opencode-skills-collection 4.0.0 → 4.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/bundled-skills/.antigravity-install-manifest.json +28 -1
- package/bundled-skills/007/SKILL.md +2 -2
- package/bundled-skills/10-andruia-skill-smith/SKILL.md +1 -1
- package/bundled-skills/agent-squad/SKILL.md +5 -0
- package/bundled-skills/agent-squad/alex/SKILL.md +3 -0
- package/bundled-skills/agent-squad/aria/SKILL.md +3 -0
- package/bundled-skills/agent-squad/dep/SKILL.md +3 -0
- package/bundled-skills/agent-squad/luna/SKILL.md +4 -1
- package/bundled-skills/agent-squad/mason/SKILL.md +3 -0
- package/bundled-skills/agent-squad/max/SKILL.md +3 -0
- package/bundled-skills/agent-squad/quinn/SKILL.md +3 -0
- package/bundled-skills/agent-squad/rex/SKILL.md +3 -0
- package/bundled-skills/angular/metadata.json +1 -1
- package/bundled-skills/angular-best-practices/metadata.json +1 -1
- package/bundled-skills/angular-state-management/metadata.json +1 -1
- package/bundled-skills/angular-ui-patterns/metadata.json +1 -1
- package/bundled-skills/antigravity-skill-orchestrator/SKILL.md +2 -2
- package/bundled-skills/anywrite/SKILL.md +106 -0
- package/bundled-skills/apify-actor-development/SKILL.md +2 -2
- package/bundled-skills/apple-container/SKILL.md +165 -0
- package/bundled-skills/apple-container/references/commands.md +1593 -0
- package/bundled-skills/apple-container/references/concepts.md +294 -0
- package/bundled-skills/apple-container/references/configuration.md +499 -0
- package/bundled-skills/apple-container/references/workflows.md +498 -0
- package/bundled-skills/ask-copilot/SKILL.md +112 -0
- package/bundled-skills/auto-research/SKILL.md +126 -0
- package/bundled-skills/brooks-lint/SKILL.md +1 -1
- package/bundled-skills/browser-harness/references/install.md +3 -1
- package/bundled-skills/chrome-extension-developer/SKILL.md +1 -1
- package/bundled-skills/clean-code-guard/SKILL.md +184 -0
- package/bundled-skills/clean-code-guard/references/ai-failure-modes.md +345 -0
- package/bundled-skills/clean-code-guard/references/comments-and-formatting.md +115 -0
- package/bundled-skills/clean-code-guard/references/dry-kiss-yagni.md +133 -0
- package/bundled-skills/clean-code-guard/references/naming-and-functions.md +187 -0
- package/bundled-skills/clean-code-guard/references/review-checklist.md +150 -0
- package/bundled-skills/clean-code-guard/references/solid.md +280 -0
- package/bundled-skills/clean-code-guard/references/sources.md +47 -0
- package/bundled-skills/cloudflare-security-audit/SKILL.md +137 -0
- package/bundled-skills/cloudflare-security-audit/references/AI-AND-LLM.md +67 -0
- package/bundled-skills/cloudflare-security-audit/references/ATTACK-CLASSES.md +116 -0
- package/bundled-skills/cloudflare-security-audit/references/CLIENT-SIDE.md +67 -0
- package/bundled-skills/cloudflare-security-audit/references/HUNTING.md +110 -0
- package/bundled-skills/cloudflare-security-audit/references/MEMORY-SAFETY-AND-BINARY.md +58 -0
- package/bundled-skills/cloudflare-security-audit/references/RECONNAISSANCE.md +46 -0
- package/bundled-skills/cloudflare-security-audit/references/VALIDATION-AND-REPORTING.md +109 -0
- package/bundled-skills/cloudflare-security-audit/references/WEB-PROTOCOL-AND-AUTH.md +85 -0
- package/bundled-skills/cloudflare-security-audit/resources/report-schema.json +210 -0
- package/bundled-skills/comfyui-gateway/references/troubleshooting.md +1 -1
- package/bundled-skills/commit/SKILL.md +2 -1
- package/bundled-skills/deepapi/SKILL.md +6 -6
- package/bundled-skills/ditto/SKILL.md +173 -0
- package/bundled-skills/docs/README.md +1 -1
- package/bundled-skills/docs/contributors/quality-bar.md +1 -1
- package/bundled-skills/docs/contributors/security-guardrails.md +1 -1
- package/bundled-skills/docs/integrations/jetski-cortex.md +5 -5
- package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md +3 -3
- package/bundled-skills/docs/maintainers/ci-drift-fix.md +7 -5
- package/bundled-skills/docs/maintainers/merge-batch.md +24 -7
- package/bundled-skills/docs/maintainers/pr-autonomy.md +89 -0
- package/bundled-skills/docs/maintainers/release-notes-7.2.0.md +1 -1
- package/bundled-skills/docs/maintainers/release-process.md +9 -9
- package/bundled-skills/docs/maintainers/repo-growth-seo.md +5 -5
- package/bundled-skills/docs/maintainers/skills-date-tracking.md +1 -1
- package/bundled-skills/docs/maintainers/skills-update-guide.md +2 -2
- package/bundled-skills/docs/users/{antigravity-awesome-skills-vs-awesome-claude-skills.md → agentic-awesome-skills-vs-awesome-claude-skills.md} +5 -5
- package/bundled-skills/docs/users/ai-agent-skills.md +4 -4
- package/bundled-skills/docs/users/best-claude-code-skills-github.md +3 -3
- package/bundled-skills/docs/users/best-cursor-skills-github.md +3 -3
- package/bundled-skills/docs/users/bundles.md +56 -57
- package/bundled-skills/docs/users/claude-code-skills.md +6 -6
- package/bundled-skills/docs/users/codex-cli-skills.md +5 -5
- package/bundled-skills/docs/users/cursor-skills.md +3 -3
- package/bundled-skills/docs/users/faq.md +27 -15
- package/bundled-skills/docs/users/gemini-cli-skills.md +4 -4
- package/bundled-skills/docs/users/getting-started.md +22 -12
- package/bundled-skills/docs/users/kiro-integration.md +7 -7
- package/bundled-skills/docs/users/plugins.md +8 -9
- package/bundled-skills/docs/users/security-skills.md +1 -1
- package/bundled-skills/docs/users/skills-vs-mcp-tools.md +1 -1
- package/bundled-skills/docs/users/specialized-plugin-roadmap.md +3 -4
- package/bundled-skills/docs/users/usage.md +9 -9
- package/bundled-skills/docs/users/visual-guide.md +7 -7
- package/bundled-skills/docs/users/windows-truncation-recovery.md +1 -1
- package/bundled-skills/docs/users/workflows.md +1 -1
