agentsclimarketplace

Plan & spec

10,746 rows, by stacks then stars

2,010 of these skill files have been read, by 1,360 distinct authors, and what they tell an agent counted. What Plan & spec authors agree on, and what they forbid

  • Cvg plan review

    gomilesf/convergo/plugins/codex/skills/cvg-plan-review Skill

    7★ repo

    Review a plan against the actual codebase. Verify slices are sufficient, surfaces are complete, and invariants are correct.

  • Cvg plan

    gomilesf/convergo/plugins/codex/skills/cvg-plan Skill

    7★ repo

    Create a plan for the assigned issue. Reads issue scope and codebase, produces a plan document with slices and invariant matrix when the work is cross-cutting.

  • Cvg plan review feedback

    gomilesf/convergo/plugins/generic/skills/cvg-plan-review-feedback Skill

    7★ repo

    Handle plan-review blocker findings returned to the planner session. Validate feedback, revise plan-owned artifacts, or stop for missing decisions.

  • Cvg plan review

    gomilesf/convergo/plugins/generic/skills/cvg-plan-review Skill

    7★ repo

    Review a plan against the actual codebase. Verify slices are sufficient, surfaces are complete, and invariants are correct.

  • Cvg plan

    gomilesf/convergo/plugins/generic/skills/cvg-plan Skill

    7★ repo

    Create a plan for the assigned issue. Reads issue scope and codebase, produces a plan document with slices and invariant matrix when the work is cross-cutting.

  • Cvg hybrid plan loop

    gomilesf/convergo/skills-src/cvg-hybrid-plan-loop Skill

    7★ repo

    Orchestrate the plan loop with split engines - a high-taste Claude design model drafts and revises the plan while Codex CLI sessions gate it as fresh plan reviewers. Use when the user asks for a hybrid, split-model, or cross-model planning loop, such as fable planning with codex reviewing. Claude Code only.

  • Cvg plan loop

    gomilesf/convergo/skills-src/cvg-plan-loop Skill

    7★ repo

    Orchestrate a monitored planning loop where a planner drafts the plan and fresh plan reviewers gate the exit. Use when the user asks to create or revise a plan through supervised specialist sessions on Codex threads or Claude Code background agents.

  • Cvg plan review feedback

    gomilesf/convergo/skills-src/cvg-plan-review-feedback Skill

    7★ repo

    Handle plan-review blocker findings returned to the planner session. Validate feedback, revise plan-owned artifacts, or stop for missing decisions.

  • Cvg plan review

    gomilesf/convergo/skills-src/cvg-plan-review Skill

    7★ repo

    Review a plan against the actual codebase. Verify slices are sufficient, surfaces are complete, and invariants are correct.

  • Cvg plan

    gomilesf/convergo/skills-src/cvg-plan Skill

    7★ repo

    Create a plan for the assigned issue. Reads issue scope and codebase, produces a plan document with slices and invariant matrix when the work is cross-cutting.

  • Finish

    bricerising/enterprise-software-playbook/skills/finish Skill

    7★ repo

    Run a final "definition of done" check before shipping: verify correctness, tighten contracts/docs, and produce a change summary. Use at the end of non-trivial work to confirm nothing was missed before merge/release. NOT for writing tests (use testing); NOT for adversarial code review (use review); NOT for initial planning (use plan).

  • Forecast

    bricerising/enterprise-software-playbook/skills/forecast Skill

    7★ repo

    Predict likely next developments from internal development patterns (git history, archobs clusters) and external signals (intel feeds). Use when you need forward-looking intelligence — what's GOING to happen, not what already happened. NOT for gathering raw signals (use intel); NOT for static code-structure analysis (coupling, boundary health, risk scores — use archobs); NOT for implementation planning (use plan).

  • Plan

    bricerising/enterprise-software-playbook/skills/plan Skill

    7★ repo

    Break a request into a scoped implementation plan with ordered tasks, risk flags, and verification steps. Use before starting non-trivial, cross-cutting, or ambiguous work to align on approach and prevent rework. NOT for writing spec artifacts or contracts (use spec); NOT for auto-routing across multiple skills (use workflow).

