Earlier you said no database needed, but now you're
asking for PostgreSQL integration"
Trigger: "Feature A requires condition C, Feature B requires not-C"
Example: "Real-time sync requires constant internet, but you also
want full offline functionality"
Trigger: "Both items need exclusive access to same resource"
Example: "Two tasks both want to restructure the database schema
in incompatible ways"
Trigger: "Features exceed reasonable scope for constraints"
Example: "You're asking for 15 major features with a 2-week deadline"
Trigger: "Technologies don't work together"
Example: "You want to use Library A and Library B, but they have
conflicting peer dependencies"
Choose one item over the other.
Resolution: Prioritize A over B
- A remains as requirement
- B is removed or deferred
- Rationale recorded
Adjust one item to remove conflict.
Resolution: Modify B to accommodate A
- A remains unchanged
- B is adjusted: [specific changes]
- Both now compatible
Adjust both items to find middle ground.
Resolution: Adjust both for compromise
- A adjusted: [changes]
- B adjusted: [changes]
- Trade-off documented
Keep both, document the trade-off.
Resolution: Accept both with trade-off
- Both remain
- Trade-off: [what is sacrificed]
- Risk documented
Postpone resolution.
Resolution: Deferred
- Marked as DEFERRED
- Reason: [why can't resolve now]
- Blocker for: [what can't proceed]
- Revisit: [when/condition]
Before creating tasks, verify:
## Cross-Plan Verification Checklist
**Against ITEM-XXX.md requirements:**
- [ ] All requirements have at least one task
- [ ] No tasks contradict requirements
- [ ] Priority order respected
- [ ] No requirements orphaned
**Against ITEM-XXX.md decisions:**
- [ ] Tasks align with recorded decisions
- [ ] No tasks contradict decisions
- [ ] Deferred items not accidentally included
**Against existing tasks in ITEM-XXX.md:**
- [ ] New tasks don't conflict with pending tasks
- [ ] File modifications don't overlap dangerously
- [ ] Dependency order preserved
- [ ] No circular dependencies created
**Against FLOW.md backlog:**
- [ ] Tasks fit within item scope
- [ ] No scope creep detected
- [ ] Dependencies on other items documented
**Conflicts found**: [List or "None"]
See resolution.md for detailed resolution strategies.