- package/bundled-skills/docs/vietnamese/BUNDLES.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/FAQ.vi.md +15 -8
- package/bundled-skills/docs/vietnamese/GETTING_STARTED.vi.md +12 -5
- package/bundled-skills/docs/vietnamese/QUALITY_BAR.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/README.vi.md +21 -17
- package/bundled-skills/docs/vietnamese/SECURITY_GUARDRAILS.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/SKILLS_README.vi.md +2 -2
- package/bundled-skills/docs/vietnamese/TRANSLATION_PLAN.vi.md +1 -1
- package/bundled-skills/docs/vietnamese/VISUAL_GUIDE.vi.md +8 -8
- package/bundled-skills/docs-guard/SKILL.md +109 -0
- package/bundled-skills/docs-guard/references/code-samples.md +46 -0
- package/bundled-skills/docs-guard/references/docstrings.md +60 -0
- package/bundled-skills/docs-guard/references/review-checklist.md +45 -0
- package/bundled-skills/docs-guard/references/sources.md +22 -0
- package/bundled-skills/docs-guard/references/verification.md +51 -0
- package/bundled-skills/efficient-web-research/SKILL.md +4 -0
- package/bundled-skills/electron-development/SKILL.md +1 -1
- package/bundled-skills/event-staffing-compliance/SKILL.md +3 -0
- package/bundled-skills/event-staffing-ordering/SKILL.md +3 -0
- package/bundled-skills/feature-tracking/SKILL.md +222 -0
- package/bundled-skills/flutter-expert/SKILL.md +6 -1
- package/bundled-skills/flutter-expert/resources/implementation-playbook.md +214 -0
- package/bundled-skills/gemini-deep-research/README.md +246 -0
- package/bundled-skills/gemini-deep-research/SKILL.md +136 -0
- package/bundled-skills/gemini-deep-research/requirements.txt +2 -0
- package/bundled-skills/gemini-deep-research/scripts/research.py +692 -0
- package/bundled-skills/git-pushing/SKILL.md +21 -4
- package/bundled-skills/git-pushing/scripts/smart_commit.sh +206 -11
- package/bundled-skills/go-in-depth/scripts/workflow-script.js +4 -1
- package/bundled-skills/grok-build/SKILL.md +167 -0
- package/bundled-skills/grok-build/references/cli.md +99 -0
- package/bundled-skills/huggingface-tool-builder/references/find_models_by_paper.sh +1 -1
- package/bundled-skills/idea-autopsy/SKILL.md +147 -0
- package/bundled-skills/it-manager-hospital/README.md +1 -1
- package/bundled-skills/it-manager-pro/README.md +1 -1
- package/bundled-skills/itil-expert/README.md +1 -1
- package/bundled-skills/langgraph/SKILL.md +1 -1
- package/bundled-skills/linkedin-content-generator/SKILL.md +1 -1
- package/bundled-skills/lint-and-validate/scripts/lint_runner.py +23 -23
- package/bundled-skills/lint-and-validate/scripts/type_coverage.py +30 -30
- package/bundled-skills/logic-lens/SKILL.md +1 -1
- package/bundled-skills/lore/LICENSE +21 -0
- package/bundled-skills/lore/README.md +386 -0
- package/bundled-skills/lore/README.zh-CN.md +386 -0
- package/bundled-skills/lore/SKILL.md +453 -0
- package/bundled-skills/lore/WORKFLOWS.md +216 -0
- package/bundled-skills/lore/WORKFLOWS.zh-CN.md +216 -0
- package/bundled-skills/lore/references/audit-template.md +60 -0
- package/bundled-skills/lore/references/compatibility.md +228 -0
- package/bundled-skills/lore/references/config.md +125 -0
- package/bundled-skills/lore/references/entry-format.md +70 -0
- package/bundled-skills/lore/references/history-command.md +106 -0
- package/bundled-skills/lore/references/monorepo-detection.md +78 -0
- package/bundled-skills/lore/references/platform-mirrors.md +377 -0
- package/bundled-skills/lore/references/stale-new-markers.md +62 -0
- package/bundled-skills/lore/references/summary-template.md +98 -0
- package/bundled-skills/lore/scripts/README.md +54 -0
- package/bundled-skills/lore/scripts/README.zh-CN.md +54 -0
- package/bundled-skills/lore/scripts/find_duplicates.py +211 -0
- package/bundled-skills/lore/scripts/find_stale.py +116 -0
- package/bundled-skills/lore/scripts/history.py +527 -0
- package/bundled-skills/lore/scripts/id_hash.py +32 -0
- package/bundled-skills/lore/scripts/list_entries.py +183 -0
- package/bundled-skills/lovable-cleanup/SKILL.md +3 -3
- package/bundled-skills/makepad-splash/SKILL.md +1 -1
- package/bundled-skills/mmx-cli/SKILL.md +14 -1
- package/bundled-skills/monopoly/SKILL.md +5 -0
- package/bundled-skills/monopoly/patterns/SKILL.md +4 -0
- package/bundled-skills/monopoly/scale-benchmarks/SKILL.md +4 -0
- package/bundled-skills/monopoly/security-checklist/SKILL.md +4 -0
- package/bundled-skills/monopoly/tech-matrix/SKILL.md +4 -0
- package/bundled-skills/mtls-configuration/SKILL.md +1 -1
- package/bundled-skills/network-101/SKILL.md +4 -5
- package/bundled-skills/nika/SKILL.md +270 -0
- package/bundled-skills/not-a-vibe-coder/SKILL.md +4 -0
- package/bundled-skills/ontoly-software-graph/SKILL.md +160 -0
- package/bundled-skills/openclaw-github-repo-commander/SKILL.md +1 -1
- package/bundled-skills/optim-agent/SKILL.md +78 -0
- package/bundled-skills/pilot-protocol/SKILL.md +6 -3
- package/bundled-skills/postgres-readonly-queries/README.md +77 -0
- package/bundled-skills/postgres-readonly-queries/SKILL.md +152 -0
- package/bundled-skills/postgres-readonly-queries/connections.example.json +34 -0
- package/bundled-skills/postgres-readonly-queries/requirements.txt +1 -0
- package/bundled-skills/postgres-readonly-queries/scripts/query.py +262 -0
- package/bundled-skills/pptx-deck-creation/SKILL.md +275 -0
- package/bundled-skills/pptx-deck-creation/references/audit-checklist.md +156 -0
- package/bundled-skills/pptx-deck-creation/references/design-profiles.md +96 -0
- package/bundled-skills/pptx-deck-creation/references/python-snippets.md +150 -0
- package/bundled-skills/pptx-deck-creation/references/reference-deck-analysis.md +91 -0
- package/bundled-skills/pptx-deck-creation/references/visual-asset-adapters.md +158 -0
