execute
Execute an implementation plan step by step
What this skill does
# Execute Plan You are helping a developer implement a plan from `docs/plans/`. Follow the plan systematically, implementing each step while keeping the user informed and involved. ## Core Principles - **Follow the plan**: The plan was agreed upon - stick to it - **Autonomous execution**: Complete the entire plan without stopping unless there's a problem - **Stop on roadblocks**: If you hit ANY issue, stop immediately and ask for input - **Track progress**: Update todos and check off acceptance criteria - **Flag deviations**: If something doesn't match the plan, stop and discuss - **Quality matters**: Code review before completion --- ## Phase 1: Load Plan **Goal**: Read and understand the plan Initial request: $ARGUMENTS **Actions**: 1. If no plan specified, list available plans in `docs/plans/` 2. Read the specified plan file 3. Create todo list from implementation steps 4. Summarize the plan to user: - What we're building - Number of steps - Requirements being implemented 5. **Ask user to confirm ready to start** --- ## Phase 2: Pre-Implementation Check **Goal**: Verify we're ready to implement **Actions**: 1. Check if any open questions remain in the plan - If yes, resolve them with user first 2. Verify the codebase matches plan assumptions: - Do the referenced files exist? - Are patterns still as expected? 3. If anything changed since planning, discuss with user: - Update plan if needed - Or proceed with adjustments 4. **Confirm ready to implement** --- ## Phase 3: Implementation **Goal**: Execute ALL steps from the plan autonomously **IMPORTANT**: Execute the entire plan without stopping. Only stop if you hit a roadblock. **For each step**: 1. Read all relevant files first 2. Implement the changes: - Follow codebase patterns noted in plan - Match existing code style - Add appropriate comments 3. Mark step complete in todo list 4. **Continue immediately to next step** (do not wait for user) **STOP IMMEDIATELY if**: - File doesn't exist or is different than expected - Pattern/code has changed since planning - Implementation conflicts with existing code - Step is unclear or ambiguous - You're unsure about the right approach - Tests fail unexpectedly - Any error or unexpected behavior **When stopping**: ``` "I hit a roadblock at Step [X]: [Clear description of the problem] The plan expected [X] but I found [Y]. Options: A) [Proposed solution] B) [Alternative approach] C) [Skip and continue] What would you like to do?" ``` **If NO roadblocks**: Complete all steps, then proceed to Phase 4. --- ## Phase 4: Quality Review **Goal**: Ensure code is simple, DRY, elegant, and functionally correct **Actions**: 1. Launch 3 `code-reviewer` agents in parallel with different focuses: - **Simplicity/DRY/Elegance**: Code quality and maintainability - **Bugs/Correctness**: Functional correctness and logic errors - **Conventions/Abstractions**: Project standards and patterns 2. Consolidate findings and identify highest severity issues 3. **Present findings to user**: ``` "Code Review Results: High Priority Issues: 1. [Issue] (file:line) - [why it matters] Medium Priority: 1. [Issue] - [suggestion] What would you like to do? A) Fix high priority issues now B) Fix all issues C) Proceed without fixing" ``` 4. Address issues based on user decision --- ## Phase 5: Verification **Goal**: Verify implementation meets requirements **Actions**: 1. Go through acceptance criteria from the plan 2. For each criterion: - Verify it's implemented - Mark as complete or flag issues 3. Run any relevant tests 4. Present verification summary: ``` "Acceptance Criteria: ✓ [Criterion 1] ✓ [Criterion 2] ✗ [Criterion 3] - [issue]" ``` 5. **Address any failed criteria with user** --- ## Phase 6: Completion **Goal**: Wrap up and document **Actions**: 1. Mark all todos complete 2. Update the plan file with completion status: - Add "Completed: [date]" to header - Check off all acceptance criteria - Note any deviations or decisions made 3. Summarize to user: - What was built - Files created/modified - Any follow-up items 4. Ask if user wants to commit the changes --- ## Dialogue Patterns ### Starting ``` "I'll execute the plan for [name]. Summary: - [X] steps to implement - Requirements: [REQ-IDs] - Key files: [list] I'll implement all steps and only stop if I hit a roadblock. Ready to start?" ``` ### On Roadblock (STOP) ``` "I hit a roadblock at Step [X]: [Clear description of problem] The plan expected [X] but I found [Y]. Options: A) [Proposed solution] B) [Alternative approach] C) [Skip and continue] What would you like to do?" ``` ### After Roadblock Resolved ``` "Got it. Continuing with the plan..." [Resume autonomous execution] ``` ### Code Review Results ``` "Code Review Results: High Priority Issues: 1. Missing error handling in [file:line] 2. Potential memory leak in [file:line] Medium Priority: 1. Could simplify [logic] in [file] 2. Consider extracting [component] All tests pass. Code follows project conventions. What would you like to do? A) Fix high priority issues now B) Fix all issues C) Proceed without fixing" ``` ### Completing (all steps done) ``` "Implementation complete! Steps completed: [X/X] Created: - [new files] Modified: - [changed files] Acceptance Criteria: [X/Y] passing Code Review: [X] issues fixed Want me to commit these changes?" ``` ## Red Flags - Stop and Discuss - File doesn't exist that plan references - Pattern changed since planning - Step seems larger than expected - Acceptance criterion can't be verified - Implementation conflicts with existing code - User seems unsure about a change - Code reviewer finds critical issues ## Handling Deviations When something doesn't match the plan: 1. Stop immediately 2. Explain what's different 3. Propose options 4. Document the decision 5. Update plan file if significant
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.