公开记录
软件健康报告模式 0.34.0 · 指标 2.10.0 · 2026-10-21 09:59 UTC

stbenjam / skillsaw

Keep your skills sharp. Intelligence for agent context.

PythonApache-2.0★ 67 星标⑂ 15 复刻始于 2026年5月在 GitHub 上查看 ↗
类型命令行工具库如何判定
#agent#agents#agents-skills#agentskill#agentskills#agentsmd#ai#antigravity#claude-code#codex#cursor#grok#linter#muse#skill#skill-md#skills

stbenjam/skillsaw 的健康指数为 100 分中的 94 分，处于「卓越」区间。 其得分最高的类别是Engineering Quality（100/100），最低的是Community & Adoption（66/100）。 最近一次更新在 4 天前。 近期的大部分工作由 1 位贡献者完成。

94
总分 / 100
卓越

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。

94
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 80 经校准后在公布的指数量表上为 94（记录校准 2026-08-02）。

所有权

Stephen Benjamin个人账户
85 关注者357 个公开仓库始于 2010年10月Red Hat

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
PyPIskillsaw0.22.0887,504374 天前agentskillsclaudeclaude-codelinterpluginskillsvalidationskillsaw

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？

91优秀 · 占总体的 21%

开发活跃度

85优秀
评分方式
36/36推送新近度 — 最近一次推送于 4 天前
20.8/36提交节奏 — 52 周中有 30 周有提交
18/18提交量 — 最近一年 1,573 次提交
10/10OpenSSF Scorecard：Maintained — 30 commit(s) and 22 issue activity found in the last 90 days -- score normalized to 10
所用输入
commits_last_year1,573
human_commit_share0.97
days_since_last_push4
active_weeks_last_year30

发布纪律

100卓越
评分方式
27/27有发布版本 — 已发布 36 个发布版本
36/36发布时效 — 最近一次发布版本于 4 天前
27/27发布节奏 — 约每 14 天发布一次
0/10OpenSSF Scorecard：Signed-Releases — 无数据
所用输入
releases_count36
latest_release_tagv0.22.0
releases_from_tags否
days_since_latest_release4
mean_days_between_releases14
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？

66良好 · 占总体的 17%

流行度与采用

41薄弱
评分方式
29.5/60星标 — 67 个星标
9.6/25复刻 — 15 个复刻
1.7/15关注者 — 3 位关注者
所用输入
forks15
stars67
watchers3
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（Apache-2.0）
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_badges5
has_contributing是
has_issue_template否
has_code_of_conduct否
readme_badge_servicesbadge.fury.io, codecov.io, github.com, shields.io
has_pull_request_template否

生态采用（下载量）

99卓越
评分方式
79.3/80月度下载量 — pypi 合计每月 887,504 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
packagesskillsaw
dependents—
ecosystemspypi
total_downloads—
monthly_downloads887,504
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？

69良好 · 占总体的 23%

维护者韧性（巴士系数）

43薄弱
评分方式
9/54巴士系数 — 1 位贡献者贡献了半数提交
10.8/22.5提交分布 — 头号贡献者编写了 52% 的提交
13.5/13.5贡献者广度 — 12 位贡献者
10/10OpenSSF Scorecard：Contributors — project has 15 contributing companies or organizations
所用输入
bus_factor1
contributors_sampled12
top_contributor_share0.52

议题与 PR 响应能力

83优秀
评分方式
41.1/42议题解决 — 98% 的议题已关闭
25.1/30PR 接受 — 已裁定的 PR 中 427/511 已合并
0/13Newcomer PR acceptance — 30 天内没有首次贡献者的 PR 得到裁决
6/15OpenSSF Scorecard：Code-Review — Found 11/25 approved changesets -- score normalized to 4
所用输入
merged_prs427
open_issues3
closed_issues131
prs_merged_7d2
prs_decided_7d2
prs_merged_30d12
prs_decided_30d12
issue_closed_ratio0.978
closed_unmerged_prs84
first_time_authors_30d0
first_time_prs_merged_30d0
first_time_prs_decided_30d0
已排除计分（无数据或不适用）：Newcomer PR acceptance。 其余权重已重新归一化。