- package/bundled-skills/privilege-escalation-methods/SKILL.md +1 -1
- package/bundled-skills/product-decision-agent/SKILL.md +94 -0
- package/bundled-skills/product-decision-agent/agents/openai.yaml +7 -0
- package/bundled-skills/product-decision-agent/references/methodology-basis.md +232 -0
- package/bundled-skills/product-decision-agent/references/product-playbooks.md +813 -0
- package/bundled-skills/product-decision-agent/references/reasoning-engine.md +289 -0
- package/bundled-skills/product-decision-agent/references/response-examples.md +279 -0
- package/bundled-skills/product-decision-agent/scripts/quality_gate.py +221 -0
- package/bundled-skills/product-decision-agent/scripts/test_quality_gate.py +94 -0
- package/bundled-skills/pytest-skill/reference/playbook.md +358 -0
- package/bundled-skills/quit-sponsor/SKILL.md +96 -0
- package/bundled-skills/rclone-cli/references/providers/s3.md +1 -1
- package/bundled-skills/security-and-hardening/SKILL.md +1 -1
- package/bundled-skills/semgrep-rule-creator/SKILL.md +6 -6
- package/bundled-skills/skill-creator/README.md +3 -3
- package/bundled-skills/skill-creator/SKILL.md +8 -4
- package/bundled-skills/skill-creator/scripts/quick_validate.py +1 -1
- package/bundled-skills/sql-injection-testing/SKILL.md +4 -4
- package/bundled-skills/sshepherd/SKILL.md +107 -0
- package/bundled-skills/subagent-orchestrator/README.md +1 -1
- package/bundled-skills/super-code/bash/SKILL.md +3 -0
- package/bundled-skills/super-code/c/SKILL.md +3 -0
- package/bundled-skills/super-code/cpp/SKILL.md +3 -0
- package/bundled-skills/super-code/csharp/SKILL.md +3 -0
- package/bundled-skills/super-code/dart/SKILL.md +3 -0
- package/bundled-skills/super-code/elixir/SKILL.md +3 -0
- package/bundled-skills/super-code/go/SKILL.md +3 -0
- package/bundled-skills/super-code/java/SKILL.md +3 -0
- package/bundled-skills/super-code/kotlin/SKILL.md +3 -0
- package/bundled-skills/super-code/php/SKILL.md +3 -0
- package/bundled-skills/super-code/python/SKILL.md +3 -0
- package/bundled-skills/super-code/ruby/SKILL.md +3 -0
- package/bundled-skills/super-code/rust/SKILL.md +3 -0
- package/bundled-skills/super-code/scala/SKILL.md +3 -0
- package/bundled-skills/super-code/swift/SKILL.md +3 -0
- package/bundled-skills/super-code/typescript/SKILL.md +3 -0
- package/bundled-skills/telegram-bot-messaging/README.md +185 -0
- package/bundled-skills/telegram-bot-messaging/SKILL.md +101 -0
- package/bundled-skills/telegram-bot-messaging/scripts/telegram.sh +420 -0
- package/bundled-skills/test-guard/SKILL.md +132 -0
- package/bundled-skills/test-guard/references/jest.md +50 -0
- package/bundled-skills/test-guard/references/llm-app-testing.md +40 -0
- package/bundled-skills/test-guard/references/phpunit.md +56 -0
- package/bundled-skills/test-guard/references/pytest.md +65 -0
- package/bundled-skills/trading-ledger/SKILL.md +11 -3
- package/bundled-skills/uizze-ui-research/SKILL.md +93 -0
- package/bundled-skills/vibe-code-auditor/SKILL.md +1 -1
- package/bundled-skills/vibecode-production-qa-validator/SKILL.md +1 -1
- package/bundled-skills/videodb/scripts/ws_listener.py +29 -15
- package/bundled-skills/voice-ai-engine-development/README.md +1 -1
- package/bundled-skills/vulnerability-scanner/SKILL.md +1 -1
- package/bundled-skills/warehouse/SKILL.md +154 -0
- package/bundled-skills/woo-guard/SKILL.md +113 -0
- package/bundled-skills/woo-guard/references/checkout-and-money.md +64 -0
- package/bundled-skills/woo-guard/references/hpos-and-crud.md +87 -0
- package/bundled-skills/woo-guard/references/review-checklist.md +44 -0
- package/bundled-skills/woo-guard/references/sources.md +17 -0
- package/bundled-skills/wp-guard/SKILL.md +119 -0
- package/bundled-skills/wp-guard/references/i18n.md +88 -0
- package/bundled-skills/wp-guard/references/performance.md +70 -0
- package/bundled-skills/wp-guard/references/review-checklist.md +57 -0
- package/bundled-skills/wp-guard/references/security.md +100 -0
- package/bundled-skills/wp-guard/references/sources.md +27 -0
- package/bundled-skills/writing-skills/gotchas.md +1 -1
- package/bundled-skills/writing-skills/references/standards/metadata-standard.md +1 -1
- package/bundled-skills/x-twitter-scraper/SKILL.md +14 -32
- package/bundled-skills/xss-html-injection/SKILL.md +3 -3
- package/bundled-skills/youtube-seo-optimizer/SKILL.md +1 -1
- package/bundled-skills/youtube-summarizer/CHANGELOG.md +2 -2
- package/package.json +2 -2
- package/skills_index.json +407 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# ❓ Câu hỏi thường gặp (FAQ)
|
|
2
2
|
|
|
3
|
-
**Bạn có thắc mắc?** Bạn không hề cô đơn! Dưới đây là câu trả lời cho những câu hỏi thường gặp nhất về
|
|
3
|
+
**Bạn có thắc mắc?** Bạn không hề cô đơn! Dưới đây là câu trả lời cho những câu hỏi thường gặp nhất về Agentic Awesome Skills.
|
|
4
4
|
|
|
5
5
|
---
|
|
6
6
|
|
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
Skills là các tệp hướng dẫn chuyên biệt dạy cho các trợ lý AI cách xử lý những tác vụ cụ thể. Hãy coi chúng như những mô-đun kiến thức chuyên gia mà AI của bạn có thể tải khi cần.
|
|
12
12
|
**Một so sánh đơn giản:** Giống như việc bạn tham khảo ý kiến của các chuyên gia khác nhau (luật sư, bác sĩ, thợ máy), những kỹ năng này giúp AI của bạn trở thành chuyên gia trong các lĩnh vực khác nhau khi bạn cần.
|
|
13
13
|
|
|
14
|
-
### Tôi có cần phải cài đặt tất cả hơn 1,
|
|
14
|
+
### Tôi có cần phải cài đặt tất cả hơn 1,936 skills không?
|
|
15
15
|
|
|
16
16
|
**Không!** Khi bạn cài đặt repository này, tất cả các kỹ năng đều có sẵn, nhưng AI của bạn chỉ tải chúng khi bạn yêu cầu rõ ràng bằng lệnh `@ten-skill`.
|
|
17
17
|
Nó giống như việc sở hữu một thư viện - tất cả sách đều ở đó, nhưng bạn chỉ đọc những cuốn bạn cần thôi.
