implement
This skill should be used when the user asks to "implement an issue", "create a PR for issue", "implement issue
What this skill does
# GitHub Issue Implementer Implement a GitHub issue by reading the implementation plan from the issue (description, comments, and replies), writing the code, creating a pull request, and updating the issue status. ## Workflow Overview 1. Fetch issue details and implementation plan from GitHub 2. Create a feature branch 3. Implement the changes based on the plan 4. Create a pull request 5. Comment on the issue with PR link 6. Add label to indicate implementation is in progress ## Step 1: Fetch Issue Details Retrieve comprehensive issue information: ```bash gh issue view $ARGUMENTS --json number,title,body,comments,labels ``` Parse the response to extract: - Issue number and title - Implementation plan from the body - Additional requirements or clarifications from comments - Existing labels for context If the issue has comments, read all comments to find implementation plans or additional requirements: ```bash gh issue view $ARGUMENTS --comments ``` Look for implementation plan sections typically marked with headers like "Implementation Plan", "Approach", or "Steps". ## Step 2: Create Feature Branch Create and checkout a new branch for the implementation: ```bash git checkout -b issue-$ARGUMENTS ``` If the branch already exists, confirm with the user before proceeding. ## Step 3: Implement Changes Based on the implementation plan extracted from the issue: 1. **Analyze the plan**: Identify all files to create or modify 2. **Follow the steps**: Implement each step in the plan sequentially 3. **Write tests**: Include unit tests as specified in the plan 4. **Follow codebase patterns**: Match existing code style and conventions During implementation: - Read relevant existing files to understand patterns - Use Grep and Glob to find related code - Make incremental changes, verifying each step works If the plan is unclear or incomplete: - Ask the user for clarification before proceeding - Document assumptions made during implementation ## Step 4: Create Pull Request After implementation is complete, create a pull request: ```bash gh pr create --title "Implement #$ARGUMENTS: <issue-title>" --body "$(cat <<EOF ## Summary Implements #$ARGUMENTS <Brief description of changes> ## Changes Made - <List of key changes> ## Testing - <How the changes were tested> ## Related Issue Closes #$ARGUMENTS --- *PR generated with [Claude Code](https://claude.ai/code) - github-devflow:implement* EOF )" ``` Link the PR to the issue using "Closes #N" or "Fixes #N" syntax. ## Step 5: Comment on Issue Add a comment to the original issue linking to the PR: ```bash gh issue comment $ARGUMENTS --body "Implementation PR created: <pr-url> The implementation follows the plan outlined in this issue. Please review the PR for details." ``` ## Step 6: Add Label Add the `implementation-started` label to indicate work is in progress: ```bash gh issue edit $ARGUMENTS --add-label "implementation-started" ``` If the label doesn't exist, create it first: ```bash gh label create "implementation-started" --description "Implementation work has started" --color "FFA500" ``` ## Error Handling ### Authentication Issues If `gh` CLI is not authenticated: ``` Error: gh CLI requires authentication. Run 'gh auth login' first. ``` ### Missing Implementation Plan If no clear implementation plan is found in the issue: - Inform the user that no implementation plan was found - Suggest using the `github-issue-planner` plugin first to create a plan - Ask if the user wants to proceed with their own implementation approach ### Merge Conflicts If there are conflicts with the base branch: - Report the conflicts to the user - Offer to help resolve them or wait for user decision ### Label Creation Fails If unable to create the label (permissions issue): - Continue without labeling - Inform the user that the label could not be added ## Important Guidelines ### Code Quality - Follow existing code patterns and conventions - Write clean, readable code - Include appropriate comments where logic is non-obvious - Handle edge cases mentioned in the plan ### Commits - Make atomic commits for logical changes - Write clear commit messages that reference the issue number - Do not commit generated files or secrets ### Testing - Run existing tests to ensure no regressions - Add tests as specified in the implementation plan - If no tests are specified, add reasonable test coverage ### Communication - Report progress at each major step - Ask for clarification when requirements are ambiguous - Summarize what was implemented when complete ## Completion Summary After successful completion, provide a summary: - PR URL and number - List of files changed - Tests added or modified - Any deviations from the original plan - Next steps (code review, CI checks, etc.)
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.