所有权与托管责任

61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
13.9/25所有者影响力 — stbenjam 有 85 位关注者
25/25既往记录 — 357 个公开仓库，账户约 16 年
所用输入
followers85
owner_typeUser
is_verified—
owner_loginstbenjam
public_repos357
account_age_days5,858
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 — pypi 上有 1 个软件包
35/35发布时效 — 最近一次发布于 4 天前
20/20版本历史 — 37 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
packagesskillsaw
ecosystemspypi
any_deprecated否
min_days_since_publish4

工程质量

基础的工程与文档实践是否到位？

100卓越 · 占总体的 19%

工程实践

100卓越
评分方式
24/24CI 工作流 — 18 个工作流
24/24存在测试
16/16Linter 配置 — pyproject.toml ([tool.black])
9.6/9.6Pre-commit 钩子
6.4/6.4.editorconfig
20/20OpenSSF Scorecard：CI-Tests — 28 out of 28 merged PRs checked by a CI test -- score normalized to 10
所用输入
has_ci是
has_tests是
has_editorconfig是
has_linter_config是
has_precommit_config是

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://skillsaw.org/
10/10仓库描述
10/10主题标签 — 17 个主题标签
10/10Wiki
所用输入
topicsagent, agents, agents-skills, agentskill, agentskills, agentsmd, ai, antigravity, claude-code, codex, cursor, grok, linter, muse, skill, skill-md, skills
has_wiki是
homepagehttps://skillsaw.org/
docs_sitehttps://skillsaw.org/
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？

74良好 · 占总体的 16%

安全态势

68良好
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
2.5/2.5CI-Tests — 28 out of 28 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
3/7.5Code-Review — Found 11/25 approved changesets -- score normalized to 4
2.5/2.5Contributors — project has 15 contributing companies or organizations
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — 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 22 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
3/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 6
5/5SAST — SAST tool is run on all commits
2/5Security-Policy — security policy file detected
0/7.5Signed-Releases — 无数据
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
6/7.5Vulnerabilities — 2 existing vulnerabilities detected
所用输入
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate6.8
已排除计分（无数据或不适用）：Signed-Releases。 其余权重已重新归一化。

依赖安全公告

100卓越
评分方式
35/35直接依赖不含已知公告 — 没有直接依赖携带已知公告
25/25间接依赖不含已知公告 — 没有间接依赖携带已知公告
0/40没有长期未处理的公告 — 没有公告带有发布日期
所用输入
sourceosv
advisories0
affected_packages0
assessed_packages13
unassessed_packages0
affected_by_severitynone
direct_affected_packages0
已排除计分（无数据或不适用）：没有长期未处理的公告。 其余权重已重新归一化。 比对的是 pypi:skillsaw@0.22.0 的运行时依赖闭包——安装已发布的软件包时真正被拉取进来的内容——共 13 个软件包。 未对可达性进行分析。