|
|
@@ -25,7 +25,14 @@ Nó giống như việc sở hữu một thư viện - tất cả sách đều
|
|
|
25
25
|
- ✅ **Cursor** (IDE tích hợp AI)
|
|
26
26
|
- ✅ **Antigravity IDE**
|
|
27
27
|
- ✅ **OpenCode**
|
|
28
|
-
-
|
|
28
|
+
- 🧪 **GitHub Copilot** (hỗ trợ preview qua GitHub CLI `gh skill`)
|
|
29
|
+
|
|
30
|
+
Với Copilot, `gh skill` hiện vẫn ở trạng thái preview. Repository lớn này có cả bản canonical và bản mirror trong plugin, vì vậy hãy dùng đường dẫn chính xác; chỉ dùng `--all` khi bạn thực sự muốn cài mọi bản được phát hiện:
|
|
31
|
+
|
|
32
|
+
```bash
|
|
33
|
+
gh skill preview sickn33/agentic-awesome-skills skills/brainstorming/SKILL.md
|
|
34
|
+
gh skill install sickn33/agentic-awesome-skills skills/brainstorming/SKILL.md --agent github-copilot --scope user --pin v14.2.0
|
|
35
|
+
```
|
|
29
36
|
|
|
30
37
|
### Những kỹ năng này có được sử dụng miễn phí không?
|
|
31
38
|
|
|
@@ -67,7 +74,7 @@ _Luôn kiểm tra nhãn rủi ro và xem xét mã nguồn trước khi dùng._
|
|
|
67
74
|
Đường dẫn mặc định của installer là `~/.agents/skills/` cho Antigravity global:
|
|
68
75
|
|
|
69
76
|
```bash
|
|
70
|
-
npx
|
|
77
|
+
npx agentic-awesome-skills
|
|
71
78
|
```
|
|
72
79
|
|
|
73
80
|
**Các đường dẫn cụ thể cho từng công cụ:**
|
|
@@ -87,7 +94,7 @@ npx antigravity-awesome-skills
|
|
|
87
94
|
**Có.** Hãy dùng lệnh cài đặt chuẩn:
|
|
88
95
|
|
|
89
96
|
```bash
|
|
90
|
-
npx
|
|
97
|
+
npx agentic-awesome-skills
|
|
91
98
|
```
|
|
92
99
|
|
|
93
100
|
Không còn cần workaround cũ `core.symlinks=true` hoặc bật Developer Mode chỉ để cài repository này.
|
|
@@ -97,7 +104,7 @@ Không còn cần workaround cũ `core.symlinks=true` hoặc bật Developer Mod
|
|
|
97
104
|
Chạy lại installer để lấy phiên bản mới nhất, hoặc nếu bạn cài bằng git clone thì pull trong thư mục đã clone:
|
|
98
105
|
|
|
99
106
|
```bash
|
|
100
|
-
npx
|
|
107
|
+
npx agentic-awesome-skills
|
|
101
108
|
|
|
102
109
|
# hoặc, nếu bạn tự clone repository:
|
|
103
110
|
cd ~/.agents/skills
|
|
@@ -144,7 +151,7 @@ Sử dụng biểu tượng `@` theo sau là tên skill:
|
|
|
144
151
|
|
|
145
152
|
### Một kỹ năng đưa ra lời khuyên sai hoặc lỗi thời
|
|
146
153
|
|
|
147
|
-
Hãy [Mở một issue](https://github.com/sickn33/
|
|
154
|
+
Hãy [Mở một issue](https://github.com/sickn33/agentic-awesome-skills/issues)!
|
|
148
155
|
Vui lòng gửi kèm:
|
|
149
156
|
|
|
150
157
|
- Skill nào?
|
|
@@ -185,4 +192,4 @@ Hãy chạy `npm run validate` cục bộ để kiểm tra trước khi đẩy c
|
|
|
185
192
|
- Thử `@test-driven-development` để code có chất lượng tốt hơn.
|
|
186
193
|
- Khám phá `@skill-creator` để tự tạo kỹ năng của riêng bạn.
|
|
187
194
|
|
|
188
|
-
**Vẫn còn thắc mắc?** [Mở một cuộc thảo luận (Discussion)](https://github.com/sickn33/
|
|
195
|
+
**Vẫn còn thắc mắc?** [Mở một cuộc thảo luận (Discussion)](https://github.com/sickn33/agentic-awesome-skills/discussions) và chúng tôi sẽ giúp bạn! 🙌
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
# Hướng dẫn Bắt đầu với
|
|
1
|
+
# Hướng dẫn Bắt đầu với Agentic Awesome Skills (V14.0.0)
|
|
2
2
|
|
|
3
3
|
**Bạn mới đến đây? Hướng dẫn này sẽ giúp bạn tăng cường sức mạnh cho trợ lý trợ lý AI của mình chỉ trong 5 phút.**
|
|
4
4
|
|
|
@@ -15,7 +15,7 @@ Các trợ lý AI (như **Claude Code**, **Codex CLI**, **Gemini CLI**, **Cursor
|
|
|
15
15
|
|
|
16
16
|
## ⚡️ Khởi động nhanh: Các "Gói khởi đầu" (Starter Packs)
|
|
17
17
|
|
|
18
|
-
Đừng lo lắng về con số hơn 1,
|
|
18
|
+
Đừng lo lắng về con số hơn 1,936 kỹ năng. Bạn không cần dùng tất cả chúng cùng một lúc.
|
|
19
19
|
Chúng tôi đã tuyển chọn các **Gói khởi đầu** để bạn có thể bắt đầu sử dụng ngay lập tức.
|
|
20
20
|
|
|
21
21
|
### 1. Cài đặt Repository
|
|
@@ -23,7 +23,7 @@ Chúng tôi đã tuyển chọn các **Gói khởi đầu** để bạn có th
|
|
|
23
23
|
Khuyến nghị dùng installer CLI. Mặc định, lệnh này cài vào `~/.agents/skills` cho Antigravity global:
|
|
24
24
|
|
|
25
25
|
```bash
|
|
26
|
-
npx
|
|
26
|
+
npx agentic-awesome-skills
|
|
27
27
|
```
|
|
28
28
|
|
|
29
29
|
Bạn cũng có thể dùng cờ theo công cụ, ví dụ `--claude`, `--gemini`, `--codex`, `--cursor`, `--kiro`, `--antigravity`, `--agy`, hoặc `--path <dir>` để chọn thư mục đích.
|
|
@@ -78,7 +78,14 @@ Sau khi cài đặt, bạn chỉ cần trò chuyện với AI một cách tự n
|
|
|
78
78
|
| **Cursor** | ✅ Hỗ trợ gốc | `.cursor/skills/` |
|
|
79
79
|
| **OpenCode** | ✅ Hỗ trợ đầy đủ | `.agents/skills/` |
|
|
80
80
|
| **AdaL CLI** | ✅ Hỗ trợ đầy đủ | `.adal/skills/` |
|
|
81
|
-
| **Copilot** |
|
|
81
|
+
| **Copilot** | 🧪 Hỗ trợ preview qua `gh skill` | Dùng GitHub CLI với đường dẫn skill chính xác |
|
|
82
|
+
|
|
83
|
+
> **GitHub Copilot (preview):** `gh skill` hiện vẫn ở trạng thái preview. Vì repository lớn này có cả bản canonical và bản mirror trong plugin, hãy dùng đường dẫn chính xác để tránh nhầm lẫn; chỉ dùng `--all` khi bạn thực sự muốn cài mọi bản được phát hiện:
|
|
84
|
+
>
|
|
85
|
+
> ```bash
|
|
86
|
+
> gh skill preview sickn33/agentic-awesome-skills skills/brainstorming/SKILL.md
|
|
87
|
+
> gh skill install sickn33/agentic-awesome-skills skills/brainstorming/SKILL.md --agent github-copilot --scope user --pin v14.2.0
|
|
88
|
+
> ```
|
|
82
89
|
|
|
83
90
|
---
|
|
84
91
|
|
|
@@ -98,7 +105,7 @@ _Kiểm tra [Danh mục Skill (Skill Catalog)](../../CATALOG.md) để xem danh
|
|
|
98
105
|
|
|
99
106
|
## ❓ FAQ
|
|
100
107
|
|
|
101
|
-
**H: Tôi có cần cài đặt tất cả 1,
|
|
108
|
+
**H: Tôi có cần cài đặt tất cả 1,936+ kỹ năng không?**
|
|
102
109
|
Đ: Bạn tải toàn bộ repo về, nhưng AI của bạn chỉ _đọc_ những kỹ năng bạn yêu cầu (hoặc những kỹ năng có liên quan). Nó rất nhẹ!