  • Spec

    bricerising/enterprise-software-playbook/skills/spec Skill

    7★ repo

    Write and maintain spec-first artifacts (service specs, API contracts via OpenAPI/protobuf/WebSocket schemas, ADRs, task lists, quickstarts). Use when creating specs/*.md, apps/*/spec/ bundles, or contracts/ docs, especially before major behavior changes or multi-agent collaboration. NOT for implementation task breakdown without spec artifacts (use plan); NOT for choosing system or code patterns (use architecture or design).

  • Workflow

    bricerising/enterprise-software-playbook/skills/workflow Skill

    7★ repo

    Auto-select and orchestrate playbook skills end-to-end for feature, bug-fix, or refactor work. Use when the user gives a general request without naming a specific skill — workflow picks the right skills, sequences them, and keeps overhead proportional to the change size. NOT for creating a standalone task breakdown (use plan) or writing spec artifacts (use spec).

  • Fix from logs

    Agent-Engineer-Master/skill-engineer/engineering/fix-from-logs Skill

    7★ repo

    Diagnoses bugs from raw error logs, stack traces, or CI failure output — triages and clusters errors, localizes root cause (file → function → line), enters plan mode with a structured fix + test proposal for human approval, writes a typed pytest regression test using mocks first, then implements a targeted code fix and verifies the test turns green. Trigger when: user pastes logs and wants the underlying bug fixed with tests that prevent recurrence; user says "here are the logs, fix it"; CI output shows failures needing code changes and test coverage; stack traces are provided with a request to fix and test. Do NOT trigger for: general code review without logs, refactoring without a specific bug, performance work, test coverage requests with no associated failure.

  • Marketing plan

    Agent-Engineer-Master/skill-engineer/marketing/marketing-plan Skill

    7★ repo

    Develops a full go-to-market marketing plan for a new online business, product, or idea — covering beachhead market, ICP, competitive landscape, Dunford positioning with messaging, channel strategy with buyer journey mapping, budget allocation, pricing, content strategy with retention, 90-day launch timeline, PMF definition, first customer motion, and AARRR + GEV KPI framework with measurement setup. Produces a structured markdown plan saved locally. Activate when: "build a marketing plan", "create a GTM strategy", "how should I market my new product/brand/startup", "plan the launch for", "what channels should I use to launch", "write a marketing plan for". Do NOT activate for: auditing existing marketing performance, writing individual content pieces, running specific campaigns, or competitive analysis without a launch goal.

  • Morning brief

    Agent-Engineer-Master/skill-engineer/operations/morning-brief Skill

    7★ repo

    Generates a structured morning brief and writes it to the daily review file. Pulls from: current priorities (goals summary), active task board, latest competitor digest, and content pipeline status. Fires automatically on weekdays. Output is the morning intention section of your daily review file.

  • Stress test

    Agent-Engineer-Master/skill-engineer/operations/stress-test Skill

    7★ repo

    Three-phase strategic decision analysis combining verbalized sampling (Stanford arXiv 2510.01171), customizable analytical lenses, and a structured decision brief. Surfaces tail-distribution insights — the non-obvious, suppressed analyses that mode-collapsed prompting misses. Adapted from @alex_prompter's Model Council article (April 2026) for single-Claude use. Works on any high-stakes decision: founder pivots, DTC category selection, brand positioning, workstream prioritisation, pricing, hiring.

  • Assess strategic environment

    Agent-Engineer-Master/skill-engineer/strategy/industry-analysis/assess-strategic-environment Skill

    7★ repo

    Diagnoses competitive environment for an industry using BCG's Strategy Palette (Reeves) — Classical / Adaptive / Visionary / Shaping / Renewal — via the three-question discipline (predictability, malleability, harshness). Output: strategic-environment.md classifying the environment, evidencing the 3 dimensions with V/C/A/I tags, flagging ambidexterity, emitting a sub-skill routing matrix that weights Phase 1+2 sub-skills heavy/light/skip. Sub-skill of analyze-industry, invocable standalone. Runs FIRST in orchestrator chain — wrong diagnosis = wrong toolkit. Triggers on 'diagnose strategic environment for [industry]', 'strategy palette for [industry]', 'is [industry] classical or adaptive', 'classify the [industry] environment', 'Reeves environment for [industry]'. Do NOT activate for industry-attractiveness (use map-five-forces), market sizing (use size-market), single-company moat work (use assess-moat-sources), or DTC category go/no-go (use assess-category).

