Skill Claude CodeCodex
Run a full product build loop in one orchestrated session — discover → research → design → PRD → task decomposition → team-based implementation. Use when the user invokes /build, when an idea needs end-to-end execution from problem to shipped change, or when a feature crosses discover/architect/deliver boundaries that…
Skill Claude CodeCodex
A task runner that sends each task to a fresh coding agent, then checks it against the specification and a quality gate before continuing.
Skill Claude CodeCodex
Write a complete unified PRD covering user/JTBD/decisions/scope/agent-spec/metrics/hypotheses in 15 sections. Single source of truth for both customer-facing products and the LLM agents inside them. Replaces the older 7-section agent-only template. prd is the canonical owner of §6 Now/Next/Later. --mode design-shotgun…
Skill Claude CodeCodex
A checklist generator and adversarial testing workflow based on a product requirements document. It creates QA test cases, where QA means checking that software works as intended, and can record multiple testing rounds.
Skill Claude CodeCodex
2-mode UI respect skill — brief (generate RESPECT.md design brief before coding) and checkpoint (final pre-ship gate enforcing user-respect via α/β/γ gate matrix). Use --mode brief when starting any UI screen; use --mode checkpoint before shipping. RESPECT.md absence blocks craft-lint (exit 2).
Skill Claude CodeCodex
A sprint planning and tracking workflow for turning a product requirements document (PRD) into a work breakdown structure (WBS), then recording progress and comparing results with the plan.
Skill Claude CodeCodex
A translator between GitHub Issues, Linear, or Jira and hplan, a planning and execution system. It moves task descriptions, estimates, and status information between those systems without creating the estimates or progress data itself.
Skill Claude CodeCodex
Unified UI validation skill — hierarchy (Playwright DOM saliency + WCAG AA), motion (CSS transition vs RESPECT.md drift), drift (pHash N-screen consistency), mobile (375/768/1440px breakpoint). Each check is independently runnable and independently failable. --check 인자 미명시 시 에러 출력 후 사용 가능한 check 목록 안내 — auto-run 절대…
Plugin Claude Code
Discover which AI agent to build — map automation outcomes to solvable opportunities, validate assumptions, and decide build vs buy. Use when exploring agent ideas, analyzing automation opportunities, running build-or-buy analysis, or estimating agent development costs.
Skill Claude CodeCodex
Identify and prioritize the riskiest assumptions in an agent idea across four axes: Value, Feasibility, Reliability, and Ethics. Use after defining an agent opportunity and before starting implementation. Prevents building agents that work technically but fail operationally or cause unintended harm. Includes…
Skill Claude CodeCodex
Simulate and forecast agent operating costs before building. Model token consumption, API call frequency, and monthly burn rate across different models and usage patterns. Use when evaluating agent feasibility, setting cost KPIs, or comparing build vs buy economics. Prevents the 'it's just API calls' cost surprise.
Skill Claude CodeCodex
A Korean-language workflow for finding people to interview, drafting outreach, and preparing interview questions.
Skill Claude CodeCodex
Design where and how humans should intervene in agent workflows. Define automation boundaries, escalation triggers, and approval gates. Use when building agents that make consequential decisions, handle sensitive data, or operate in domains where errors have high impact. Prevents the 'fully autonomous' default trap.
Skill Claude CodeCodex
Analyze where AI agents can add value and which tasks to automate — systematically map repetitive workflows, manual processes, and operational bottlenecks to identify the best agent opportunities. Build an Agent Opportunity Tree from desired outcomes to solvable problems, agent solution candidates, and validation…
Skill Claude CodeCodex
A skill that updates an iOS app's release version and commits the change on the appropriate branch. The release version is the number users see for an app release.
Plugin Claude Code
Evidence + COGS + Decision gate that runs BEFORE you commit to building. Mandatory competitor and interview evidence, executable COGS sentinel (p50/p90 margin with abuse blend), append-only Do-Not-Build exclusions registry, self-eval decision log, and multi-target handoff to Spec-Kit / Kiro / GStack / Claude Code. Use.
Agent
Use to make the final hplan Build Gate decision. Returns build / interview / pivot / hold / CONDITIONALGO and writes to harness/decisions.jsonl. Requires evidence-reviewer and product-reviewer and economics-reviewer to have signed off.
Agent
Use to challenge an hplan Build Gate's economic readiness. Accepts or rejects COGS sentinel result, pricing, usage caps, free-user abuse, and payment boundary. Cannot make Evidence or Product Gate decisions.
Agent
Use to challenge an hplan Evidence Gate package. Accepts or rejects competitor research, ICP/JTBD, interview kit, and 5/3 strong-Push pattern. Cannot make Product or Build Gate decisions.
Agent
Use to challenge an hplan Product Gate package. Accepts or rejects Problem Brief, Opportunity Solution Tree, User Journey Map, Sitemap, and Design Guidelines. Cannot make Evidence or Build Gate decisions.
Command
A command that runs the AI product cost check using provider prices, expected token use, call volume, and price per customer. It reports typical and high-use margins, the effect of free-user misuse, and a green, conditional-go, or red decision.
Command
A scoring checklist for judging how much customer evidence supports a product idea. It scores eight areas, including the target user, recent problem, current workaround, frequency, financial impact, buying trigger, narrow first version, and way to reach the first five users.
Command
Full build pipeline — evidence gate, product gate, COGS gate, PRD writing, OKR design, sprint planning, design system setup, spec compliance review (--step spec-review), quality gate (--step quality-gate), progress tracking, and scope guard. Use when committing to building a product or agent, running individual gate…
Command
End-to-end discovery workflow — opportunity mapping, assumption analysis, cost simulation, build/buy decision, and assumption validation. Use when exploring a new product or agent idea, stress-testing an agent concept, or running a full discovery pass before any gate decision.