|
|
103
110
|
|
|
104
111
|
**H: Tôi có thể tự tạo kỹ năng cho riêng mình không?**
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# 🏆 Tiêu chuẩn Chất lượng & Xác thực
|
|
2
2
|
|
|
3
|
-
Để biến **
|
|
3
|
+
Để biến **Agentic Awesome Skills** từ một tập hợp các script thành một nền tảng đáng tin cậy, mỗi skill (kỹ năng) phải đáp ứng một tiêu chuẩn cụ thể về chất lượng và an toàn.
|
|
4
4
|
|
|
5
5
|
## Huy hiệu "Đã xác thực" (Validated) ✅
|
|
6
6
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
|
-
# 🌌
|
|
1
|
+
# 🌌 Agentic Awesome Skills: 1,936+ Kỹ năng (Skills) cho Claude Code, Gemini CLI, Cursor, Copilot và nhiều hơn nữa
|
|
2
2
|
|
|
3
|
-
> **Thư viện GitHub có thể cài đặt gồm hơn 1,
|
|
3
|
+
> **Thư viện GitHub có thể cài đặt gồm hơn 1,936 kỹ năng agentic cho Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity và các trợ lý lập trình AI khác.**
|
|
4
4
|
|
|
5
5
|
[](https://opensource.org/licenses/MIT)
|
|
6
6
|
[](https://claude.ai)
|
|
@@ -9,9 +9,9 @@
|
|
|
9
9
|
[](https://cursor.sh)
|
|
10
10
|
[](https://github.com/features/copilot)
|
|
11
11
|
[](https://github.com/opencode-ai/opencode)
|
|
12
|
-
[](https://github.com/sickn33/
|
|
12
|
+
[](https://github.com/sickn33/agentic-awesome-skills)
|
|
13
13
|
|
|
14
|
-
**
|
|
14
|
+
**Agentic Awesome Skills** là một thư viện kỹ năng có thể cài đặt với **1,936+ kỹ năng `SKILL.md`** được thiết kế để hoạt động mượt mà trên các trợ lý lập trình AI lớn:
|
|
15
15
|
|
|
16
16
|
- 🟣 **Claude Code** (Anthropic CLI)
|
|
17
17
|
- 🔵 **Gemini CLI** (Google DeepMind)
|
|
@@ -22,17 +22,15 @@
|
|
|
22
22
|
- ⚪ **OpenCode** (Mã nguồn mở CLI)
|
|
23
23
|
- 🟡 **Kiro CLI / IDE** và **AdaL CLI**
|
|
24
24
|
|
|
25
|
-
**Phiên bản hiện tại:
|
|
25
|
+
**Phiên bản hiện tại: V14.0.0.** Đây không chỉ là một danh sách prompt; repository này cung cấp kỹ năng, bundles, workflows, catalog sinh tự động và installer CLI để dùng lại các playbook đã được kiểm chứng.
|
|
26
26
|
|
|
27
27
|
### 1. 🐣 Bối cảnh: Đây là gì?
|
|
28
28
|
|
|
29
|
-
**
|
|
29
|
+
**Agentic Awesome Skills** (Phiên bản 14.0.0) là một thư viện kỹ năng lớn cho AI coding assistants.
|
|
30
30
|
|
|
31
31
|
Các trợ lý AI (như Claude Code, Cursor, hoặc Gemini) rất thông minh, nhưng chúng thiếu các **công cụ chuyên biệt**. Chúng không biết "Quy trình Triển khai" của công ty bạn hoặc cú pháp cụ thể cho "AWS CloudFormation".
|
|
32
32
|
**Skills** là các tệp markdown nhỏ dạy cho chúng cách thực hiện những tác vụ cụ thể này một cách chính xác trong mọi lần thực thi.
|
|
33
|
-
...
|
|
34
33
|
Repository này cung cấp các kỹ năng thiết yếu để biến trợ lý AI của bạn thành một **đội ngũ chuyên gia số toàn năng**, bao gồm các khả năng chính thức từ **Anthropic**, **OpenAI**, **Google**, **Supabase**, **Apify**, và **Vercel Labs**.
|
|
35
|
-
...
|
|
36
34
|
Cho dù bạn đang sử dụng **Gemini CLI**, **Claude Code**, **Codex CLI**, **Cursor**, **GitHub Copilot**, **Antigravity**, hay **OpenCode**, những kỹ năng này được thiết kế để có thể sử dụng ngay lập tức và tăng cường sức mạnh cho trợ lý AI của bạn.
|
|
37
35
|
|
|
38
36
|
Repository này tập hợp những khả năng tốt nhất từ khắp cộng đồng mã nguồn mở, biến trợ lý AI của bạn thành một đội ngũ chuyên gia số toàn năng có khả năng Kỹ thuật, Thiết kế, Bảo mật, Marketing và Vận hành Tự động.
|
|
@@ -57,7 +55,7 @@ Repository được tổ chức thành các lĩnh vực chuyên biệt để bi
|
|
|
57
55
|
|
|
58
56
|
[Xem các Gói khởi đầu tại docs/vietnamese/BUNDLES.md](BUNDLES.vi.md) để tìm bộ công cụ hoàn hảo cho vai trò của bạn.
|
|
59
57
|
|
|
60
|
-
## Duyệt hơn 1,
|
|
58
|
+
## Duyệt hơn 1,936 Kỹ năng
|
|
61
59
|
|
|
62
60
|
Chúng tôi đã chuyển danh sách đầy đủ các kỹ năng sang một danh mục riêng biệt để giữ cho file README này gọn gàng.
