stevenmburns/build-issue
skills/build-issue/SKILL.md
Implement a feature issue using test-driven development
development
Updated Apr 20, 2026
$ install --global
skillsauthnpx skillsauth add stevenmburns/dot-claude-files build-issueInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 4:34 AM21.9s1 file scanned
SKILL.md
- name:
- build-issue
- description:
- Implement a feature issue using test-driven development
- user-invocable:
- true
- allowed-tools:
- Bash, Glob, Grep, Read, Write, Edit
Implement Feature with TDD
Read a GitHub feature issue, implement it test-first, and open a PR that references the issue.
Usage
/build-issue <issue-number>
Steps
- Read the issue with
gh issue view <number> --json title,body,commentsto understand the desired behavior and acceptance criteria - Explore the codebase to locate relevant files — understand existing patterns, data models, and conventions in the affected area
- Create a feature branch named descriptively (e.g.
feature/<short-description>) - Write tests first that describe the desired behavior from the issue's acceptance criteria:
- Tests should fail because the feature does not exist yet, not due to a technical problem (missing import, unresolvable module, etc.)
- If a test fails for a technical reason, fix that problem first so it fails for the right reason before continuing
- Follow existing test conventions in the project (file location, naming, test runner)
- Run the tests to confirm they fail for the right reason
- Implement the feature — write what is needed to make the tests pass
- Run tests to confirm all new tests pass and nothing else is broken — check CLAUDE.md or
package.json/pyproject.tomlfor the test command; if tests fail, fix them before continuing - Stage and commit with a descriptive conventional commit message; include
Closes #<number>in the commit body - Push the branch with
-uflag - Create a PR with
gh pr create:- Title: concise description of the feature (under 70 chars)
- Body must include
Closes #<number>so GitHub auto-closes the issue on merge; summarize what was built and how
- Report the PR URL to the user
Related Skills
stevenmburns/triage-issues
tools
VerifiedTrustedCommunity
Scan open GitHub issues, flag duplicates, and summarize with suggested priorities
SKILL.mdUpdated Apr 20, 2026
stevenmburns/tidy-branch
testing
VerifiedTrustedCommunity
Interactively clean up the current branch's commits (squash fixups, reword sloppy messages, reorder, drop) before merging — especially important on repos using rebase-merge where every branch commit lands on main verbatim
SKILL.mdUpdated Apr 20, 2026
stevenmburns/rename-pr
tools
VerifiedTrustedCommunity
Analyze the changes in the current PR and suggest a more accurate title if the current one no longer fits
SKILL.mdUpdated Apr 20, 2026
stevenmburns/merge-pr
data-ai
VerifiedTrustedCommunity
Merge the open PR for the current branch into main, delete the branch, and pull main
SKILL.mdUpdated Apr 20, 2026