公开记录
软件健康报告模式 0.34.0 · 指标 2.10.0 · 2026-09-05 19:34 UTC

danielvm-git / bigpowers

Agent skills synthesizing years of software engineering discipline into a prescriptive methodology for solo developers

Shell · MDX · JavaScriptMIT★ 168 星标⑂ 13 复刻始于 2026年4月在 GitHub 上查看 ↗
类型库命令行工具MCP 服务器网络服务网页界面终端界面如何判定
#ai-agents#automation#bmad#claude-code#clean-code#cursor-rules#devops#documentation-as-code#gemini-cli#productivity#software-engineering#solo-developer#spec-driven-development#tdd

danielvm-git/bigpowers 的健康指数为 100 分中的 78 分，处于「良好」区间。 其得分最高的类别是Vitality（89/100），最低的是Security（39/100）。 最近一次更新在今天。 近期的大部分工作由 1 位贡献者完成。

78
总分 / 100
良好

软件健康指数

指标归入加权类别，统一采用 1–100 量表。总体分先取类别加权平均，再依据公开记录的分布进行校准，使各等级具有百分位含义；当公开证据触发高风险司法辖区政策时，评级会按政策调整，并设置 34（存在风险）的上限。

78
卓越93-100公开记录中的最高层级（约前 5%）；基本满足所有检验标准
优秀80-92各方面均表现强劲；仅有少量不足
良好65-79健康；不足之处有限且可控
中等50-64可接受，但存在明显不足；建议进行审查
薄弱35-49多个领域存在实质性薄弱环节
存在风险20-34存在重大薄弱环节；采用时应保持审慎
危急1-19问题严重（项目被弃置、仅有单一维护者、缺乏基本工程规范）
活力社区与采用可持续性与治理工程质量安全AI 就绪度

评分画像

每条轴代表一个类别。形状比平均值更重要——健康的对象会填满整个图形，而“一峰一谷”式画像意味着某一维度的优势正掩盖另一维度的风险。

加权总体分 67 经校准后在公布的指数量表上为 78（记录校准 2026-08-02）。

所有权

Daniel V M个人账户
11 关注者47 个公开仓库始于 2011年9月

该仓库由个人账户拥有。相较于组织支持的项目，单一所有者项目的延续性风险更高。

软件包生态系统

注册表软件包版本月下载量版本数最近发布标签
npmbigpowers2.88.134,8872220 天前skillsagentsclaudedevelopmentspec-driventest-firstpi-package

按类别列示的指标

活力

项目是否仍有生命——是否仍在编写代码，是否仍在发布版本？

89优秀 · 占总体的 21%

开发活跃度

81优秀
评分方式
36/36推送新近度 — 最近一次推送于 0 天前
17.3/36提交节奏 — 52 周中有 25 周有提交
18/18提交量 — 最近一年 1,013 次提交
10/10OpenSSF Scorecard：Maintained — 30 commit(s) and 24 issue activity found in the last 90 days -- score normalized to 10
所用输入
commits_last_year1,013
human_commit_share1
days_since_last_push0
active_weeks_last_year25

发布纪律

100卓越
评分方式
27/27有发布版本 — 已发布 100 个发布版本
36/36发布时效 — 最近一次发布版本于 0 天前
27/27发布节奏 — 约每 4.1 天发布一次
0/10OpenSSF Scorecard：Signed-Releases — 无数据
所用输入
releases_count100
latest_release_tagv2.88.1
releases_from_tags否
days_since_latest_release0
mean_days_between_releases4.1
已排除计分（无数据或不适用）：OpenSSF Scorecard：Signed-Releases。 其余权重已重新归一化。

社区与采用

项目是否拥有用户、下载量与关注度，并具备欢迎贡献者参与的配置？

62中等 · 占总体的 17%

流行度与采用

45薄弱
评分方式
36.1/60星标 — 168 个星标
9/25复刻 — 13 个复刻
0/15关注者 — 0 位关注者
所用输入
forks13
stars168
watchers0
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

社区健康

70良好
评分方式
22.5/22.5README
22.5/22.5许可证 — 可识别的许可证（MIT）
18/18CONTRIBUTING 指南
0/13.5行为准则
0/7.2议题模板
0/6.3PR 模板
所用输入
has_readme是
has_license是
readme_badges3
has_contributing是
has_issue_template否
has_code_of_conduct否
readme_badge_servicesshields.io
has_pull_request_template否

生态采用（下载量）

76良好
评分方式
60.6/80月度下载量 — npm 合计每月 34,887 次下载
0/20注册表被依赖数 — 该生态系统不报告此项
所用输入
packagesbigpowers
dependents—
ecosystemsnpm
total_downloads—
monthly_downloads34,887
unverified_packages_excluded—
已排除计分（无数据或不适用）：注册表被依赖数。 其余权重已重新归一化。

可持续性与治理

项目能否在其成员之外延续——巴士系数、响应能力、由谁支持，以及软件包的维护状况？

62中等 · 占总体的 23%

维护者韧性（巴士系数）

28存在风险
评分方式
9/54巴士系数 — 1 位贡献者贡献了半数提交
5.7/22.5提交分布 — 头号贡献者编写了 75% 的提交
6.8/13.5贡献者广度 — 5 位贡献者
6/10OpenSSF Scorecard：Contributors — project has 2 contributing companies or organizations -- score normalized to 6
所用输入
bus_factor1
contributors_sampled5
top_contributor_share0.748

议题与 PR 响应能力

81优秀
评分方式
41.1/42议题解决 — 98% 的议题已关闭
26.9/30PR 接受 — 已裁定的 PR 中 61/68 已合并
13/13Newcomer PR acceptance — 30 天内首次贡献者的 PR 已合并 2/2
0/15OpenSSF Scorecard：Code-Review — Found 2/30 approved changesets -- score normalized to 0
所用输入
merged_prs61
open_issues1
closed_issues47
prs_merged_7d4
prs_decided_7d4
prs_merged_30d7
prs_decided_30d7
issue_closed_ratio0.979
closed_unmerged_prs7
first_time_authors_30d1
first_time_prs_merged_30d2
first_time_prs_decided_30d2

所有权与托管责任

52中等
评分方式
10/30所有权背书 — 个人（用户）账户
0/20已验证域名 — 不适用于个人账户
7.8/25所有者影响力 — danielvm-git 有 11 位关注者
24.2/25既往记录 — 47 个公开仓库，账户约 15 年
所用输入
followers11
owner_typeUser
is_verified—
owner_logindanielvm-git
public_repos47
account_age_days5,482
已排除计分（无数据或不适用）：已验证域名。 其余权重已重新归一化。

软件包维护

100卓越
评分方式
25/25已发布且可解析 — npm 上有 1 个软件包
35/35发布时效 — 最近一次发布于 0 天前
20/20版本历史 — 222 个已发布版本
20/20未被弃用 — 活跃，未被弃用或撤回
所用输入
packagesbigpowers
ecosystemsnpm
any_deprecated否
min_days_since_publish0

工程质量

基础的工程与文档实践是否到位？

77良好 · 占总体的 19%

工程实践

62中等
评分方式
24/24CI 工作流 — 8 个工作流
24/24存在测试
0/16Linter 配置
0/9.6Pre-commit 钩子
0/6.4.editorconfig
14/20OpenSSF Scorecard：CI-Tests — 5 out of 7 merged PRs checked by a CI test -- score normalized to 7
所用输入
has_ci是
has_tests是
has_editorconfig否
has_linter_config否
has_precommit_config否

文档

100卓越
评分方式
30/30README
25/25文档目录
15/15文档 / 主页站点 — https://danielvm-git.github.io/bigpowers/
10/10仓库描述
10/10主题标签 — 14 个主题标签
10/10Wiki
所用输入
topicsai-agents, automation, bmad, claude-code, clean-code, cursor-rules, devops, documentation-as-code, gemini-cli, productivity, software-engineering, solo-developer, spec-driven-development, tdd
has_wiki是
homepagehttps://danielvm-git.github.io/bigpowers/
docs_sitehttps://danielvm-git.github.io/bigpowers/
has_readme是
has_docs_dir是
has_description是