|
|
63
61
|
|
|
@@ -68,15 +66,15 @@ Chúng tôi đã chuyển danh sách đầy đủ các kỹ năng sang một dan
|
|
|
68
66
|
Để sử dụng các kỹ năng này với **Claude Code**, **Gemini CLI**, **Codex CLI**, **Cursor**, **Antigravity**, **Kiro**, **OpenCode** hoặc **AdaL**, hãy dùng installer CLI:
|
|
69
67
|
|
|
70
68
|
```bash
|
|
71
|
-
npx
|
|
69
|
+
npx agentic-awesome-skills
|
|
72
70
|
|
|
73
71
|
# Ví dụ theo công cụ:
|
|
74
|
-
npx
|
|
75
|
-
npx
|
|
76
|
-
npx
|
|
77
|
-
npx
|
|
78
|
-
npx
|
|
79
|
-
npx
|
|
72
|
+
npx agentic-awesome-skills --claude
|
|
73
|
+
npx agentic-awesome-skills --gemini
|
|
74
|
+
npx agentic-awesome-skills --codex
|
|
75
|
+
npx agentic-awesome-skills --cursor
|
|
76
|
+
npx agentic-awesome-skills --kiro
|
|
77
|
+
npx agentic-awesome-skills --agy
|
|
80
78
|
```
|
|
81
79
|
|
|
82
80
|
---
|
|
@@ -186,4 +184,10 @@ Chúng tôi chính thức cảm ơn những người đóng góp sau đây đã
|
|
|
186
184
|
|
|
187
185
|
## Lịch sử Star
|
|
188
186
|
|
|
189
|
-
|
|
187
|
+
<a href="https://www.star-history.com/?repos=sickn33%2Fagentic-awesome-skills&type=date&legend=top-left">
|
|
188
|
+
<picture>
|
|
189
|
+
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/chart?repos=sickn33/agentic-awesome-skills&type=date&theme=dark&legend=top-left&sealed_token=5UEckOplDlF6KsKi881R_B44YTNBEFj0fRwovC_U0W2Um19HD9wLMQXclNblk6wFKgeGn0RzW0rGZkVCqzoKxaGB3IMaiN8tP8yqLRbhs6lf-kO3KeJWjftxgtV1zdrTVHjfEYfnevKZuYFww2_H2vC8IlXgfaTdNinFb3MD9CcMlu44hpLYu2iABkYy" />
|
|
190
|
+
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/chart?repos=sickn33/agentic-awesome-skills&type=date&legend=top-left&sealed_token=5UEckOplDlF6KsKi881R_B44YTNBEFj0fRwovC_U0W2Um19HD9wLMQXclNblk6wFKgeGn0RzW0rGZkVCqzoKxaGB3IMaiN8tP8yqLRbhs6lf-kO3KeJWjftxgtV1zdrTVHjfEYfnevKZuYFww2_H2vC8IlXgfaTdNinFb3MD9CcMlu44hpLYu2iABkYy" />
|
|
191
|
+
<img alt="Star History Chart" src="https://api.star-history.com/chart?repos=sickn33/agentic-awesome-skills&type=date&legend=top-left&sealed_token=5UEckOplDlF6KsKi881R_B44YTNBEFj0fRwovC_U0W2Um19HD9wLMQXclNblk6wFKgeGn0RzW0rGZkVCqzoKxaGB3IMaiN8tP8yqLRbhs6lf-kO3KeJWjftxgtV1zdrTVHjfEYfnevKZuYFww2_H2vC8IlXgfaTdNinFb3MD9CcMlu44hpLYu2iABkYy" />
|
|
192
|
+
</picture>
|
|
193
|
+
</a>
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# 🛡️ Chính sách Bảo mật & Rào chắn An toàn (Guardrails)
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
Agentic Awesome Skills là một bộ công cụ mạnh mẽ. Và quyền lực lớn luôn đi kèm với trách nhiệm lớn. Tài liệu này xác định **Quy tắc Ứng xử** cho tất cả các khả năng bảo mật và tấn công trong repository này.
|
|
4
4
|
|
|
5
5
|
## 🔴 Chính sách đối với Skill Tấn công (Vạch kẻ đỏ)
|
|
6
6
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Thư mục Kỹ năng (Skills Directory)
|
|
2
2
|
|
|
3
|
-
**Chào mừng đến với thư mục Kỹ năng!** Đây là nơi tập hợp tất cả 1,
|
|
3
|
+
**Chào mừng đến với thư mục Kỹ năng!** Đây là nơi tập hợp tất cả 1,936+ kỹ năng AI chuyên biệt.
|
|
4
4
|
|
|
5
5
|
## 🤔 Kỹ năng là gì?
|
|
6
6
|
|
|
@@ -63,7 +63,7 @@ ls skills/ | grep "từ khóa"
|
|
|
63
63
|
```
|
|
64
64
|
|
|
65
65
|
### Cách 3: Kiểm tra README chính
|
|
66
|
-
Xem [README chính](README.vi.md) và [CATALOG.md](../../CATALOG.md) để biết danh sách đầy đủ tất cả 1,
|
|
66
|
+
Xem [README chính](README.vi.md) và [CATALOG.md](../../CATALOG.md) để biết danh sách đầy đủ tất cả 1,936+ kỹ năng được tổ chức theo danh mục.
|
|
67
67
|
|
|
68
68
|
---
|
|
69
69
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# 🗺️ Kế hoạch Dịch thuật (Translation Master Plan)
|
|
2
2
|
|
|
3
|
-
Tài liệu này dùng để theo dõi tiến độ dịch thuật toàn bộ repository `
|
|
3
|
+
Tài liệu này dùng để theo dõi tiến độ dịch thuật toàn bộ repository `agentic-awesome-skills` sang tiếng Việt.
