skills/5d-build/SKILL.md
Execute implementation tasks with quality and awareness. Use when: (1) After TASKS phase in 5D-SDD workflow, (2) Tasks are defined and sequenced, (3) User is ready to write code, (4) User asks to 'implement,' 'build,' or 'code' a task. This phase produces working code while maintaining connection to spec intent.
npx skillsauth add tapania/5d-skills 5d-buildInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Execute tasks while maintaining spec alignment and code quality.
Before writing code, re-read the relevant spec section. After writing code, verify it matches spec.
Common drift patterns:
If drift is intentional: update spec first, then code.
The implementation is one solution, not the only solution. Stay open to:
Flag these for VERIFY phase rather than silently changing.
While building, ask: "Does this still serve the business/user intent?"
Technical correctness ≠ solving the right problem.
During implementation, check all perspectives:
If blocked:
Watch for defensive coding:
For each task:
## Task [N] Complete
**Status:** done / blocked / needs-spec-update
**Implementation notes:**
[Brief description of approach taken]
**Spec drift:**
[Any deviations from spec - intentional or discovered]
**Discoveries:**
[Edge cases, issues, or insights found during implementation]
**Ready for verify:** [yes/no]
Stop building and escalate if:
Return to appropriate earlier phase rather than guessing.
Proceed to VERIFY when:
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.