  • 80 20 feature prioritization

    HDeibler/universal-design-principles/plugins/cognition-and-learnability-principles/skills/80-20-feature-prioritization Skill

    no license7★ repo

    Use this skill when scoping a roadmap, prioritizing features, planning an MVP, or deciding what to ship and what to defer. Trigger when the user asks "what should we build next?", "is this feature worth it?", "should we ship feature X?", or when reviewing a feature backlog. Sub-aspect of `80-20-rule`; read that first.

  • Openapi to dart

    Poorgramer-Zack/dart-expert-skills/skills/openapi-to-dart Skill

    7★ repo

    Reads an OpenAPI 3.0 specification and manually implements a type-safe Dart API layer using Dio for HTTP, Freezed or Equatable for models, and json_serializable for serialisation. Use when given an OpenAPI/Swagger file (JSON or YAML) and asked to implement the API in Flutter/Dart, create Dart models from an API schema, build a Dio API client, implement endpoints from a spec, convert openapi to dart, or set up a data/network layer from an API contract. Handles $ref resolution, oneOf union types, enums, query params, request bodies, and DioException error mapping.

    The same file is in 1 other repository

  • Qa engineer

    grimoire-rs/grimoire/.claude/skills/qa-engineer Skill

    7★ repo

    Use when designing test suites, writing acceptance tests, validating an implementation against a spec, or planning test coverage before implementation. Trigger: /qa-engineer.

  • Swarm plan

    grimoire-rs/grimoire/.claude/skills/swarm-plan Skill

    7★ repo

    Use for feature planning, task decomposition, multi-perspective research, or ADR scaffolding. Tier (`low | auto | high | max`) scales research depth, architect model, and review breadth. Canonical research primitive for AI config / ADR work.

  • Llm wiki pm

    anh-chu/llm-wiki-pm/skills/llm-wiki-pm Skill

    7★ repo

    Persistent PM knowledge base, competitive intel, customer notes, strategy, roadmap, AI market. Markdown wiki with entities, concepts, comparisons. Ingest sources, query, update with diffs, lint. Fires on "remember that / note that / don't forget / what do we know about X / what am I missing / blind spots".

  • Llm wiki prd

    anh-chu/llm-wiki-pm/skills/llm-wiki-prd Skill

    7★ repo

    Generate PRDs, user stories, and release notes grounded in wiki knowledge. Reads entities, concepts, decisions, and customer pages as source material.

  • Content calendar planner

    WesleySmits/agent-skills/.agent/skills/content-calendar-planner Skill

    no license7★ repo

    Creates strategic content schedules with themes, dates, and publishing cadence. Use when the user asks about content calendars, publishing schedules, content planning, editorial calendars, or content strategy timelines.

  • Search modelica docs

    WolframResearch/system-modeler-ai-toolkit/search-modelica-docs Skill

    7★ repo

    Search the bundled Modelica and Wolfram System Modeler documentation for authoritative answers, then cite the source. Use this skill whenever the user asks a how-to, what-is, or why question about the Modelica language (syntax, semantics, equations, when/if, arrays, connectors, annotations, the language specification), about Wolfram System Modeler (the tool: building/simulating models, the GUI, tutorials, release/what's-new notes), OR about the Modelica Standard Library (which MSL component/block to use, its exact parameter names and defaults, example models). Triggers on phrases like 'how do I write a when statement', 'what does the Modelica spec say about ...', 'how do I simulate this in System Modeler', 'is this valid Modelica', 'which MSL block does ...', 'what are the parameters of Modelica.X.Y', 'find an example model that ...', 'look it up in the docs'. Also use it while WRITING a model that uses MSL components, to ground parameter names and wiring instead of recalling them. Prefer this over answering Modelica/System Modeler/MSL questions from memory.

  • Milestone issues

    deevus/tea-skills/skills/milestone-issues Skill

    7★ repo

    Manage issues within Gitea/Forgejo milestones — list, add, remove, progress tracking, burndown, bulk assign, and move between milestones.

  • Plan

    OdinMB/ops-workflow/skills/plan Skill

    6★ repo

    Create an ops work plan for a new task. Proposes steps and success criteria for user approval before execution.

