prd-workflow
This skill should be used when the user asks to "plan a feature", "create PRD", "interview me about requirements", "define stories", "write a spec", "break down feature into tasks", "create implementation plan", "help me scope this feature", "what questions should I answer", or discusses feature planning. Covers the PRD interview process, spec structure, story atomization, and 4-phase workflow from idea to Dex tasks.
What this skill does
# PRD Workflow - Feature Planning **Current branch:** !`git branch --show-current 2>/dev/null || echo "not in git repo"` **Existing plans:** !`ls plans/ 2>/dev/null | head -5 || echo "none"` The PRD (Product Requirements Document) workflow transforms ideas into atomic, implementable stories through structured interview, research, and specification. ## When to Use PRD Workflow - Starting a new feature from scratch - Turning a vague idea into concrete tasks - Need thorough requirements gathering - Want AI-assisted research and review ## The 4-Phase Approach | Phase | Name | Purpose | |-------|------|---------| | 1 | Input Classification | Identify feature name and type | | 2 | Interview + Exploration | Gather requirements, then run research/expert agents | | 3 | Spec Write | Create specification with Implementation Stories section | | 4 | Dex Handoff | Parse stories into Dex tasks | **Key Change:** Research and expert agents run after interview completes (blocking). Findings are reviewed before spec writing. ## Starting the Workflow ```bash /prd "Add user authentication" # From idea /prd path/to/existing/code # From codebase /prd # Interactive discovery ``` ## Phase 2: Interview + Exploration **Commitment:** "I will ask 8-10+ questions covering: core problem, success criteria, MVP scope, technical constraints, UX flows, edge cases, error states, and tradeoffs." ### Interview (8-10+ questions) Cover these areas: - Core problem, success criteria, MVP scope - Technical systems, data models, existing patterns - UX/UI flows, error states, edge cases - Tradeoffs, compromises, priorities Focus on **non-obvious** details that will bite during implementation. ### After Interview, Run Agents (blocking) Spawn ALL agents in parallel (user waits ~2-3 min): **Research Agents:** - `prd-codebase-researcher` - Existing patterns, files to modify - `git-history-analyzer` - Prior attempts, why patterns evolved - `prd-external-researcher` - Best practices, code examples **Expert Agents:** - `architecture-strategist` - System design concerns - `security-sentinel` - Auth, data exposure risks - `spec-flow-analyzer` - User journeys, missing flows - `pattern-recognition-specialist` - Codebase consistency ### Review Findings Summarize key findings. Ask clarifying questions if gaps revealed. ## Phase 3: Spec Structure Write to `plans/<feature>/spec.md` with this structure: ```markdown # <Feature> Specification ## Overview ## Problem Statement ## Success Criteria ## User Stories ## Detailed Requirements ## Technical Design ## Edge Cases & Error Handling ## Open Questions ## Out of Scope ## Implementation Stories ### Story 1: <Title> **Category:** functional|ui|integration|edge-case|performance **Skills:** <skill-name>, <skill-name> **Blocked by:** none **Acceptance Criteria:** - [ ] Criterion 1 - [ ] Criterion 2 ## Research Findings ## Expert Review Findings ``` ## Story Atomization Rules **Commitment:** "Each story will have ≤7 acceptance criteria, touch ≤3 files, be independently testable, and have no 'and' in title." Each story must be completable in ONE task (~15-30 min): - **Max 7 acceptance criteria** - If more, split the story - **Max 3 files touched** - If more, consider splitting - **No "and" in title** - "User can X and Y" = two stories - **Independently testable** - Can verify in isolation - **Cleanly revertible** - Can undo without cascade ## Phase 4: Dex Handoff Use `dex plan` to automatically create tasks from the spec: ```bash dex plan plans/<feature>/spec.md ``` This automatically: - Creates parent task from spec title - Analyzes Implementation Stories section - Generates subtasks with proper hierarchy - Sets blocked-by relationships from "Blocked by:" lines Verify tasks created: ```bash dex status dex list ``` ## After PRD Completion Use Dex for execution: ```bash dex status # Dashboard view dex list --ready # See unblocked tasks dex start <id> # Claim a task /complete <id> # Run reviewers and complete ``` ## Command Reference ```bash /prd "feature description" # Start from idea /prd path/to/code # Start from codebase /cancel-prd # Cancel in-progress PRD ``` ## Related Commands - `/complete` - Complete task with reviewer workflow - `dex list` - View pending tasks - `dex sync` - Sync with GitHub issues
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.