deepen-plan
Enhance a plan with parallel research agents validating each section against best practices
What this skill does
# Deepen Plan Command You take an existing plan (from `/architect`, `/scope`, or any structured plan document) and enhance it by spawning parallel research agents — one per major section — to validate each section against external best practices, framework documentation, and known pitfalls. **Arguments:** $ARGUMENTS ## Phase 1: Load the Plan ```bash PLAN_SOURCE="$ARGUMENTS" if [ -z "$PLAN_SOURCE" ]; then echo "Usage: /deepen-plan [file path]" echo "" echo " /deepen-plan docs/architecture.md" echo " /deepen-plan /tmp/plan.md" echo "" echo "Provide the path to a plan file to deepen." exit 1 fi ``` Read the plan file using the Read tool. If the file doesn't exist, ask the user to provide the path. ## Phase 2: Extract Sections Parse the plan into its major sections (## headings). Each section becomes an independent research task. For each section, identify: - **Section title** — The heading text - **Key topics** — Technologies, patterns, or decisions mentioned - **Risk level** — High (new tech, complex integration), Medium (standard patterns), Low (straightforward) Present the section breakdown: ```markdown ### Plan Sections Identified | # | Section | Key Topics | Risk | Research Focus | |---|---------|------------|------|----------------| | 1 | [title] | [topics] | [H/M/L] | [what to research] | | 2 | [title] | [topics] | [H/M/L] | [what to research] | ``` ## Phase 3: Parallel Research Dispatch For each section, spawn a research agent in parallel using the Task tool. All agents run simultaneously. **For High-risk sections**, use the best-practices-researcher: - subagent_type: "psd-coding-system:research:best-practices-researcher" - description: "Research for section: [title]" - prompt: "Research best practices, known pitfalls, and recommended patterns for: [section content summary]. Focus on: [key topics]. Return structured findings with specific recommendations, anti-patterns to avoid, and relevant documentation links." **For Medium-risk sections**, use the framework-docs-researcher: - subagent_type: "psd-coding-system:research:framework-docs-researcher" - description: "Validate frameworks in: [title]" - prompt: "Validate that frameworks, APIs, and libraries mentioned in this plan section are current and not deprecated: [section content summary]. Check official docs, changelogs, and migration guides. Flag any deprecated or EOL technologies." **For Low-risk sections**, use the learnings-researcher: - subagent_type: "psd-coding-system:research:learnings-researcher" - description: "Check learnings for: [title]" - prompt: "Search project learnings and knowledge base for any relevant past experiences related to: [section content summary]. Return any applicable learnings, patterns, or warnings from previous work." **Launch ALL section research agents in parallel** using multiple Task tool calls in a single message. ## Phase 4: Synthesize Findings After all agents return, compile their findings into a structured deepening report: ```markdown ## Plan Deepening Report ### Section 1: [title] **Research Agent:** [which agent was used] **Findings:** - [Key finding 1] - [Key finding 2] **Recommendations:** - [Specific recommendation] **Warnings:** - [Any anti-patterns or pitfalls flagged] --- ### Section 2: [title] ... ``` ## Phase 5: Present Enhanced Plan Present the original plan with research annotations inline. For each section, add a collapsible "Research Notes" block: ```markdown ## [Original Section Title] [Original section content unchanged] <details> <summary>Research Notes (from /deepen-plan)</summary> - [Finding 1] - [Finding 2] - **Warning:** [Any flagged issues] - **Recommendation:** [Suggested improvement] </details> ``` ## Phase 6: Summary ```markdown ### Deepening Complete | Metric | Value | |--------|-------| | Sections analyzed | X | | High-risk sections | X | | Warnings found | X | | Recommendations | X | **Next steps:** - Review the annotated plan above - Address any warnings before implementation - Run `/work` or `/lfg` to implement the deepened plan ```
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.