STAR
Review Skills in wanghao9610/STAR, with license, maintenance context, and source paths.
- Skills
- 14
- Repository stars
- 44
- Identity status
- Source-linked
Provenance
Source and identity
- Profile type
- Repository
- Canonical name
- STAR
- Public sources
- 1
- License context
- MIT
Source entries
Agent Skills from STAR
Repository stars and maintenance signals provide context, but do not automatically become an individual Skill's quality score.
wanghao9610/STAR
star-code-architect
Set up or reorganize the project codebase (${CODE_NAME}/, from .env) so plan code has a home. An empty tree scores reference implementations on GitHub, clones the pick, strips its history, rebrands it; existing code is surveyed read-only. Both design a target architecture, migrate only approved changes, and write metds/codearc.md. Use when the user runs star-code-architect, wants a starter codebase, or wants ${CODE_NAME}/ scaffolded or refactored. Bilingual (en/zh).
wanghao9610/STAR
star-code-reviewer
Review code against the project's conventions and, when scoped to a plan, against what it promised. No argument reviews all of ${CODE_NAME}/; a PLAN_NAME (slug / prefix / filename) reviews the files that plan touches plus conformance (§3 tasks, §4 deliverables, §5 done-criterion); a path reviews that path; `diff` or a git range reviews changed files. Gathers static evidence through the .env env (installs no tools), scores findings on a six-dimension rubric (docstrings, naming, simplicity, conven
wanghao9610/STAR
star-code-reviewer
Review code against the project's conventions and, when scoped to a plan, against what it promised. No argument reviews all of ${CODE_NAME}/; a PLAN_NAME (slug / prefix / filename) reviews the files that plan touches plus conformance (§3 tasks, §4 deliverables, §5 done-criterion); a path reviews that path; `diff` or a git range reviews changed files. Gathers static evidence through the .env env (installs no tools), scores findings on a six-dimension rubric (docstrings, naming, simplicity, conven
wanghao9610/STAR
star-env-builder
Build and verify the project's Python runtime so plan execution has a working interpreter. Reads .env: a valid CONDA_HOME creates conda env ENV_NAME (argument, default CODE_NAME); otherwise a .venv in the root. An existing environment is never deleted — after confirmation it is renamed to a dated backup first. Dependencies come from the first source that has them: existing CODE_NAME/requirements* → packaging metadata (pyproject / setup.py / environment.yml) → import scan of the code, written out
wanghao9610/STAR
star-env-builder
Build and verify the project's Python runtime so plan execution has a working interpreter. Reads .env: a valid CONDA_HOME creates conda env ENV_NAME (argument, default CODE_NAME); otherwise a .venv in the root. An existing environment is never deleted — after confirmation it is renamed to a dated backup first. Dependencies come from the first source that has them: existing CODE_NAME/requirements* → packaging metadata (pyproject / setup.py / environment.yml) → import scan of the code, written out
wanghao9610/STAR
star-expt-analyst
Analyze what a plan's run produced and judge it against what the plan expected. A PLAN_NAME (slug / prefix / filename) resolves via exec_runs to its wkdrs/<run>/; a wkdrs/<run>/ path back-resolves to its plan; no argument lists the runs and asks. Inventories the §4 deliverables, checks EXEC_LOG's claims against artifacts, scans logs for health signals (crashes, NaN, OOM, divergence), scores the §5 done-criteria metrics against those criteria and baselines, writing the analysis under wkdrs/<run>/
wanghao9610/STAR
star-expt-analyst
Analyze what a plan's run produced and judge it against what the plan expected. A PLAN_NAME (slug / prefix / filename) resolves via exec_runs to its wkdrs/<run>/; a wkdrs/<run>/ path back-resolves to its plan; no argument lists the runs and asks. Inventories the §4 deliverables, checks EXEC_LOG's claims against artifacts, scans logs for health signals (crashes, NaN, OOM, divergence), scores the §5 done-criteria metrics against those criteria and baselines, writing the analysis under wkdrs/<run>/
wanghao9610/STAR
star-refs-reviewer
Build an auditable related-work base: 5–10 close papers read into per-paper analysis notes, plus a classified reference.bib of ≥50 verified entries. No argument finds the method in metds/ and runs the full pass, resuming if metds/refs/ exists; a PLAN_NAME or topic scopes the search; `verify` re-fetches and diffs every entry; `organize` re-classifies the bib; `synthesize` compiles the notes into a related-work narrative; `survey` reads a topic in tiers into its own file; `score` refreshes the imp
wanghao9610/STAR
star-refs-reviewer
Build an auditable related-work base: 5–10 close papers read into per-paper analysis notes, plus a classified reference.bib of ≥50 verified entries. No argument finds the method in metds/ and runs the full pass, resuming if metds/refs/ exists; a PLAN_NAME or topic scopes the search; `verify` re-fetches and diffs every entry; `organize` re-classifies the bib; `synthesize` compiles the notes into a related-work narrative; `survey` reads a topic in tiers into its own file; `score` refreshes the imp
wanghao9610/STAR
star-refs-reviewer
Literature review and related work: per-paper analysis notes plus a verified reference.bib. Builds an auditable base — 5–10 close papers read into notes, plus a classified reference.bib of ≥50 verified entries. No argument finds the method in metds/ and runs the full pass, resuming if metds/refs/ exists; a PLAN_NAME or topic scopes the search; `verify` re-fetches and diffs every entry; `organize` re-classifies the bib; `synthesize` compiles the notes into a related-work narrative; `survey` reads
wanghao9610/STAR
star-refs-reviewer
Build an auditable related-work base: 5–10 close papers read into per-paper analysis notes, plus a classified reference.bib of ≥50 verified entries. No argument finds the method in metds/ and runs the full pass, resuming if metds/refs/ exists; a PLAN_NAME or topic scopes the search; `verify` re-fetches and diffs every entry; `organize` re-classifies the bib; `synthesize` compiles the notes into a related-work narrative; `survey` reads a topic in tiers into its own file; `score` refreshes the imp
wanghao9610/STAR
star-refs-reviewer
Build an auditable related-work base: 5–10 close papers read into analysis notes, plus a classified reference.bib of ≥50 entries. No argument runs the full pass, resuming; a PLAN_NAME or topic scopes it; `verify`, `organize`, `synthesize`, `survey`, `score` and `add` are narrower passes. Every bib field is transcribed from a record fetched in-run, its source URL logged. Use when the user runs star-refs-reviewer, or wants a literature review or reference.bib. Bilingual (en/zh).
Pinned paths
Every entry links to a specific source path and commit when available.
Repository context
Activity, license, and repository-level popularity are shown as context.
Open the source
Inspect the public repository