安全

可见的安全与供应链实践是否稳固，且不存在未解决的高风险司法辖区暴露？

39薄弱 · 占总体的 16%

安全态势

39薄弱
评分方式
7.5/7.5Binary-Artifacts — no binaries found in the repo
2.2/7.5Branch-Protection — branch protection is not maximal on development and all release branches
1.8/2.5CI-Tests — 5 out of 7 merged PRs checked by a CI test -- score normalized to 7
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 2/30 approved changesets -- score normalized to 0
1.5/2.5Contributors — project has 2 contributing companies or organizations -- score normalized to 6
10/10Dangerous-Workflow — no dangerous workflow patterns detected
0/7.5Dependency-Update-Tool — no update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5许可证 — license file detected
7.5/7.5Maintained — 30 commit(s) and 24 issue activity found in the last 90 days -- score normalized to 10
0/5Packaging — 无数据
3/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 6
0/5SAST — SAST tool is not run on all commits -- score normalized to 0
0/5Security-Policy — security policy file not detected
0/7.5Signed-Releases — 无数据
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 57 existing vulnerabilities detected
所用输入
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate3.9
已排除计分（无数据或不适用）：Packaging, Signed-Releases。 其余权重已重新归一化。

AI 就绪度

该仓库在多大程度上具备与 AI 编码代理协同开发与维护的条件？权重刻意设小（4%）：代理工具链是一项真实的维护信号，但完全不具备的仓库仍可达到 100/100。

66良好 · 占总体的 4%

AI 代理上下文与指引

100卓越
评分方式
45/45代理指令 — .cursor/rules/align-grid.mdc, .cursor/rules/assess-impact.mdc, .cursor/rules/audit-code.mdc, .cursor/rules/audit-plan.mdc, .cursor/rules/build-epic.mdc, .cursor/rules/change-request.mdc, .cursor/rules/commit-message.mdc, .cursor/rules/compose-workflow.mdc, .cursor/rules/context7-mcp.mdc, .cursor/rules/craft-skill.mdc, .cursor/rules/deepen-architecture.mdc, .cursor/rules/define-language.mdc, .cursor/rules/define-success.mdc, .cursor/rules/delegate-task.mdc, .cursor/rules/deploy.mdc, .cursor/rules/design-interface.mdc, .cursor/rules/develop-tdd.mdc, .cursor/rules/diagnose-root.mdc, .cursor/rules/diagnose-stall.mdc, .cursor/rules/dispatch-agents.mdc, .cursor/rules/edit-document.mdc, .cursor/rules/elaborate-spec.mdc, .cursor/rules/enforce-first.mdc, .cursor/rules/evolve-skill.mdc, .cursor/rules/execute-plan.mdc, .cursor/rules/extract-design.mdc, .cursor/rules/find-way.mdc, .cursor/rules/fix-bug.mdc, .cursor/rules/gate-trace.mdc, .cursor/rules/generate-allure-report.mdc, .cursor/rules/grill-me.mdc, .cursor/rules/grill-with-docs.mdc, .cursor/rules/guard-git.mdc, .cursor/rules/harden-vps.mdc, .cursor/rules/hook-commits.mdc, .cursor/rules/inspect-quality.mdc, .cursor/rules/investigate-bug.mdc, .cursor/rules/kickoff-branch.mdc, .cursor/rules/maintain-wiki.mdc, .cursor/rules/map-codebase.mdc, .cursor/rules/migrate-spec.mdc, .cursor/rules/model-domain.mdc, .cursor/rules/orchestrate-project.mdc, .cursor/rules/organize-workspace.mdc, .cursor/rules/plan-refactor.mdc, .cursor/rules/plan-release.mdc, .cursor/rules/plan-tests.mdc, .cursor/rules/plan-work.mdc, .cursor/rules/publish-package.mdc, .cursor/rules/quick-fix.mdc, .cursor/rules/release-branch.mdc, .cursor/rules/request-review.mdc, .cursor/rules/research-first.mdc, .cursor/rules/reset-baseline.mdc, .cursor/rules/respond-review.mdc, .cursor/rules/run-benchmark.mdc, .cursor/rules/run-evals.mdc, .cursor/rules/run-planning.mdc, .cursor/rules/scope-work.mdc, .cursor/rules/search-skills.mdc, .cursor/rules/security-review.mdc, .cursor/rules/seed-conventions.mdc, .cursor/rules/session-state.mdc, .cursor/rules/setup-environment.mdc, .cursor/rules/simple-english.mdc, .cursor/rules/simulate-agents.mdc, .cursor/rules/slice-tasks.mdc, .cursor/rules/smoke-test.mdc, .cursor/rules/spike-prototype.mdc, .cursor/rules/stocktake-skills.mdc, .cursor/rules/survey-context.mdc, .cursor/rules/terse-mode.mdc, .cursor/rules/trace-requirement.mdc, .cursor/rules/using-bigpowers.mdc, .cursor/rules/validate-contracts.mdc, .cursor/rules/validate-fix.mdc, .cursor/rules/verify-work.mdc, .cursor/rules/visual-dashboard.mdc, .cursor/rules/wire-ci.mdc, .cursor/rules/wire-observability.mdc, .cursor/rules/write-document.mdc, CLAUDE.md, GEMINI.md, docs/AGENTS.md, docs/templates/AGENTS.md, specs/wayfinder/doc-templates/templates/agents.md, templates/codex/AGENTS.md, tests/fixtures/.tmp-v1.x/CLAUDE.md, tests/fixtures/v1.x-project/CLAUDE.md, tests/fixtures/v2.0.0-project/CLAUDE.md, tests/fixtures/v2.20-project/CLAUDE.md, website/AGENTS.md, website/CLAUDE.md, website/src/content/docs/guides/AGENTS.md
15/15机器可读文档（llms.txt） — 存在 llms.txt
40/40可读的提交历史 — 100 次人类提交中有 98 次说明了意图（结构化标题或解释性正文）
所用输入
has_llms_txt是
llms_txt_url—
legible_history_share0.98
agent_instruction_files.cursor/rules/align-grid.mdc, .cursor/rules/assess-impact.mdc, .cursor/rules/audit-code.mdc, .cursor/rules/audit-plan.mdc, .cursor/rules/build-epic.mdc, .cursor/rules/change-request.mdc, .cursor/rules/commit-message.mdc, .cursor/rules/compose-workflow.mdc, .cursor/rules/context7-mcp.mdc, .cursor/rules/craft-skill.mdc, .cursor/rules/deepen-architecture.mdc, .cursor/rules/define-language.mdc, .cursor/rules/define-success.mdc, .cursor/rules/delegate-task.mdc, .cursor/rules/deploy.mdc, .cursor/rules/design-interface.mdc, .cursor/rules/develop-tdd.mdc, .cursor/rules/diagnose-root.mdc, .cursor/rules/diagnose-stall.mdc, .cursor/rules/dispatch-agents.mdc, .cursor/rules/edit-document.mdc, .cursor/rules/elaborate-spec.mdc, .cursor/rules/enforce-first.mdc, .cursor/rules/evolve-skill.mdc, .cursor/rules/execute-plan.mdc, .cursor/rules/extract-design.mdc, .cursor/rules/find-way.mdc, .cursor/rules/fix-bug.mdc, .cursor/rules/gate-trace.mdc, .cursor/rules/generate-allure-report.mdc, .cursor/rules/grill-me.mdc, .cursor/rules/grill-with-docs.mdc, .cursor/rules/guard-git.mdc, .cursor/rules/harden-vps.mdc, .cursor/rules/hook-commits.mdc, .cursor/rules/inspect-quality.mdc, .cursor/rules/investigate-bug.mdc, .cursor/rules/kickoff-branch.mdc, .cursor/rules/maintain-wiki.mdc, .cursor/rules/map-codebase.mdc, .cursor/rules/migrate-spec.mdc, .cursor/rules/model-domain.mdc, .cursor/rules/orchestrate-project.mdc, .cursor/rules/organize-workspace.mdc, .cursor/rules/plan-refactor.mdc, .cursor/rules/plan-release.mdc, .cursor/rules/plan-tests.mdc, .cursor/rules/plan-work.mdc, .cursor/rules/publish-package.mdc, .cursor/rules/quick-fix.mdc, .cursor/rules/release-branch.mdc, .cursor/rules/request-review.mdc, .cursor/rules/research-first.mdc, .cursor/rules/reset-baseline.mdc, .cursor/rules/respond-review.mdc, .cursor/rules/run-benchmark.mdc, .cursor/rules/run-evals.mdc, .cursor/rules/run-planning.mdc, .cursor/rules/scope-work.mdc, .cursor/rules/search-skills.mdc, .cursor/rules/security-review.mdc, .cursor/rules/seed-conventions.mdc, .cursor/rules/session-state.mdc, .cursor/rules/setup-environment.mdc, .cursor/rules/simple-english.mdc, .cursor/rules/simulate-agents.mdc, .cursor/rules/slice-tasks.mdc, .cursor/rules/smoke-test.mdc, .cursor/rules/spike-prototype.mdc, .cursor/rules/stocktake-skills.mdc, .cursor/rules/survey-context.mdc, .cursor/rules/terse-mode.mdc, .cursor/rules/trace-requirement.mdc, .cursor/rules/using-bigpowers.mdc, .cursor/rules/validate-contracts.mdc, .cursor/rules/validate-fix.mdc, .cursor/rules/verify-work.mdc, .cursor/rules/visual-dashboard.mdc, .cursor/rules/wire-ci.mdc, .cursor/rules/wire-observability.mdc, .cursor/rules/write-document.mdc, CLAUDE.md, GEMINI.md, docs/AGENTS.md, docs/templates/AGENTS.md, specs/wayfinder/doc-templates/templates/agents.md, templates/codex/AGENTS.md, tests/fixtures/.tmp-v1.x/CLAUDE.md, tests/fixtures/v1.x-project/CLAUDE.md, tests/fixtures/v2.0.0-project/CLAUDE.md, tests/fixtures/v2.20-project/CLAUDE.md, website/AGENTS.md, website/CLAUDE.md, website/src/content/docs/guides/AGENTS.md
agent_instruction_max_bytes31,701

