D
djenriquez/claude-plugins
Custom Claude Code plugins, skills, and agents
★ 3·更新 2026-11-19
在 GitHub 查看 ↗直链 · 无中转页
- ★ 数取值
- 3 ★ · djenriquez/claude-plugins · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
- 收录与活跃
- 收录于 2026-11-20 · 最近见到 2026-11-20 · 共见到 1 次 · 被 1 个来源列出
- 评分构成
- 综合分 103 · 3 ★ · 1 个来源 · repo
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: 开源项目。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
djenriquez/claude-plugins;我们收录于 2026-11-20;最近见到 2026-11-20。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。README 原文(英文,未翻译) · 在 GitHub 读完整 README →
# djenriquez agent plugins
以下摘录自该仓库的 README(片段)
Agent workflow plugins by @djenriquez, packaged for Claude Code and Codex (Cursor reads the same SKILL.md files).
## Installation
### Claude Code
/plugin marketplace add djenriquez/claude-plugins
/plugin install djenriquez-core
### Codex
Codex marketplace metadata lives at:
.agents/plugins/marketplace.json
The djenriquez-core entry points to:
./plugins/djenriquez-core
Install djenriquez-core from that Codex marketplace entry after this repository is available as a Codex plugin marketplace/source.
## Skills
Skills are invariant-focused orchestrators. Detailed mechanics live in plugin-root
protocols/ and references/ (siblings of skills/, never under a skill
directory).
### /write-spec
Human-first design spec: plain-language narrative plus an implementation
appendix. Also rewrites dense specs without dropping facts.
/write-spec
/write-spec add retry logic to webhook delivery
/write-spec docs/specs/existing-verbose-spec.md
Structure lives in references/spec-style.md. Required spec-narrative
humanizer on the narrative layer only (inline by default).
### /humanizer
Edits engineering text for a plain, concise voice: removes jargon, repeated
ideas, and canned phrasing while preserving facts and uncertainty. Forked from
abatilo-core:humanizer; prefer the local skill.
/humanizer pr-body
/humanizer review-comment
/humanizer
Modes: pr-body, review-comment, digest, spec-narrative, pr-reply,
ledger, narration, general. Callers apply the Process inline by default; nested
/humanizer is optional.
| Layer | Resource | When |
| Reporting tone | references/reporting-style.md | PR bodies, digests, ledgers, replies |
| AI cleanup | this skill + references/humanizer-patterns.md | Before publish/present |
| Procedure craft | /technical-writing | Runbooks, how-tos, READMEs, references |
| Caller | Mode |
| /pr-publish | pr-body |
| /pr-figure | pr-reply (comment body) |
| /code-review | review-comment (findings and synthesis) |
| /publish-review | review-comment |
| /write-spec | spec-narrative (narrative only) |
| /handle-pr-feedback | pr-reply |
| /audit-decisions | ledger |
| /audit-state-machines | digest |
| /guided-review | digest (explanations), review-comment (comment drafts) |
| /interactive-review | digest (graph prose and panel answers) |
| /lecture-video | narration |
### /technical-writing
Opt-in craft for docs a reader follows (runbooks, how-tos, API references). Not
for ordinary PR summaries. Pair with reporting-style and humanizer when needed.
### /spec-review
Risk-scaled specialist review → binary APPROVED / REVISIONS NEEDED.
/spec-review path/to/spec.md
/spec-review #42
/spec-review staged
L0: clarity + completeness. L1: selected specialists + targeted cross-review.
L2: all relevant specialists; optional debate only for judgment-sensitive
cases (always report debate status, including skips). Pass paths and section
anchors — not large pasted specs. Specialists load
protocols/review-protocol.md from the plugin root.
Specialists (add only when risk warrants): clarity, completeness, product,
feasibility, api, operations, scope, complexity, structure.
### /code-review
Lean staged review: generalist first, specialists only on evidence, debate only
## Installation
### Claude Code
/plugin marketplace add djenriquez/claude-plugins
/plugin install djenriquez-core
### Codex
Codex marketplace metadata lives at:
.agents/plugins/marketplace.json
The djenriquez-core entry points to:
./plugins/djenriquez-core
Install djenriquez-core from that Codex marketplace entry after this repository is available as a Codex plugin marketplace/source.
## Skills
Skills are invariant-focused orchestrators. Detailed mechanics live in plugin-root
protocols/ and references/ (siblings of skills/, never under a skill
directory).
### /write-spec
Human-first design spec: plain-language narrative plus an implementation
appendix. Also rewrites dense specs without dropping facts.
/write-spec
/write-spec add retry logic to webhook delivery
/write-spec docs/specs/existing-verbose-spec.md
Structure lives in references/spec-style.md. Required spec-narrative
humanizer on the narrative layer only (inline by default).
### /humanizer
Edits engineering text for a plain, concise voice: removes jargon, repeated
ideas, and canned phrasing while preserving facts and uncertainty. Forked from
abatilo-core:humanizer; prefer the local skill.
/humanizer pr-body
/humanizer review-comment
/humanizer
Modes: pr-body, review-comment, digest, spec-narrative, pr-reply,
ledger, narration, general. Callers apply the Process inline by default; nested
/humanizer is optional.
| Layer | Resource | When |
| Reporting tone | references/reporting-style.md | PR bodies, digests, ledgers, replies |
| AI cleanup | this skill + references/humanizer-patterns.md | Before publish/present |
| Procedure craft | /technical-writing | Runbooks, how-tos, READMEs, references |
| Caller | Mode |
| /pr-publish | pr-body |
| /pr-figure | pr-reply (comment body) |
| /code-review | review-comment (findings and synthesis) |
| /publish-review | review-comment |
| /write-spec | spec-narrative (narrative only) |
| /handle-pr-feedback | pr-reply |
| /audit-decisions | ledger |
| /audit-state-machines | digest |
| /guided-review | digest (explanations), review-comment (comment drafts) |
| /interactive-review | digest (graph prose and panel answers) |
| /lecture-video | narration |
### /technical-writing
Opt-in craft for docs a reader follows (runbooks, how-tos, API references). Not
for ordinary PR summaries. Pair with reporting-style and humanizer when needed.
### /spec-review
Risk-scaled specialist review → binary APPROVED / REVISIONS NEEDED.
/spec-review path/to/spec.md
/spec-review #42
/spec-review staged
L0: clarity + completeness. L1: selected specialists + targeted cross-review.
L2: all relevant specialists; optional debate only for judgment-sensitive
cases (always report debate status, including skips). Pass paths and section
anchors — not large pasted specs. Specialists load
protocols/review-protocol.md from the plugin root.
Specialists (add only when risk warrants): clarity, completeness, product,
feasibility, api, operations, scope, complexity, structure.
### /code-review
Lean staged review: generalist first, specialists only on evidence, debate only
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/djenriquez-claude-plugins/)
- 来源
- github · https://github.com/djenriquez/claude-plugins
- 按领域浏览
- 开源项目
- Traction
- 3 ★
- 收录于
- 今天
更多条目
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。