kimsanguine

kimsanguine/hplan

Command

Use when hplan을 새로 설치했거나 gate 동작이 예상과 다를 때 설치 상태를 확인해야 합니다. Verifies Claude Code hook registration, gateguard execution, checkpoint state, exclusions registry integrity, and git pre-commit hook.

kimsanguine/hplan

Command

Manage the append-only Do-Not-Build exclusions registry — add an exclusion with reopentrigger, or check whether a new idea collides with prior exclusions. Use when adding a Do-Not-Build entry to permanent memory, or when checking whether a new idea collides with prior exclusions.

kimsanguine/hplan

Command

Export the Build Gate brief to your downstream coding ecosystem — Spec-Kit, Kiro, GStack, Claude Code, or all four at once. Use when Build Gate is approved and you need to export the brief to a downstream coding ecosystem (Spec-Kit, Kiro, GStack, Claude Code).

kimsanguine/hplan

Command

Full production operations workflow — KPI dashboard, reliability scan, cost review, improvement planning, knowledge extraction, decision pattern matching, and TK-to-instruction conversion. Use when an agent is live and needs a weekly/monthly operational review, or when running any individual operations step. Use…

kimsanguine/hplan

Command

Full technical architecture and strategy planning — orchestration pattern, 3-tier design, memory architecture, model routing, architecture doc, and strategy review. Use when a product has passed the evidence gate and needs a complete technical and strategic blueprint before build.

kimsanguine/hplan

Command

Verify task/feature completion against CONDITIONALGO conditions in STATE.md. Syncs condition status (❌→✅) before any 'done' declaration. Use when marking a task complete, closing a sprint, or claiming a condition is met. Use --spec to run full Spec Compliance Review instead of STATE.md condition check.

kimsanguine/hplan

Command

Run the full hplan build gate in one command — exclusions collision check + evidence rubric + COGS analysis — and return a single GO / HOLD / INVESTIGATE verdict with 3-line reason. Use when a PM or founder has a new product idea and wants the fastest WHETHER answer before committing any further time.

kimsanguine/hplan

Skill Claude CodeCodex

A guided process for deciding whether a product or feature idea is worth building, then shaping it into an initial design. It produces a draft design document, a list of assumptions, and early problem statements for later product planning.

kimsanguine/hplan

Skill Claude CodeCodex

Executable COGS gate for AI products. Runs a deterministic Python sampler (lognormal token-cost distribution) to compute p50/p90 per-paid-user monthly COGS, gross margin scenarios, and free-user abuse blend. Returns GREEN / CONDITIONALGO / RED before any paid AI product is greenlit. Use when promising a paid AI…

kimsanguine/hplan

Skill Claude CodeCodex

Append-only build/interview/pivot/hold/CONDITIONALGO decision log with 3-6 month self-eval audit. Records every gate decision with score + reasons; later backfilled with outcome (shipped, killed, alivenorevenue, pivoted, externalsuccess) to compute hitrate, falseholds, and missedbuilds. The only PM gate skill that…

kimsanguine/hplan

Skill Claude CodeCodex

Score a product idea against the 100-point evidence rubric before any PRD work. Eight axes: ICP specificity, recent painful event, current workaround, repetition, economic pain, switching trigger, MVP narrowness, and acquisition path to first 5 users. Returns build/interview/pivot/hold decision plus the specific axes…

kimsanguine/hplan

Skill Claude CodeCodex

Append-only Do-Not-Build registry. Each exclusion carries a reason, an owning competitor, and a reopentrigger that says what evidence would unblock it. Future runs auto-check new ideas against the registry with Korean-aware char-bigram fuzzy match. Use when an idea overlaps with an established competitor (any…

kimsanguine/hplan

Skill Claude CodeCodex

Export an approved Build Gate brief to a downstream coding ecosystem, or emit a read-only AI PM Handoff Profile v0 for growth planning. Use only after the Build Gate checkpoint and referenced decision agree.

kimsanguine/hplan

Skill Claude CodeCodex

Import AI synthesis output (BuildBetter MCP, Perspective AI, and similar AI synthesis tools) into hplan, then force a human to tag each quote with strength (strong/medium/weak) and Push/Pull/Habit/Anxiety/workaround/trigger axes. AI extracts quotes; humans assign evidence strength. Audits the SKILL.md rule: 5…

kimsanguine/hplan

Skill Claude CodeCodex

Generate a Teresa Torres-style Opportunity Solution Tree as docs/OPPORTUNITYTREE.md with auto-rendered Mermaid diagram. Forces the discipline: opportunities are unmet user needs (not solutions), each solution links to exactly one experiment with a decision rule, and opportunities backed by fewer than 3 strong-Push…

kimsanguine/hplan

Plugin Claude Code

Operate and continuously improve AI agents — portfolio tiering, scorecards, weekly rollups, cross-team routing, KPI/North Star/OKR design (metrics-design), reliability measurement, cost monitoring, cohort analysis, incident response, stakeholder reporting (ops-review: exec-summary 임원 보고, weekly-update 팀 주간…

kimsanguine/hplan

Skill Claude CodeCodex

Respond to and learn from AI agent incidents — triage severity, coordinate response, contain blast radius, and write postmortems. Use when an agent produces harmful outputs, costs spike unexpectedly, accuracy drops suddenly, or users report critical failures.

kimsanguine/hplan

Skill Claude CodeCodex

Design the metrics hierarchy and OKRs for an AI agent — North Star, KPI derivation, and OKR setting. Supports --step north-star | kpi | okr | all (default).

kimsanguine/hplan

Skill Claude CodeCodex

A skill for weekly or monthly operational reviews of AI agents, covering token spending, weekly metrics, cost comparisons, anomalies, budgets, and stakeholder updates.

kimsanguine/hplan

Skill Claude CodeCodex

Interface with the PM-ENGINE-MEMORY file — the operator's accumulated PM tacit knowledge database. Enables agents to reference, search, and apply TK (Tacit Knowledge) entries, and supports TK extraction from experience (--mode extract), TK querying and referencing (--mode query), and TK-to-instruction conversion…

kimsanguine/hplan

Skill Claude CodeCodex

A skill for managing and comparing multiple deployed AI agents as a portfolio. It provides views of individual agent status, cross-agent costs, and overall operational health.

kimsanguine/hplan

Skill Claude CodeCodex

Systematically review and improve AI agent reliability — identify failure patterns, assess error handling, design safeguards, and set reliability targets. Use when agents are producing inconsistent results, after incidents, or when preparing for production deployment.