Software Development Skills

Bootstrap or reorganize the project codebase (${CODENAME}/, read from .env) so research plans under metds/plans/ have a code home. When ${CODENAME}/ is missing or empty: mine the research plan for a search profile, find and score candidate reference implementations on GitHub (plan fit, completeness, license, activity), let the user pick one, then clone it, strip its git history, record provenance, and conservatively rebrand it to CODENAME. When code already exists: survey it with read-only subagents instead. Both paths then design a target architecture plus a migration table, execute only user-approved migrations via orchestrated subagents with per-group verification and git checkpoints, and write the architecture spec to metds/codearc.md with thin pointers in AGENTS.md and .cursor/rules/. Use when the user runs /star-code-architect, wants a reference implementation or starter codebase for a plan, wants to set up / scaffold ${CODENAME}/, or wants to organize / refactor the existing codebase and record its architecture. Bilingual (en/zh).

Compile the research-plan tree under metds/plans/ into paper-ready method documents under metds/. Invoked as /star-metd-summarize [OPT] where OPT is overview, dataset, framework, training, or evaluation; no argument compiles all five in dependency order (dataset → framework → training → evaluation → overview, which links the other four and so compiles last). Rebuilds the plan tree from parent:, then extracts what each document needs through a written map (overview ← root §1 problem, §2 positioning, §3 idea, §6 milestones; dataset ← §4 data choices plus every leaf's §2 datas/ inputs and data-building steps; framework ← §3 route plus modeling leaves and their ${CODENAME}/ paths; training ← §3 strategy, §4 budget, inits/ and hyperparameters; evaluation ← §4 benchmarks, baselines, metrics and ablation design plus §5 kill-criteria), merges the passages along the method's axis instead of the plan's, resolves conflicts leaf-over-parent and newer-over-older, marks content from unexecuted leaves as not yet verified, and turns uncovered template sections into TODOs naming the plan section to fill. Plans are the only source — never code, logs, wkdrs/ or chat; result numbers stay with star-expt-analyst. Writes only metds/ .md, and overwrites an existing generated doc only after a section-level change list is approved. An end-of-flow skill: the readiness gate compiles only a finished tree — every strategy plan finalized and every leaf execstatus done, i.e. all experiments finished and the method determined — and otherwise stops, naming and routing the unfinished work; a draft compile is an explicit user choice, never the default. Use when all experiments are finished and the plans are finalized and the user runs /star-metd-summarize, or wants to summarize / consolidate the finished research plans into a method write-up, produce overview, dataset, framework, training or evaluation documentation, or draft paper method material from the plans. Bilingual (en/zh).