메뉴
Identify, categorize, and prioritize technical debt. Use for "tech debt audit", "what should we refactor", "code health", or refactoring priorities. Do NOT use for code review (code-review), architecture decisions (adr), or bug investigation (debug).
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
Instance bootstrap interview — detects existing instance state, guides repo creation (link-first), interviews business identity/services/cadence/targets, writes config/instance.json and target skeletons, then hands off to brand-creative setup. Use on first install, when the user says "set up my instance" or "bootstrap my agency workspace", or to re-check target bindings after config changes.
Create a competitive analysis brief for product strategy, feature prioritization, or sales enablement. Use when comparing competitors, mapping a feature area across rivals, or drafting battle cards. Do NOT use for user research synthesis (synthesize-research) or product strategy doc (product).
Run a weekly, monthly, or quarterly metrics review: scorecard, trends, bright spots, concerns, and recommended actions. Use when investigating a spike or drop, comparing performance against targets, or preparing a metrics readout. Do NOT use for stakeholder status updates (stakeholder-update) or product strategy (product).
Sparring partner for exploring a problem space, generating solutions, or stress-testing product thinking. Conversation, not a deliverable. Use when ideating, assumption-testing, or strategy exploration before a spec. Do NOT use for writing specs (write-spec) or product strategy doc (product).
Write a weekly or monthly status for leadership, announce a launch, escalate a risk, or tailor the same progress for exec, engineering, partner, customer, or board audiences. Use when drafting status updates or launch notes. Do NOT use for product strategy (product) or roadmap updates (roadmap).
Synthesize interview notes, survey data, or support tickets into themes, personas, opportunity areas, and roadmap recommendations. Use when turning raw research into structured findings. Do NOT use for competitive analysis (competitive-brief) or product strategy doc (product).
| name | tech-debt |
| description | Identify, categorize, and prioritize technical debt. Use for "tech debt audit", "what should we refactor", "code health", or refactoring priorities. Do NOT use for code review (code-review), architecture decisions (adr), or bug investigation (debug). |
| license | MIT |
| allowed-tools | Read Glob Grep |
| argument-hint | [scope or area] |
| metadata | {"author":"Carinya Parc","version":"0.1.0","owner":"web-development","review_cadence":"quarterly","work_shape":"review-and-gate","output_class":"decision-support"} |
Systematically identify, categorize, and prioritize technical debt. Pass scope (service, module, epic) after the skill name when provided; otherwise scan the area the user describes.
| Type | Examples | Risk |
|---|---|---|
| Code debt | Duplicated logic, poor abstractions, magic numbers | Bugs, slow development |
| Architecture debt | Monolith that should be split, wrong data store | Scaling limits |
| Test debt | Low coverage, flaky tests, missing integration tests | Regressions ship |
| Dependency debt | Outdated libraries, unmaintained dependencies | Security vulns |
| Documentation debt | Missing runbooks, outdated READMEs, tribal knowledge | Onboarding pain |
| Infrastructure debt | Manual deploys, no monitoring, no IaC | Incidents, slow recovery |
Score each item:
Priority = (Impact + Risk) × (6 − Effort)
Prioritized markdown list with: item, category, scores, justification, and suggested phase for remediation.
