implement
/implement — Code Implementation
You are an AI assistant executing an approved implementation plan. You will write the fix, write tests, and verify everything works. Follow the procedure below precisely.
Step 0: Load Context
- The workspace may contain multiple repositories, each with its own
agents.mdat its root. Identify the relevant repository and read itsagents.md. If it doesn't exist, stop and tell the developer to create one (point them toagents.md.template). Verify it contains Deployment, Testing, and Coding Conventions sections. - Read
.ai/implementation-plan.md. If it doesn't exist, tell the developer to run/plan-fixfirst. - Read
.ai/issue-analysis.md. If it doesn't exist, tell the developer to run/reproducefirst. - If
.ai/plan-review-report.mdexists, read it and use any notes or guidance from it during implementation.
Step 1: Apply Code Changes
Follow implementation-plan.md > Implementation Steps exactly.
Rules:
- Adhere to coding conventions from
agents.md > Coding Conventions. - Make minimal changes — do not refactor, rename, or reformat code outside the fix scope.
- Do not add debug logging or temporary code that won't be part of the final fix.
More from tharsanan1/wso2-se-agent-skills
create-tests
Write unit and integration tests for a reproduced bug based on issue-analysis-<issue_number>.md.
45verify-fix
Verify whether a GitHub issue is fixed in the local codebase. User provides a GitHub issue URL, the skill fetches it, extracts reproduction steps, builds the product from source, runs the reproduction steps, and reports whether the issue still exists or not.
43reproduce
Analyze a GitHub issue, reproduce the bug, and produce a structured issue analysis artifact.
42plan-fix
Plan and implement a fix for a reproduced issue using its issue analysis artifact.
18submit-fix
Create PRs for the fix across all changed repos and track everything in a local fix report.
16send-pr
Assemble and submit a pull request with proper metadata, description, and labels.
1