验证循环（构建 / 测试 / 类型检查）

51中等
评分方式
0/18一条命令的引导启动
22/22自动化测试
0/11Lint / 格式化配置
11/11静态类型检查 — bigpowers-mcp/tsconfig.json, website/tsconfig.json
10/10可复现环境 — lockfile
2/10已体现的代理实践 — 最近 100 次提交中有 1 次由代理编写或署名代理
0/8自动化维护 — 未观察到自动依赖更新
6/10OpenSSF Scorecard：Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 6
所用输入
has_nix否
has_tests是
lockfilespackage-lock.json
has_dockerfile否
typed_language否
bootstrap_files—
has_devcontainer否
has_linter_config否
typecheck_configsbigpowers-mcp/tsconfig.json, website/tsconfig.json
agent_commit_share0.01
toolchain_manifests—
dependency_bot_commit_share0

面向模型的代码可读性

82优秀
评分方式
27/45可类型检查的代码 — Shell，已配置类型检查（bigpowers-mcp/tsconfig.json, website/tsconfig.json）
55/55可控的文件大小 — 采样的 111 个源文件中有 0 个超过 60KB
所用输入
primary_languageShell
largest_source_bytes29,742
source_files_sampled111
oversized_source_files0

机器可读接口

20存在风险
评分方式
0/40API 模式（OpenAPI/GraphQL/proto）
20/20MCP 服务器
0/40可运行示例
所用输入
example_dirs—
has_mcp_signal是
api_schema_files—
interfaces_expected_ofnetwork-service

关键数据

168GitHub 星标
5贡献者
1,013最近 12 个月提交数
0距最近推送天数
100发布版本数
1巴士系数（bus factor）
1开放议题
npm, PyPI软件包生态系统数