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。

85优秀 · 占总体的 4%

AI 代理上下文与指引

93卓越
评分方式
45/45代理指令 — .agents/skills/skillsaw-maintenance/references/claude.md, .apm/skills/skillsaw-maintenance/references/claude.md, .claude/skills/skillsaw-maintenance/references/claude.md, .cursor/rules/development.mdc, .cursor/rules/python.mdc, .cursor/rules/testing.mdc, .github/copilot-instructions.md, .github/instructions/development.instructions.md, .github/instructions/python.instructions.md, .github/instructions/testing.instructions.md, AGENTS.md, docs/rules/claude.md, examples/plugins/skillsaw-example-plugin/tests/fixture/CLAUDE.md, src/skillsaw/marketplace/templates/claude-code/agent.md, tests/fixtures/agent-memory/notes/AGENTS.md, tests/fixtures/antigravity/codex-marketplace/AGENTS.md, tests/fixtures/antigravity/dual-manifest/AGENTS.md, tests/fixtures/antigravity/plugins-symlink/repo/AGENTS.md, tests/fixtures/antigravity/portable-manifest/AGENTS.md, tests/fixtures/antigravity/registry-entries/AGENTS.md, tests/fixtures/antigravity/registry-escape/repo/AGENTS.md, tests/fixtures/antigravity/shared-codex-hooks/AGENTS.md, tests/fixtures/antigravity/shared-cursor-hooks/AGENTS.md, tests/fixtures/antigravity/shared-hooks-file/AGENTS.md, tests/fixtures/antigravity/shared-plugin-hooks/AGENTS.md, tests/fixtures/antigravity/symlink-escape/repo/AGENTS.md, tests/fixtures/antigravity/workspace-broken/AGENTS.md, tests/fixtures/antigravity/workspace-clean/AGENTS.md, tests/fixtures/apm/broken/CLAUDE.md, tests/fixtures/apm/broken/GEMINI.md, tests/fixtures/apm/clean/.apm/instructions/CLAUDE.md, tests/fixtures/apm/hooks-clean/.apm/instructions/CLAUDE.md, tests/fixtures/apm/hooks-dangerous/.apm/instructions/CLAUDE.md, tests/fixtures/autofix/name-inline-comment/CLAUDE.md, tests/fixtures/autofix/name-multiline-scalar/CLAUDE.md, tests/fixtures/autofix/rename-refs-substring/CLAUDE.md, tests/fixtures/autofix/safe-idempotency/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-already-linked/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-backtick-paths/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-duplicate-paths/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-mixed/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-multiple-paths/CLAUDE.md, tests/fixtures/codex/config-hooks-broken/AGENTS.md, tests/fixtures/codex/config-hooks-clean/AGENTS.md, tests/fixtures/codex/hooks-broken/AGENTS.md, tests/fixtures/codex/hooks-clean/AGENTS.md, tests/fixtures/codex/hooks-root-dangerous/AGENTS.md, tests/fixtures/codex/hooks-subpackage/AGENTS.md, tests/fixtures/codex/hooks-subpackage/services/billing/AGENTS.md, tests/fixtures/config/baseline-info/CLAUDE.md, tests/fixtures/config/baseline-test/CLAUDE.md, tests/fixtures/config/deprecated-rules/CLAUDE.md, tests/fixtures/config/exclude-conventional-skill-root/CLAUDE.md, tests/fixtures/config/opt-in-rules/CLAUDE.md, tests/fixtures/config/terminology-groups/AGENTS.md, tests/fixtures/config/terminology-groups/CLAUDE.md, tests/fixtures/content-unclosed-fence/skill-hides-violations/CLAUDE.md, tests/fixtures/content/banned-references-migration/CLAUDE.md, tests/fixtures/content/emphasis-density/CLAUDE.md, tests/fixtures/content/inconsistent-terminology-registers/AGENTS.md, tests/fixtures/content/inconsistent-terminology-registers/CLAUDE.md, tests/fixtures/content/inline-tool-examples/CLAUDE.md, tests/fixtures/content/instruction-drift/CLAUDE.md, tests/fixtures/content/mcp-tool-name-ambiguous/CLAUDE.md, tests/fixtures/content/mcp-tool-name-coderabbit/CLAUDE.md, tests/fixtures/content/mcp-tool-name-hook-prompt/AGENTS.md, tests/fixtures/content/mcp-tool-name/CLAUDE.md, tests/fixtures/content/progressive-disclosure/CLAUDE.md, tests/fixtures/content/repeated-directive-html-example/CLAUDE.md, tests/fixtures/content/repeated-directive/CLAUDE.md, tests/fixtures/content/terminology-distinct-concepts/AGENTS.md, tests/fixtures/content/unclosed-fence-coderabbit/CLAUDE.md, tests/fixtures/content/unlinked-reference-signal/CLAUDE.md, tests/fixtures/cursor-rules/broken-frontmatter/.cursorrules, tests/fixtures/cursor-rules/broken-frontmatter/AGENTS.md, tests/fixtures/cursor-rules/broken-hooks/AGENTS.md, tests/fixtures/cursor-rules/clean/AGENTS.md, tests/fixtures/cursor-rules/prompt-hooks/AGENTS.md, tests/fixtures/custom-rule-tree-example/CLAUDE.md, tests/fixtures/devin/valid/.windsurfrules, tests/fixtures/devin/valid/AGENT.md, tests/fixtures/devin/valid/apps/web/.windsurfrules, tests/fixtures/devin/valid/apps/web/CLAUDE.md, tests/fixtures/devin/valid/apps/web/agents.md, tests/fixtures/dot-claude/agents-imports-broken/AGENTS.md, tests/fixtures/dot-claude/agents-imports-clean/AGENTS.md, tests/fixtures/dot-claude/broken/CLAUDE.md, tests/fixtures/dot-claude/clean/CLAUDE.md, tests/fixtures/editor-tools/broken-mcp/AGENTS.md, tests/fixtures/editor-tools/monorepo/AGENTS.md, tests/fixtures/frontmatter-paths/CLAUDE.md, tests/fixtures/grok/config-broken/AGENTS.md, tests/fixtures/grok/config-clean/AGENTS.md, tests/fixtures/grok/marketplace-broken/AGENTS.md, tests/fixtures/grok/plugin-broken/AGENTS.md, tests/fixtures/grok/plugin-declarations/AGENTS.md, tests/fixtures/grok/project-broken/AGENTS.md, tests/fixtures/grok/project-clean/AGENTS.md, tests/fixtures/grok/project-monorepo/AGENTS.md, tests/fixtures/instructions/agents-import/diverged-pair/AGENTS.md, tests/fixtures/instructions/agents-import/diverged-pair/CLAUDE.md, tests/fixtures/instructions/agents-import/duplicated-pair/AGENTS.md, tests/fixtures/instructions/agents-import/duplicated-pair/CLAUDE.md, tests/fixtures/instructions/agents-import/generated-pair/AGENTS.md, tests/fixtures/instructions/agents-import/generated-pair/CLAUDE.md, tests/fixtures/instructions/agents-import/import-only/AGENTS.md, tests/fixtures/instructions/agents-import/import-only/CLAUDE.md, tests/fixtures/instructions/agents-import/import-plus-extras/AGENTS.md, tests/fixtures/instructions/agents-import/import-plus-extras/CLAUDE.md, tests/fixtures/muse/broken-groups/AGENTS.md, tests/fixtures/muse/broken/AGENTS.md, tests/fixtures/muse/clean/AGENTS.md, tests/fixtures/muse/dangerous-windows/AGENTS.md, tests/fixtures/muse/dangerous/AGENTS.md, tests/fixtures/muse/worktrees/.muse/worktrees/agent-1/AGENTS.md, tests/fixtures/muse/worktrees/AGENTS.md, tests/fixtures/opencode/broken/AGENTS.md, tests/fixtures/opencode/malformed-shapes/AGENTS.md, tests/fixtures/opencode/native-v1/AGENTS.md, tests/fixtures/opencode/native-v1/packages/worker/AGENTS.md, tests/fixtures/opencode/native-v2/AGENTS.md, tests/fixtures/opencode/unparseable/AGENTS.md, tests/fixtures/plugin-target-acme/CLAUDE.md, tests/fixtures/plugin-target/CLAUDE.md, tests/fixtures/promptfoo/nested-config/CLAUDE.md, tests/fixtures/regression/broken-ref-parentheses/AGENTS.md, tests/fixtures/regression/broken-ref-percent-encoding/CLAUDE.md, tests/fixtures/regression/broken-ref-query/AGENTS.md, tests/fixtures/regression/markdown-ast-anchor/CLAUDE.md, tests/fixtures/regression/markdown-ast-crossparagraph/CLAUDE.md, tests/fixtures/regression/markdown-ast-indented-code/CLAUDE.md, tests/fixtures/regression/markdown-ast-refdef/CLAUDE.md, tests/fixtures/regression/markdown-ast-substring/AGENTS.md, tests/fixtures/regression/markdown-ast-suppress-fence/CLAUDE.md, tests/fixtures/regression/markdown-ast-titled/CLAUDE.md, tests/fixtures/regression/settings-not-content/CLAUDE.md, tests/fixtures/root-mcp/broken/CLAUDE.md, tests/fixtures/root-mcp/clean/CLAUDE.md, tests/fixtures/root-mcp/invalid-json/CLAUDE.md, tests/fixtures/security/encoded-payload-data-uri/CLAUDE.md, tests/fixtures/security/encoded-payload-hex-ascii/CLAUDE.md, tests/fixtures/security/hidden-instructions-allowlist-bypass/CLAUDE.md, tests/fixtures/security/hidden-instructions-benign-maintenance/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-allowed/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-destination/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-duplicate/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-empty/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-fenced/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label/CLAUDE.md, tests/fixtures/security/hidden-instructions-reference-variants/CLAUDE.md, tests/fixtures/security/hidden-instructions-unterminated/CLAUDE.md, tests/fixtures/security/invisible-unicode-allowed-hex/CLAUDE.md, tests/fixtures/single-plugin/content-violations/CLAUDE.md, tests/fixtures/supply-chain-hooks/clean/CLAUDE.md, tests/fixtures/supply-chain-hooks/malicious/CLAUDE.md
15/15机器可读文档（llms.txt） — 项目网站提供 llms.txt（https://skillsaw.org/llms.txt）
33/40可读的提交历史 — 97 次人类提交中有 60 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_urlhttps://skillsaw.org/llms.txt
legible_history_share0.619
agent_instruction_files.agents/skills/skillsaw-maintenance/references/claude.md, .apm/skills/skillsaw-maintenance/references/claude.md, .claude/skills/skillsaw-maintenance/references/claude.md, .cursor/rules/development.mdc, .cursor/rules/python.mdc, .cursor/rules/testing.mdc, .github/copilot-instructions.md, .github/instructions/development.instructions.md, .github/instructions/python.instructions.md, .github/instructions/testing.instructions.md, AGENTS.md, docs/rules/claude.md, examples/plugins/skillsaw-example-plugin/tests/fixture/CLAUDE.md, src/skillsaw/marketplace/templates/claude-code/agent.md, tests/fixtures/agent-memory/notes/AGENTS.md, tests/fixtures/antigravity/codex-marketplace/AGENTS.md, tests/fixtures/antigravity/dual-manifest/AGENTS.md, tests/fixtures/antigravity/plugins-symlink/repo/AGENTS.md, tests/fixtures/antigravity/portable-manifest/AGENTS.md, tests/fixtures/antigravity/registry-entries/AGENTS.md, tests/fixtures/antigravity/registry-escape/repo/AGENTS.md, tests/fixtures/antigravity/shared-codex-hooks/AGENTS.md, tests/fixtures/antigravity/shared-cursor-hooks/AGENTS.md, tests/fixtures/antigravity/shared-hooks-file/AGENTS.md, tests/fixtures/antigravity/shared-plugin-hooks/AGENTS.md, tests/fixtures/antigravity/symlink-escape/repo/AGENTS.md, tests/fixtures/antigravity/workspace-broken/AGENTS.md, tests/fixtures/antigravity/workspace-clean/AGENTS.md, tests/fixtures/apm/broken/CLAUDE.md, tests/fixtures/apm/broken/GEMINI.md, tests/fixtures/apm/clean/.apm/instructions/CLAUDE.md, tests/fixtures/apm/hooks-clean/.apm/instructions/CLAUDE.md, tests/fixtures/