agent-skills/beamho-sdd-workflow/SKILL.md
Use when developing, reviewing, or closing work in beamHO-bench that is governed by an active pending SDD, especially when the task requires reading PROJECT_CONSTRAINTS, active pending status, validation rules, and lifecycle-sync docs before editing code.
npx skillsauth add cedarwud/beamHO-bench beamho-sdd-workflowInstall 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.
Use this skill for beamHO-bench/ when the task is tied to an active pending SDD or when lifecycle status may need updating.
Read these first:
PROJECT_CONSTRAINTS.mdsdd/completed/beamHO-bench-implementation-status.mdsdd/pending/README.mddocs/zh-TW/07-observer-sky-visual-acceptance.mdgit status --short.If the change affects observer-sky rendering:
docs/zh-TW/07-observer-sky-visual-acceptance.mdPrefer this set unless the task is docs-only:
npm run lintnpm run test:simnpm run buildnpm run validate:stageIf validation is skipped, say so explicitly and explain why.
sdd/completed/beamHO-bench-implementation-status.md is the authority.sdd/pending/README.md and sdd/README.md must stay in sync with it.testing
Use when validating beamHO-bench changes, deciding which project gates to run, preparing SDD closure, or checking whether lifecycle docs and manual acceptance evidence are sufficient before marking work complete.
data-ai
Use when editing beamHO-bench paper profiles, source maps, assumption-backed research parameters, or paper-source registries so schema, profile JSON, sources JSON, and validation coverage stay traceable and synchronized.
development
Use when editing beamHO-bench observer-sky satellite rendering, composition, camera framing, display selection, continuity, or screen-space acceptance so frontend changes stay aligned with visual-acceptance rules instead of proxy metrics alone.
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.