数据采集警告

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • Could not fetch npm package 'bigpowers-mcp' from its registry
  • GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
  • deps.dev does not index npm:bigpowers@2.88.1; advisories assessed against the repository dependency graph instead

更多细节

Star 与 Fork 历史 0 ★ / 13 ⇿
0Star
13Fork
99发布

每颗 star 和每个 fork 的添加时间，来自 GitHub 并按天汇总。累计增长位于其构成来源——每日新增——的正上方，二者可相互对照：稳定的自然增长与短暂的突增形态截然不同。当这一差别可被衡量时，它会作为增长真实性予以报告。

03581013151322026-062026-072026-09
主版本 0次版本 27修订 72
OpenSSF Scorecard 3.9 / 10
3.9综合

来自开源项目 OpenSSF Scorecard 的独立、工具无关的安全评估。每项检查奖励的是安全实践本身，而非特定供应商的工具。Scorecard 无法判定的检查项标记为 不适用，并从安全评分中剔除（绝不按零分计）。Scorecard v5.5.0 · 2026-09-05 19:34 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
7CI-Tests5 out of 7 merged PRs checked by a CI test -- score normalized to 7
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 2/30 approved changesets -- score normalized to 0
6Contributorsproject has 2 contributing companies or organizations -- score normalized to 6
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 24 issue activity found in the last 90 days -- score normalized to 10
不适用Packagingpackaging workflow not detected
6Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 6
0SASTSAST tool is not run on all commits -- score normalized to 0
0Security-Policysecurity policy file not detected
不适用Signed-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities57 existing vulnerabilities detected
直接依赖 22
注册表软件包版本约束清单文件
npm@modelcontextprotocol/sdk^1.29.0bigpowers-mcp/package.json
npmjs-yaml^4.1.0bigpowers-mcp/package.json
npmremark-frontmatter^5.0.0bigpowers-mcp/package.json
npmremark-parse^11.0.0bigpowers-mcp/package.json
npmunified^11.0.5bigpowers-mcp/package.json
npmzod^3.24.2bigpowers-mcp/package.json
npmblessed0.1.81dashboard/package.json
npmchokidar3.6.0dashboard/package.json
npmexpress4.19.0dashboard/package.json
npmjs-yaml4.1.0dashboard/package.json
npm@clack/prompts^0.10.0package.json
npmpicocolors^1.1.1package.json
npm@astrojs/react^6.0.1website/package.json
npm@astrojs/sitemap^3.7.3website/package.json
npm@astrojs/starlight^0.41.3website/package.json
npmastro^7.0.2website/package.json
npmclsx^2.1.1website/package.json
npmreact^19.2.7website/package.json
npmreact-dom^19.2.7website/package.json
npmsharp^0.34.5website/package.json
npmtailwind-merge^3.6.0website/package.json
npmyaml^2.9.0website/package.json
全部依赖 未采集

本报告未能采集到解析后的依赖集合：GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

原始 JSON 报告 机器可读

反馈

发现这份报告有不准确之处，或有想法要分享？错误的测量、未识别的工具、建议、疑问——都欢迎提出。每条消息都会被阅读并得到回复。

登录过程中消息不会丢失。

相关记录

与 danielvm-git/bigpowers 共享目录标签或生态系统的已检测仓库。 并排阅读 →

98awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions卓越97langgenius/difyBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.卓越96e2b-dev/E2BOpen-source, secure environment with real-world tools for enterprise-grade agents.卓越95sickn33/agentic-awesome-skillsAAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,000+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.卓越95NousResearch/hermes-agentThe agent that grows with you卓越98kestra-io/kestraEvent Driven Orchestration & Scheduling Platform for Mission Critical Applications卓越

评分是信号，而非担保。 评分反映的是 GitHub 上公开可见的实践——不是代码审计，也不是安全保证。

缺失数据将被剔除并重新归一化权重，绝不按零分计。方法论已版本化并公开：指标 v2.10.0、模式 v0.34.0—— 完整方法论 · 指标知识库.

单项结果在整体记录中的位置： 汇总统计 — npm.