apm/hooks-dangerous/.apm/instructions/CLAUDE.md, tests/fixtures/autofix/name-inline-comment/CLAUDE.md, tests/fixtures/autofix/name-multiline-scalar/CLAUDE.md, tests/fixtures/autofix/rename-refs-substring/CLAUDE.md, tests/fixtures/autofix/safe-idempotency/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-already-linked/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-backtick-paths/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-duplicate-paths/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-mixed/CLAUDE.md, tests/fixtures/autofix/unlinked-ref-multiple-paths/CLAUDE.md, tests/fixtures/codex/config-hooks-broken/AGENTS.md, tests/fixtures/codex/config-hooks-clean/AGENTS.md, tests/fixtures/codex/hooks-broken/AGENTS.md, tests/fixtures/codex/hooks-clean/AGENTS.md, tests/fixtures/codex/hooks-root-dangerous/AGENTS.md, tests/fixtures/codex/hooks-subpackage/AGENTS.md, tests/fixtures/codex/hooks-subpackage/services/billing/AGENTS.md, tests/fixtures/config/baseline-info/CLAUDE.md, tests/fixtures/config/baseline-test/CLAUDE.md, tests/fixtures/config/deprecated-rules/CLAUDE.md, tests/fixtures/config/exclude-conventional-skill-root/CLAUDE.md, tests/fixtures/config/opt-in-rules/CLAUDE.md, tests/fixtures/config/terminology-groups/AGENTS.md, tests/fixtures/config/terminology-groups/CLAUDE.md, tests/fixtures/content-unclosed-fence/skill-hides-violations/CLAUDE.md, tests/fixtures/content/banned-references-migration/CLAUDE.md, tests/fixtures/content/emphasis-density/CLAUDE.md, tests/fixtures/content/inconsistent-terminology-registers/AGENTS.md, tests/fixtures/content/inconsistent-terminology-registers/CLAUDE.md, tests/fixtures/content/inline-tool-examples/CLAUDE.md, tests/fixtures/content/instruction-drift/CLAUDE.md, tests/fixtures/content/mcp-tool-name-ambiguous/CLAUDE.md, tests/fixtures/content/mcp-tool-name-coderabbit/CLAUDE.md, tests/fixtures/content/mcp-tool-name-hook-prompt/AGENTS.md, tests/fixtures/content/mcp-tool-name/CLAUDE.md, tests/fixtures/content/progressive-disclosure/CLAUDE.md, tests/fixtures/content/repeated-directive-html-example/CLAUDE.md, tests/fixtures/content/repeated-directive/CLAUDE.md, tests/fixtures/content/terminology-distinct-concepts/AGENTS.md, tests/fixtures/content/unclosed-fence-coderabbit/CLAUDE.md, tests/fixtures/content/unlinked-reference-signal/CLAUDE.md, tests/fixtures/cursor-rules/broken-frontmatter/.cursorrules, tests/fixtures/cursor-rules/broken-frontmatter/AGENTS.md, tests/fixtures/cursor-rules/broken-hooks/AGENTS.md, tests/fixtures/cursor-rules/clean/AGENTS.md, tests/fixtures/cursor-rules/prompt-hooks/AGENTS.md, tests/fixtures/custom-rule-tree-example/CLAUDE.md, tests/fixtures/devin/valid/.windsurfrules, tests/fixtures/devin/valid/AGENT.md, tests/fixtures/devin/valid/apps/web/.windsurfrules, tests/fixtures/devin/valid/apps/web/CLAUDE.md, tests/fixtures/devin/valid/apps/web/agents.md, tests/fixtures/dot-claude/agents-imports-broken/AGENTS.md, tests/fixtures/dot-claude/agents-imports-clean/AGENTS.md, tests/fixtures/dot-claude/broken/CLAUDE.md, tests/fixtures/dot-claude/clean/CLAUDE.md, tests/fixtures/editor-tools/broken-mcp/AGENTS.md, tests/fixtures/editor-tools/monorepo/AGENTS.md, tests/fixtures/frontmatter-paths/CLAUDE.md, tests/fixtures/grok/config-broken/AGENTS.md, tests/fixtures/grok/config-clean/AGENTS.md, tests/fixtures/grok/marketplace-broken/AGENTS.md, tests/fixtures/grok/plugin-broken/AGENTS.md, tests/fixtures/grok/plugin-declarations/AGENTS.md, tests/fixtures/grok/project-broken/AGENTS.md, tests/fixtures/grok/project-clean/AGENTS.md, tests/fixtures/grok/project-monorepo/AGENTS.md, tests/fixtures/instructions/agents-import/diverged-pair/AGENTS.md, tests/fixtures/instructions/agents-import/diverged-pair/CLAUDE.md, tests/fixtures/instructions/agents-import/duplicated-pair/AGENTS.md, tests/fixtures/instructions/agents-import/duplicated-pair/CLAUDE.md, tests/fixtures/instructions/agents-import/generated-pair/AGENTS.md, tests/fixtures/instructions/agents-import/generated-pair/CLAUDE.md, tests/fixtures/instructions/agents-import/import-only/AGENTS.md, tests/fixtures/instructions/agents-import/import-only/CLAUDE.md, tests/fixtures/instructions/agents-import/import-plus-extras/AGENTS.md, tests/fixtures/instructions/agents-import/import-plus-extras/CLAUDE.md, tests/fixtures/muse/broken-groups/AGENTS.md, tests/fixtures/muse/broken/AGENTS.md, tests/fixtures/muse/clean/AGENTS.md, tests/fixtures/muse/dangerous-windows/AGENTS.md, tests/fixtures/muse/dangerous/AGENTS.md, tests/fixtures/muse/worktrees/.muse/worktrees/agent-1/AGENTS.md, tests/fixtures/muse/worktrees/AGENTS.md, tests/fixtures/opencode/broken/AGENTS.md, tests/fixtures/opencode/malformed-shapes/AGENTS.md, tests/fixtures/opencode/native-v1/AGENTS.md, tests/fixtures/opencode/native-v1/packages/worker/AGENTS.md, tests/fixtures/opencode/native-v2/AGENTS.md, tests/fixtures/opencode/unparseable/AGENTS.md, tests/fixtures/plugin-target-acme/CLAUDE.md, tests/fixtures/plugin-target/CLAUDE.md, tests/fixtures/promptfoo/nested-config/CLAUDE.md, tests/fixtures/regression/broken-ref-parentheses/AGENTS.md, tests/fixtures/regression/broken-ref-percent-encoding/CLAUDE.md, tests/fixtures/regression/broken-ref-query/AGENTS.md, tests/fixtures/regression/markdown-ast-anchor/CLAUDE.md, tests/fixtures/regression/markdown-ast-crossparagraph/CLAUDE.md, tests/fixtures/regression/markdown-ast-indented-code/CLAUDE.md, tests/fixtures/regression/markdown-ast-refdef/CLAUDE.md, tests/fixtures/regression/markdown-ast-substring/AGENTS.md, tests/fixtures/regression/markdown-ast-suppress-fence/CLAUDE.md, tests/fixtures/regression/markdown-ast-titled/CLAUDE.md, tests/fixtures/regression/settings-not-content/CLAUDE.md, tests/fixtures/root-mcp/broken/CLAUDE.md, tests/fixtures/root-mcp/clean/CLAUDE.md, tests/fixtures/root-mcp/invalid-json/CLAUDE.md, tests/fixtures/security/encoded-payload-data-uri/CLAUDE.md, tests/fixtures/security/encoded-payload-hex-ascii/CLAUDE.md, tests/fixtures/security/hidden-instructions-allowlist-bypass/CLAUDE.md, tests/fixtures/security/hidden-instructions-benign-maintenance/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-allowed/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-destination/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-duplicate/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-empty/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label-fenced/CLAUDE.md, tests/fixtures/security/hidden-instructions-link-label/CLAUDE.md, tests/fixtures/security/hidden-instructions-reference-variants/CLAUDE.md, tests/fixtures/security/hidden-instructions-unterminated/CLAUDE.md, tests/fixtures/security/invisible-unicode-allowed-hex/CLAUDE.md, tests/fixtures/single-plugin/content-violations/CLAUDE.md, tests/fixtures/supply-chain-hooks/clean/CLAUDE.md, tests/fixtures/supply-chain-hooks/malicious/CLAUDE.md
agent_instruction_max_bytes24,415