  • Ozor url to video

    Mintii-Labs/ozor-skills/skills/ozor-url-to-video Skill

    6★ repo

    Turn any URL — landing page, blog post, product page, documentation page, changelog, public PDF, or web article — into a finished AI-generated video using the Ozor MCP. Use this skill whenever the user gives a link and wants a video from its content: 'make a video from this URL', 'video from my landing page', 'turn this blog post into a video', 'video from https://...', 'video from our homepage', 'generate a video from this product page', 'create a video from this article'. This skill runs analyze_document with the url parameter (no scraping needed on our side), presents the resulting plan to the user, then generates → exports → embeds. Do NOT use this skill for a short text brief (use ozor-generate) or for an attached local file (use ozor-document-video).

  • Dw requirement analysis

    pugyy/dw-harness/template/.claude/skills/dw-requirement-analysis Skill

    6★ repo

    数仓需求分析流程,适用于 PRD 解读、字段口径梳理、上游表结构探索和待确认问题清单输出。直接调用命令:/dw-requirement-analysis。

  • Eso crafting account strategy

    Neetx/eso-skills/skills/eso-crafting-account-strategy Skill

    no license6★ repo

    Plans ESO account-level crafting strategy. Use for writs, master writs, motifs, furnishing crafting, set stations, transmute, reconstruction, crafting roles, and account crafter responsibilities.

  • Eso crafting research planner

    Neetx/eso-skills/skills/eso-crafting-research-planner Skill

    no license6★ repo

    Creates and optimizes ESO RESEARCH.md trait research plans. Use for crafting trait order, research timers, scroll usage, item priority, crafter goals, future builds, and efficient research queues.

  • Eso routine planner

    Neetx/eso-skills/skills/eso-routine-planner Skill

    no license6★ repo

    Creates, updates, and optimizes ESO ROUTINE.md plans. Use for daily, weekly, event, cross-character, cross-farming, limited-time, casual, efficient, or extreme play routines.

  • Plan em

    ndisisnd/msg/.claude/skills/plan-em Skill

    6★ repo

    Engineering Manager skill. Reads an approved PRD, runs pre-flight checks against AHA.md, GLOSSARY.md and ARCHITECTURE.md, auto-runs plan-tune certification inline before each wave (product before the plan wave, eng before the build wave — no ask), identifies specialist agents to activate (roster approval — the single human gate), spins them up to write engineering sections directly into the PRD, then synthesises the full output. Runs in --team mode by default (an Opus orchestrator engineer decomposes each wave into file-disjoint, model-tiered packets fanned out to leaf eng subagents) or --solo (one leaf subagent per roster stack). Refuses without a referenced PRD .md path.

  • Plan pm

    ndisisnd/msg/.claude/skills/plan-pm Skill

    6★ repo

    Principal PM skill — the autonomous PRD writer. Consumes a graded, fleshed-out row from the INTAKE.md backlog (idea, goal, type, grade) and drafts the full PRD solo — edge cases, feature/acceptance table, user flows, error handling — saved to features/planned/prd-[n]-[feature-slug]/. The requirements interview lives in /intake now, not here. Pauses ONLY for batched open questions the draft couldn't resolve and for breaking/critical touches. Refuses requests that would skip the PRD stage entirely.

  • Plan tune

    ndisisnd/msg/.claude/skills/plan-tune Skill

    6★ repo

    Staff PM contract certifier. Reads an existing PRD and runs a fixed seven-check certification (G1) — each check tied to a named downstream consumer (regression authoring, pre-merge's PRD-consistency gate, the safety pauses, eng --build's row/ticket reads). Product tune (--product) runs checks 1/2/3/6; eng tune (--eng) runs 2/4/5/6/7. Auto-selects the tune type from PRD content (no ask), auto-fixes every Critical and Major with a compact terminal table, asks once about Minors, and pauses only for a product-decision finding. Each auto-fixed Critical/Major writes a category-tagged learning to devkit/AHA.md so the next plan-pm draft self-heals. Applies all fixes directly to the PRD file. No separate report file.

  • Planning

    konglong87/methodology-skills/skills/planning Skill

    6★ repo

    MUST use after prompt-enhancer. Create implementation plan with MECE decomposition, dependency analysis, risk assessment, and mandatory plan-review.

