.agents/skills/init-project/SKILL.md
Codex wrapper for staged `CLAUDE.md` generation and updates. Use when the user wants the compact project snapshot initialized or refreshed while preserving the original staged template behavior.
npx skillsauth add linzhe001/Harness-Research init-projectInstall 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:
./references/claude-md-template.md./references/claude-maintenance.md../../../.agents/references/language-policy.md../../../PROJECT_STATE.json if it exists../../../CLAUDE.md if it existsInterpret natural-language requests as one of:
initupdatedeps-changedinitCLAUDE.md with an explicit placeholder that WF5 baseline-repro owns first environment creation.CLAUDE.md using the canonical template../references/claude-maintenance.md when editing individual sections instead of rewriting the whole file.updatePROJECT_STATE.json and the stage artifacts.## Custom.CLAUDE.md immediately../references/claude-maintenance.md for section-safe updates../references/claude-maintenance.md before writing them into CLAUDE.md.deps-changed$env-setup refresh.$init-project {init|update|deps-changed} interface.## Custom preservation rule.## Language Policy section and keep it aligned with ../../../.agents/references/language-policy.md.AGENTS.md as Codex-native always-on guidance, but maintain CLAUDE.md for compatibility exactly as the canonical prompt expects.Follow the local prompt, template, and language policy rather than replacing CLAUDE.md maintenance with a generic project summary.
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.