验证循环（构建 / 测试 / 类型检查）

85优秀
评分方式
18/18一条命令的引导启动 — Makefile, src/skillsaw/marketplace/templates/claude-code/makefile
22/22自动化测试
11/11Lint / 格式化配置 — pyproject.toml ([tool.black])
0/11静态类型检查
10/10可复现环境 — Dockerfile, lockfile
10/10已体现的代理实践 — 最近 100 次提交中有 6 次由代理编写或署名代理
8/8自动化维护 — 最近 100 次提交中有 2 次为自动依赖更新
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
lockfilespnpm-lock.yaml
has_dockerfile是
typed_language否
bootstrap_filesMakefile, src/skillsaw/marketplace/templates/claude-code/makefile
has_devcontainer否
has_linter_config是
typecheck_configs—
agent_commit_share0.06
toolchain_manifests—
dependency_bot_commit_share0.02

面向模型的代码可读性

54中等
评分方式
0/45可类型检查的代码 — Python，未配置类型检查
53.8/55可控的文件大小 — 采样的 536 个源文件中有 12 个超过 60KB
所用输入
primary_languagePython
largest_source_bytes489,893
source_files_sampled536
oversized_source_files12

机器可读接口

100卓越
评分方式
0/40API 模式（OpenAPI/GraphQL/proto） — 不适用于此类软件
20/20MCP 服务器
40/40可运行示例 — example, examples, recipes
所用输入
example_dirsexample, examples, recipes
has_mcp_signal是
api_schema_files—
interfaces_expected_of—
已排除计分（无数据或不适用）：API 模式（OpenAPI/GraphQL/proto）。 其余权重已重新归一化。

关键数据

67GitHub 星标
12贡献者
1,573最近 12 个月提交数
4距最近推送天数
36发布版本数
1巴士系数（bus factor）
3开放议题
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

更多细节

Star 与 Fork 历史 0 ★ / 15 ⇿
0Star
15Fork
27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。

03581013151522026-052026-072026-08
主版本 0次版本 12修订 15
OpenSSF Scorecard 6.8 / 10
6.8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 · 2026-10-21 09:58 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
10CI-Tests28 out of 28 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
4Code-ReviewFound 11/25 approved changesets -- score normalized to 4
10Contributorsproject has 15 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 22 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
6Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 6
10SASTSAST tool is run on all commits
4Security-Policysecurity policy file detected
不适用Signed-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
8Vulnerabilities2 existing vulnerabilities detected
直接依赖 8
注册表软件包版本约束清单文件
PyPIwcmatch>=10,<12pyproject.toml
PyPIpathspec>=1,<2pyproject.toml
PyPIPyYAML>=6.0pyproject.toml
PyPIruamel.yaml>=0.18pyproject.toml
PyPImarkdown-it-py>=3,<5pyproject.toml
PyPIjsonschema>=4.18,<5pyproject.toml
PyPIjson5>=0.12,<1pyproject.toml
PyPItomli>=2.0,<3pyproject.toml
全部依赖 23

来自 GitHub 依赖图的完整解析依赖集合：8 个直接依赖与 15 个间接（传递）软件包。仓库提交锁文件时，传递闭包才是完整的。

注册表软件包版本关系
PyPIjson5—直接
PyPIjsonschema—直接
PyPImarkdown-it-py—直接
PyPIpathspec—直接
PyPIpyyaml—直接
PyPIruamel-yaml—直接
PyPItomli—直接
PyPIwcmatch—直接
PyPIblack—间接
PyPIbuild—间接
PyPIcoverage—间接
PyPIflake8—间接
PyPImkdocs-material—间接
PyPImkdocs-redirects—间接
PyPImypy—间接
PyPIpre-commit—间接
PyPIpytest—间接
PyPIpytest-cov—间接
PyPIpytest-xdist—间接
PyPIsetuptools—间接
PyPIskillsaw—间接
PyPIskillsaw-runbooks0.1.0间接
PyPItwine—间接
依赖安全公告 0

安装 pypi:skillsaw@0.22.0 会引入 13 个包（直接与传递）：其中 0 个存在已知公告，0 个为直接依赖。

没有已知公告影响已评估的依赖。

公告表示依赖图中记录的版本落入某条公告的受影响范围。可达性未经分析，且依赖图包含开发与测试的版本固定——某项发现可能只涉及工具链而非交付的软件。

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 stbenjam/skillsaw 共享目录标签或生态系统的已检测仓库。 并排阅读 →

97Observal/ObservalObserval is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.卓越99awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions卓越96alpic-ai/skybridgeSkybridge is a full-stack TypeScript framework for MCP Apps and ChatGPT Apps. Type-safe. React-powered. Platform-agnostic.卓越96diegosouzapw/OmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors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98CherryHQ/cherry-studioAI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs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 — PyPI.