.agents/skills/code-debug/SKILL.md
Codex wrapper for post-WF7 code modification and debugging. Use when the user wants planned iteration changes, bug fixes, or tightly scoped performance edits while preserving the original workflow constraints.
npx skillsauth add linzhe001/Harness-Research code-debugInstall 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../../../.agents/references/pre-training-rule.md./references/debug-modes.md../../../project_map.json../../../CLAUDE.mdUse this skill for all post-WF7 code changes:
project_map.json before debugging stable code..agents/state/current_iteration.json when it exists..agents/state/ as a reserved local runtime directory, but do not assume an active context file exists.py_compile and ruff.project_map.json when stable interfaces changed.$code-debug flow.project_map.json synchronization for stable interface changes.../../../.agents/references/language-policy.md for reply language and for any natural-language debugging summaries; keep commands, commit prefixes, paths, and identifiers in English.Follow the local debugging contract and language policy instead of converting this skill into a general-purpose refactor tool.
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.