  • Iac plan

    thettwe/nyann/skills/iac-plan Skill

    6★ repo

    Preview an Infrastructure-as-Code change WITHOUT applying it. Runs `bin/iac-plan.sh`, which detects the repo's IaC tool (terraform, opentofu, aws-cdk, pulumi, helm, kubernetes, kustomize, ansible), shells out to the user's already-authenticated CLI, and renders a normalized add/change/destroy summary. READ-ONLY — it never mutates infrastructure. TRIGGER when the user says "terraform plan", "preview my infra change", "what will this deploy", "cdk diff", "pulumi preview", "show me the terraform diff", "dry-run the infra change", "what would terraform/tofu/cdk/pulumi do", "plan the infrastructure", "kubectl diff", "helm diff", "what does this deploy change", "/nyann:plan". DISAMBIGUATION — fire ONLY for IaC plan intent on a detected infra repo. Do NOT trigger on the bare word "plan": this is NOT project planning, NOT sprint/roadmap planning, NOT `sc:*` task planning, NOT Claude's ExitPlanMode / "make a plan" for code work. "plan a feature", "plan my week", "let's plan the refactor" → ignore. Require an infra signal (a tool name like terraform/tofu/cdk/pulumi/helm/kubectl, OR the word "infra"/"infrastructure"/"deploy", OR a detected `iac.tool` in the stack descriptor). With no infra signal, do NOT trigger. To apply the change after previewing, that's `/nyann:apply` (the iac-apply skill) — iac-plan never applies.

  • Api integrator

    vignesh2027/Claude-Agentic-Skills2.0-version/api-integrator Skill

    6★ repo

    Activates APIIntegrator for API design, integration, and automation workflows. Use when you need OpenAPI 3.0 specification design, OAuth 2.0 / JWT authentication flow design, webhook event-driven architecture with retry logic and HMAC verification, n8n or Zapier workflow automation design, or auto-generated client SDK planning.

  • Business intelligence pro

    vignesh2027/Claude-Agentic-Skills2.0-version/business-intelligence-pro Skill

    6★ repo

    Activates BusinessIntelligence-Pro for KPI design, dashboard strategy, and SQL optimization. Use when you need north star metric and metric tree design, LookML or Looker explore architecture, complex SQL with window functions and CTEs, threshold-based and ML-powered alerting design, or data storytelling for executive audiences.

  • Database genius

    vignesh2027/Claude-Agentic-Skills2.0-version/database-genius Skill

    6★ repo

    Activates DatabaseGenius for database design, optimization, and migration. Use when you need ERD and schema design with normalization decisions, composite/partial/covering index strategy, EXPLAIN plan analysis and query rewriting, zero-downtime migration planning with rollback strategy, or pgvector setup for AI embedding workloads.

  • Hr analytics

    vignesh2027/Claude-Agentic-Skills2.0-version/hr-analytics Skill

    6★ repo

    Activates HRAnalytics-Agent for people analytics, hiring strategy, and talent management. Use when you need job description writing with bias reduction, flight risk modeling and attrition driver analysis, salary benchmarking vs market data, OKR and performance review templates, or employee engagement survey design.

  • Partnership intelligence

    vignesh2027/Claude-Agentic-Skills2.0-version/partnership-intelligence Skill

    6★ repo

    Complete strategic partnerships intelligence — partnership strategy, BD deal design, integration partnerships, revenue sharing, OEM/white-label, distribution partnerships, and building a partner ecosystem that compounds

  • Product roadmap os

    vignesh2027/Claude-Agentic-Skills2.0-version/product-roadmap-os Skill

    6★ repo

    Complete product roadmap operating system — strategy translation, prioritization frameworks, stakeholder alignment, roadmap formats, quarterly planning, and saying no without losing trust

  • Product strategy

    vignesh2027/Claude-Agentic-Skills2.0-version/product-strategy Skill

    6★ repo

    Activates ProductStrategy-Agent for product management and growth strategy. Use when you need a full PRD written, features prioritized using RICE or MoSCoW, user research interview guides created, funnel or retention analysis, LTV/CAC modeling, or competitive feature comparison matrices.

