.agents/skills/code-expert/SKILL.md
Codex wrapper for WF7 first-pass code generation. Use when the user wants implementation generated directly from `project_map.json`, the roadmap, and the original Claude skill contract.
npx skillsauth add linzhe001/Harness-Research code-expertInstall 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.
Read these first:
../../../.agents/references/workflow-guide.md../../../.agents/references/code-style.md../../../.agents/references/language-policy.md../../../.agents/references/project-map-rule.md./references/generation-order.md../../../PROJECT_STATE.json../../../project_map.json../../../docs/Implementation_Roadmap.mdUse this skill for WF7 first-pass code generation only.
project_map.json, docs/Implementation_Roadmap.md, PROJECT_STATE.json, and the style/rule files before editing.src/utils/src/models/src/data/src/losses/scripts/tests/project_map.json.python -m py_compileruff check --select=E,F,IPROJECT_STATE.json on full success.$code-debug instead.$code-expert [target or all] flow.project_map.json and the roadmap before editing.../../../.agents/references/language-policy.md for reply language and for any natural-language summaries; keep paths, schema keys, commands, and code identifiers in English.Follow the local prompt and language policy as the source of truth for WF7 code generation behavior.
development
WF7.5 training pipeline validation. Before entering WF8 iteration, first use Codex to review code for baseline equivalence, then run a 100-step smoke test to verify end-to-end pipeline functionality.
business
WF1 Inspiration survey and gap analysis. Takes the user's research idea, performs literature search, gap analysis, competitor analysis, and feasibility scoring, then outputs Feasibility_Report.md. Use when the user has a new CV research idea that needs a feasibility assessment.
tools
WF10 Submission/Release Tool. Multi-scene training, result packaging, filename validation, dry-run submission checks. Used after ablation experiments are complete and before competition submission.
development
WF2 Architecture refinement and MVP design. Reads the feasibility report, analyzes the base codebase architecture, designs plug-and-play new modules, defines the MVP, provides A/B/C alternative plans, and outputs Technical_Spec.md. Use when a research idea needs to be translated into a concrete technical architecture design.