Skip to main content
在 Manus 中运行任何 Skill
一键导入
jc1122
GitHub 创作者资料

jc1122

按仓库查看 16 个 GitHub 仓库中的 39 个已收集 skills。

已收集 skills
39
仓库
16
更新
2026-06-20
这里展示前 8 个仓库;完整仓库列表在下方继续。
仓库浏览

仓库与代表性 skills

test-effectiveness-audit
软件质量保证分析师与测试员

Deterministic, advisory mutation-testing audit for Python. Wraps mutmut==3.6.0 to measure per-module mutation kill rates, emitting TEST findings (shared code-health schema) for modules whose kill rate falls below the configured threshold. Never mutates source in-place; runs in a sandbox copy. The machine-readable answer to "how good are my tests at catching bugs?".

2026-06-16
code-health-audit-pipeline
软件质量保证分析师与测试员

Umbrella that runs the code-health leaf skills (complexity, duplication, dead-code, structure, quality) in parallel, merges and ranks their findings into one report, and emits a supervisor decision with exit codes 0/1/2. Reads a leaf registry so new language leaves plug in without changing the orchestrator. Advisory only.

2026-06-15
complexity-audit
软件质量保证分析师与测试员

Deterministic, advisory complexity and maintainability audit for Python. Uses lizard (per-function cyclomatic complexity, length, parameters) and radon mi (per-module maintainability index) to emit SIMPLIFY / DECOMPOSE findings to the shared code-health finding schema. Never mutates source.

2026-06-15
coverage-gap-audit
软件质量保证分析师与测试员

Deterministic, advisory testedness audit for Python. Consumes coverage.py JSON report(s) and emits TEST findings (shared code-health schema) for production files with no or insufficient test coverage. Never runs tests, never mutates source. The machine-readable answer to "is this file safe to refactor?".

2026-06-15
dead-code-audit
软件开发工程师

Deterministic, advisory dead-code audit for Python. Uses vulture (unused functions/classes/methods/properties) and ruff F401/F811/F841 (unused imports, redefinitions, unused locals) to emit DELETE findings to the shared code-health finding schema. Never mutates source.

2026-06-15
dependency-audit
软件开发工程师

Deterministic, advisory dependency audit for Python. Compiles declared dependencies (pyproject.toml [project] or requirements*.txt) against AST-collected imports and reports unused declarations, undeclared imports, test-only runtime usage, and optional C-8 advisory enrichment. Uses stdlib only, requires Python >=3.11, never mutates source, and never makes network calls.

2026-06-15
docs-consistency-audit
软件开发工程师

Deterministic, advisory docs-vs-reality audit for Python docs and command docs that emits LINT findings. Compares documented CLI flags against actual argparse parsers, checks doc paths for dead references, flags stale version pins, and optionally reports docstring coverage. Never mutates source.

2026-06-15
duplication-audit
软件开发工程师

Deterministic, advisory copy-paste clone audit for Python. Uses jscpd to detect duplicated token sequences and emits EXTRACT (cross-file) / MERGE (same-file) findings to the shared code-health finding schema. Never mutates source.

2026-06-15
当前展示该仓库 Top 8 / 19 个已收集 skills。
goal-branch-orchestrator
其他计算机职业

Runtime-only branch orchestrator for an audited branch prompt and existing branch worktree. Use when goal-main-orchestrator has passed prompt audit, created a branch integration worktree, and launched a branch session that must run skill/CLI bootstrap, optionally use CLI-only Lite advisors for packet planning/context packing/completed-worker summaries/blocked triage, create path-safe worker/research-worker/reviewer packets with telemetry, choose allowed per-worker routes from the ds-pro-max -> ds-flash-max -> codex-spark -> codex-mini ladder (bridge deepseek leading, native Codex fallback) for normal workers, keep worker launcher slots saturated with ready workers, integrate results, dispatch a read-only heavy-model reviewer, and return only when the branch prompt's falsifiable Definition of Done is satisfied or blocked.

2026-06-20
goal-config
其他计算机职业

Configure and verify goal orchestration model/provider profiles. Use when the user wants lean agent UX for model ladders, harness providers, branch/worker aggressiveness, token/character/time effort settings, or a fail-closed smoke test before goal-preflight or runtime orchestration.

2026-06-20
goal-main-orchestrator
其他计算机职业

Runtime-only main orchestrator for prepared /goal job bundles. Use when a /goal session has been launched from a goal-preflight bootloader and must consume existing job.manifest.json, main.prompt.md, and branch prompts; first run skill availability bootstrap and fail-closed prompt audit with telemetry, optionally use CLI-only Lite advisors after audit or completed branch artifacts for advisory summaries, then create path-validated branch worktrees, dispatch goal-branch-orchestrator sessions within the hard agent limit, summarize packet telemetry, and finish only when the main prompt's falsifiable Definition of Done is satisfied.

2026-06-20
goal-plan-amender
其他计算机职业

Runtime-only plan amender for audited /goal bundles. Use only when goal-main-orchestrator has validated a terminal branch result and needs amendment proposals or deterministic blocker-repair proposals; create file-backed packets, validate safe manifest amendments, and apply accepted amendments without changing active or terminal branch evidence.

2026-06-20
goal-preflight
其他计算机职业

Prepare path-hardened /goal orchestration bundles from a report, roadmap, diagnosis, or rough goal brief. Use when the user needs prompt infrastructure for goal-main-orchestrator: optionally use CLI-only Lite advisors for source digestion or lint-repair advice, synthesize rolling-scheduled branch groups and worker-sized work items when missing, enforce reproducible manifest paths and telemetry requirements, write job.manifest.json/main.prompt.md/branch prompts/location-bound goal-bootloader.md, run deterministic lint, and present the exact bootloader text for manual /goal launch.

2026-06-20
已展示 12 / 16 个仓库