  • Project command

    vignesh2027/Claude-Agentic-Skills2.0-version/project-command Skill

    6★ repo

    Activates ProjectCommand for project management, agile delivery, and execution tracking. Use when you need a Work Breakdown Structure (WBS) with milestone definition, RAID log creation (Risks/Assumptions/Issues/Dependencies), sprint planning and velocity tracking, RACI matrix and stakeholder communication plan, or weekly status report generation.

  • Sprint master

    vignesh2027/Claude-Agentic-Skills2.0-version/sprint-master Skill

    6★ repo

    Complete Agile/Scrum/Kanban intelligence — sprint planning, backlog grooming, velocity optimization, retrospective facilitation, estimation techniques, and scaling agile for growing teams

  • Startup advisor

    vignesh2027/Claude-Agentic-Skills2.0-version/startup-advisor Skill

    6★ repo

    Activates StartupAdvisor for early-stage company strategy and fundraising. Use when you need pitch deck review and feedback, unit economics analysis (LTV/CAC/payback), fundraising strategy (which round, how much, which investors), go-to-market planning, competitive moat analysis, or hiring plan and org design for early-stage teams.

  • Dbt incremental strategy audit

    yeaight7/agent-powerups/plugins/data-engineering/skills/dbt-incremental-strategy-audit Skill

    6★ repo

    Use when reviewing a new or changed dbt incremental model -- the strategy looks over-engineered, rebuild or delete behavior is unclear, or the model deviates from how the rest of the repo handles incrementals.

  • Dbt strategy

    yeaight7/agent-powerups/plugins/data-engineering/skills/dbt-strategy Skill

    6★ repo

    Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming conventions, no-alias SQL rule, surrogate-key and missing-record patterns, incremental strategies, deduplication, and common project macros. Use when building fact tables, dimension tables, staging models, writing SQL, or designing tests.

  • Strategic context compaction

    yeaight7/agent-powerups/plugins/dev-vitals/skills/strategic-context-compaction Skill

    6★ repo

    Use when deciding whether to compact agent context -- the window is filling up, you are about to switch from one phase to another (research, planning, implementation, debugging), a failed approach left dead-end reasoning, or a previous mid-task compaction lost critical state.

  • Autonomous delivery pipeline

    yeaight7/agent-powerups/plugins/software-engineering/skills/autonomous-delivery-pipeline Skill

    6★ repo

    Use when the user wants end-to-end autonomous execution from a brief idea to working, verified code -- multi-phase work spanning requirements, planning, implementation, QA, and validation. Not for brainstorming, single focused changes, or quick fixes.

  • Autonomous delivery pipeline

    yeaight7/agent-powerups/skills/autonomous-delivery-pipeline Skill

    6★ repo

    Use when the user wants end-to-end autonomous execution from a brief idea to working, verified code -- multi-phase work spanning requirements, planning, implementation, QA, and validation. Not for brainstorming, single focused changes, or quick fixes.

  • Dbt incremental strategy audit

    yeaight7/agent-powerups/skills/dbt-incremental-strategy-audit Skill

    6★ repo

    Use when reviewing a new or changed dbt incremental model -- the strategy looks over-engineered, rebuild or delete behavior is unclear, or the model deviates from how the rest of the repo handles incrementals.

  • Dbt strategy

    yeaight7/agent-powerups/skills/dbt-strategy Skill

    6★ repo

    Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming conventions, no-alias SQL rule, surrogate-key and missing-record patterns, incremental strategies, deduplication, and common project macros. Use when building fact tables, dimension tables, staging models, writing SQL, or designing tests.

  • Strategic context compaction

    yeaight7/agent-powerups/skills/strategic-context-compaction Skill

    6★ repo

    Use when deciding whether to compact agent context -- the window is filling up, you are about to switch from one phase to another (research, planning, implementation, debugging), a failed approach left dead-end reasoning, or a previous mid-task compaction lost critical state.

  • Ai native prd architect

    DYAI2025/Plumbline/config/claude/skills/ai-native-prd-architect Skill

    no license6★ repo

    Use when turning a feature idea into an implementation-ready PRD with traceable REQ IDs, acceptance criteria, NFRs, risks, data model, and task slices for /agileteam Phase 0.

  • Product management write spec

    DYAI2025/Plumbline/config/claude/skills/product-management-write-spec Skill

    no license6★ repo

    Use optionally before ai-native-prd-architect when a vague product idea needs a user-facing feature spec and scope framing.