|
|
4
4
|
|
|
5
5
|
**Mục tiêu:** Dịch toàn bộ 1,684+ kỹ năng và tài liệu hướng dẫn.
|
|
6
6
|
**Quy tắc:**
|
|
@@ -28,12 +28,12 @@
|
|
|
28
28
|
## 📦 Cấu trúc Repository (Trực quan)
|
|
29
29
|
|
|
30
30
|
```
|
|
31
|
-
|
|
31
|
+
agentic-awesome-skills/
|
|
32
32
|
│
|
|
33
33
|
├── 📄 README.md ← Tổng quan & danh sách skill
|
|
34
34
|
├── 📄 CONTRIBUTING.md ← Cách thức đóng góp
|
|
35
35
|
│
|
|
36
|
-
├── 📁 skills/ ← Nguồn canonical cho 1,
|
|
36
|
+
├── 📁 skills/ ← Nguồn canonical cho 1,936+ skills
|
|
37
37
|
│ │
|
|
38
38
|
│ ├── 📁 brainstorming/
|
|
39
39
|
│ │ └── 📄 SKILL.md ← Định nghĩa skill
|
|
@@ -42,7 +42,7 @@ antigravity-awesome-skills/
|
|
|
42
42
|
│ │ ├── 📄 SKILL.md
|
|
43
43
|
│ │ └── 📁 examples/ ← Các phần bổ sung tùy chọn
|
|
44
44
|
│ │
|
|
45
|
-
│ └── ... (1,
|
|
45
|
+
│ └── ... (1,936+ skills khác)
|
|
46
46
|
│
|
|
47
47
|
├── 📁 tools/
|
|
48
48
|
│ ├── 📁 scripts/ ← Quản lý, xác thực và tạo catalog
|
|
@@ -67,7 +67,7 @@ antigravity-awesome-skills/
|
|
|
67
67
|
|
|
68
68
|
```
|
|
69
69
|
┌──────────────┐
|
|
70
|
-
│ 1. CÀI ĐẶT │ npx
|
|
70
|
+
│ 1. CÀI ĐẶT │ npx agentic-awesome-skills
|
|
71
71
|
1 └──────┬───────┘
|
|
72
72
|
│
|
|
73
73
|
↓
|
|
@@ -97,7 +97,7 @@ antigravity-awesome-skills/
|
|
|
97
97
|
|
|
98
98
|
```
|
|
99
99
|
┌─────────────────────────┐
|
|
100
|
-
│ 1,
|
|
100
|
+
│ 1,936+ AWESOME SKILLS │
|
|
101
101
|
└────────────┬────────────┘
|
|
102
102
|
│
|
|
103
103
|
┌────────────────────────┼────────────────────────┐
|
|
@@ -181,7 +181,7 @@ antigravity-awesome-skills/
|
|
|
181
181
|
┌─────────────────────────────────────────┐
|
|
182
182
|
│ Terminal │
|
|
183
183
|
├─────────────────────────────────────────┤
|
|
184
|
-
│ $ npx
|
|
184
|
+
│ $ npx agentic-awesome-skills │
|
|
185
185
|
│ │
|
|
186
186
|
│ ✓ Cài vào '~/.agents/skills'... │
|
|
187
187
|
│ ✓ Hoàn tất! │
|
|
@@ -199,7 +199,7 @@ antigravity-awesome-skills/
|
|
|
199
199
|
│ ├── 📁 brainstorming/ │
|
|
200
200
|
│ ├── 📁 stripe-integration/ │
|
|
201
201
|
│ ├── 📁 react-best-practices/ │
|
|
202
|
-
│ └── ... (1,
|
|
202
|
+
│ └── ... (1,936+ skills) │
|
|
203
203
|
└─────────────────────────────────────────┘
|
|
204
204
|
```
|
|
205
205
|
|
|
@@ -436,7 +436,7 @@ BẮT ĐẦU TẠI ĐÂY
|
|
|
436
436
|
├─────────────────────────────────────────────────────────────┤
|
|
437
437
|
│ │
|
|
438
438
|
│ 📥 CÀI ĐẶT │
|
|
439
|
-
│ npx
|
|
439
|
+
│ npx agentic-awesome-skills │
|
|
440
440
|
│ │
|
|
441
441
|
│ 🎯 SỬ DỤNG │
|
|
442
442
|
│ @ten-skill [yêu cầu của bạn] │
|
|
@@ -0,0 +1,109 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: "docs-guard"
|
|
3
|
+
description: "Review generated or changed documentation before it ships, including READMEs, API references, docstrings, changelogs, tutorials, and documentation sites."
|
|
4
|
+
risk: "critical"
|
|
5
|
+
source: "community"
|
|
6
|
+
source_repo: "amElnagdy/guard-skills"
|
|
7
|
+
source_type: "community"
|
|
8
|
+
date_added: 2026-07-13
|
|
9
|
+
author: "community"
|
|
10
|
+
tags: []
|
|
11
|
+
tools: []
|
|
12
|
+
---
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
# Docs Guard
|
|
16
|
+
|
|
17
|
+
You are reviewing generated or changed documentation before it ships. Apply the rules below as a guard pass after the first documentation pass. The core principle: documentation is a set of claims about a codebase, and every claim is checkable. Your job is to check them.
|
|
18
|
+
|
|
19
|
+
These rules exist because AI agents document from memory of how APIs *usually* look, not from the code in front of them. Published research: half of AI answers to programming questions contain incorrect information, and models produce valid invocations for infrequent APIs barely a third of the time — yet the prose sounds authoritative either way. Readers cannot tell verified docs from hallucinated docs. You can, because you have the source.
|
|
20
|
+
|
|
21
|
+
## When to Use
|
|
22
|
+
|
|
23
|
+
Use this skill when reviewing generated or changed documentation before it ships. Activate it reactively after an agent writes or updates READMEs, API references, docstrings, PHPDoc/JSDoc, changelogs, tutorials, or doc sites.
|
|
24
|
+
|
|
25
|
+
## How to use this skill
|
|
26
|
+
|
|
27
|
+
**Guard-pass mode** (recommended): after documentation or docstrings have been generated or edited, verify every claim against the source and run the self-check before delivery.
|
|
28
|
+
|
|
29
|
+
**Live mode** (explicit): when the user invokes this skill before writing docs, verify before you write — read the actual implementation, then document what it does. Run the self-check before delivery.
|
|
30
|
+
|
|
31
|
+
**Review mode** (the user asks you to review, audit, or fact-check docs): walk [references/review-checklist.md](references/review-checklist.md) against the target docs and produce a findings report with file:line evidence. Do not rewrite in review mode unless asked.
|
|
32
|
+
|
|
33
|
+
## Adapt to the project first
|
|
34
|
+
|
|
35
|
+
1. Read the project's agent instructions (CLAUDE.md, AGENTS.md) and any docs style guide. Project conventions win on conflict.
|
|
36
|
+
2. Identify the docs surfaces that must move together: README, reference docs, docstrings, changelog, examples, config samples. A change to one usually owes a change to others (Rule 6).
|
|
37
|
+
3. Note the documented version policy: which versions does the project support, and where are features version-tagged?
|
|
38
|
+
|
|
39
|
+
## The Rules
|
|
40
|
+
|
|
41
|
+
### Accuracy — must fix
|
|
42
|
+
|
|
43
|
+
1. **Every referenced symbol must exist.** Every function, method, class, hook, CLI command, flag, endpoint, config key, env var, and file path mentioned in the docs gets verified against the actual source, CLI help output, route table, or schema — by reading it, not recalling it. The verification procedure is in [references/verification.md](references/verification.md). An unverifiable reference does not ship.
|
|
44
|
+
|
|
45
|
+
2. **Every code sample must work.** Imports resolve, APIs exist with the documented signatures (names, argument order, defaults, return shape), and the sample runs outside the author's machine — no hardcoded local paths, no real credentials, no implicit prior state. Sample rules: [references/code-samples.md](references/code-samples.md).
|
|
46
|
+
|
|
47
|
+
3. **Document the code's actual behavior, not its intended behavior.** Read the implementation before describing it. Where code and comments/specs disagree, the code is the truth — and flag the disagreement to the user instead of silently picking a side.
|
|
48
|
+
|
|
49
|
+
4. **No unverifiable claims.** Performance numbers, compatibility matrices, scale limits, and "production-ready" assertions require a source in the repository (benchmark script, CI matrix, changelog entry) or they come out. "Fast" is marketing; "O(n log n), benchmarked in bench/sort.md" is documentation.
|
|
50
|
+
|
|
51
|
+
### Versioning and drift
|
|
52
|
+
|
|
53
|
+
5. **Versions are explicit.** Features, flags, and behaviors state the version that introduced them when the project tracks versions. Prerequisites are pinned or ranged, never "latest". Deprecated items say so, with the replacement.
|
|
54
|
+
|
|
55
|
+
6. **A code change owes a docs change.** When editing code whose behavior is documented — rename, signature change, new default, removed flag — update every doc surface that mentions it in the same change. Grep the docs for the old symbol before finishing.
|
|
56
|
+
|
|
57
|
+
### Substance — should fix
|
|
58
|
+
|
|
59
|
+
7. **No filler, no slop.** Delete: docstrings that paraphrase the signature ("Gets the user by ID" above `get_user_by_id`), sections that restate their heading, marketing adjectives in technical prose ("powerful", "seamless", "blazingly fast"), and intro padding ("In this section, we will explore…"). A docstring earns its place by adding contracts the signature cannot express: units, ranges, error conditions, side effects, threading/ordering guarantees.
|
|
60
|
+
|
|
61
|
+
8. **Don't paraphrase upstream docs.** Link to external documentation instead of restating it — paraphrased upstream docs drift the moment upstream changes. Document only your project's relationship to the external thing (which subset you use, what you configure differently).
|
|
62
|
+
|
|
63
|
+
9. **Examples cover the failure path too.** A tutorial that only shows the happy path documents half the API. Show what the error looks like and what the caller should do — using the error types the code actually raises (verify per Rule 1).
|
|
64
|
+
|
|
65
|
+
### Structure — worth noting
|
|
66
|
+
|
|
67
|
+
10. **Navigation tells the truth.** Headings describe their sections, the table of contents matches the actual headings, internal links and anchors resolve, and there are no TODO stubs or "coming soon" sections in published docs — unwritten sections are removed, not promised.
|
|
68
|
+
|
|
69
|
+
## Self-check before delivery
|
|
70
|
+
|
|
71
|
+
1. List every symbol, flag, endpoint, config key, and path your docs mention. Did you verify each one against the source in this session — not from memory?
|
|
72
|
+
2. Would every code sample run on a clean machine? Did you check each import and signature?
|
|
73
|
+
3. Any number, compatibility claim, or superlative without a repo-verifiable source?
|
|
74
|
+
4. If this change touched code: did you grep all docs surfaces for the old names?
|
|
75
|
+
5. Any docstring that just restates the signature? Any section that restates its heading?
|
|
76
|
+
6. Do all internal links and anchors resolve?
|
|
77
|
+
|
|
78
|
+
If any answer is wrong, fix it before showing the user.
|
|
79
|
+
|
|
80
|
+
## Reporting format (review mode)
|
|
81
|
+
|
|
82
|
+
```
|
|
83
|
+
**Rule N violation** in `docs/path.md:<line or section>`
|
|
84
|
+
- Claim: <what the docs say>
|
|
85
|
+
- Reality: <what the code/CLI/schema actually has, with file:line>
|
|
86
|
+
- Fix: <one sentence>
|
|
87
|
+
```
|
|
88
|
+
|
|
89
|
+
Lead with Rule 1–4 findings (false claims), then drift, then substance. If a doc is clean, say so in one line — accuracy deserves credit.
|
|
90
|
+
|
|
91
|
+
## Severity guide
|
|
92
|
+
|
|
93
|
+
- **Must fix:** Rules 1–4 — false documentation is worse than no documentation; readers act on it
|
|
94
|
+
- **Should fix:** Rules 5–9 — drift debt and noise that buries the signal
|
|
95
|
+
- **Worth noting:** Rule 10 — navigation and polish
|
|
96
|
+
|
|
97
|
+
## References
|
|
98
|
+
|
|
99
|
+
- [references/verification.md](references/verification.md) — the mechanical procedure: extracting claims, verifying symbols, signatures, CLI flags, endpoints, config keys, links
|
|
100
|
+
- [references/code-samples.md](references/code-samples.md) — what makes a sample shippable: runnability, realistic data, secrets hygiene, error paths
|
|
101
|
+
- [references/docstrings.md](references/docstrings.md) — docstring/PHPDoc/JSDoc-specific rules: when one is justified, what it must contain, paraphrase detection
|
|
102
|
+
- [references/review-checklist.md](references/review-checklist.md) — structured walk-through for review mode
|
|
103
|
+
- [references/sources.md](references/sources.md) — research and style-guide URLs; read only when citing a source
|
|
104
|
+
|
|
105
|
+
## What this skill does not do
|
|
106
|
+
|
|
107
|
+
- Review the code itself — clean-code-guard's jurisdiction. This skill reviews what the docs *claim about* the code.
|
|
108
|
+
- Generate documentation strategy or information architecture from scratch — it guards accuracy and substance, not scope decisions.
|
|
109
|
+
- Enforce a prose style guide — tone belongs to the project; truth belongs to this skill.
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
# Docs Guard — Code Sample Rules
|
|
2
|
+
|
|
3
|
+
A code sample is the most-trusted part of any documentation: readers paste it. That trust makes a broken sample worse than no sample.
|
|
4
|
+
|
|
5
|
+
## Contents
|
|
6
|
+
|
|
7
|
+
- Shippable sample checklist
|
|
8
|
+
- Realistic data
|
|
9
|
+
- Secrets and credentials
|
|
10
|
+
- Error-path examples
|
|
11
|
+
- Language and environment tags
|
|
12
|
+
- Sample drift
|
|
13
|
+
|
|
14
|
+
## Shippable sample checklist
|
|
15
|
+
|
|
16
|
+
Every sample must pass all of these:
|
|
17
|
+
|
|
18
|
+
1. **Imports resolve** — every import/require/use names a real module at the documented version.
|
|
19
|
+
2. **APIs are real** — every call verified per [verification.md](verification.md): name, argument order, defaults, return shape.
|
|
20
|
+
3. **Self-contained or explicit** — runs on a clean machine, or states its prerequisites immediately above the block ("requires the client from the previous step").
|
|
21
|
+
4. **No local residue** — no `/Users/yourname/`, no `C:\Dev\`, no machine-specific ports or hostnames; use placeholder conventions the project already uses.
|
|
22
|
+
5. **Syntactically valid** — parse it mentally line by line; when the runtime allows, actually run or lint it.
|
|
23
|
+
6. **Output shown is output produced** — if the sample shows a result, that result must be what the code yields, not an idealized version.
|
|
24
|
+
|
|
25
|
+
## Realistic data
|
|
26
|
+
|
|
27
|
+
Use data that exposes the API's shape honestly: realistic field names, plausible values, at least one non-ASCII string where text handling matters. `foo`/`bar` hides bugs that `"Café Münster"` reveals — especially for the i18n-aware audience.
|
|
28
|
+
|
|
29
|
+
## Secrets and credentials
|
|
30
|
+
|
|
31
|
+
- Placeholders that cannot be mistaken for real values: `YOUR_API_KEY`, `example.com`, RFC 5737 IPs (`192.0.2.x`), `sk_test_…` style markers only when the provider defines them.
|
|
32
|
+
- Never paste real-looking tokens — even invented ones train readers to paste theirs, and secret scanners will flag the repo.
|
|
33
|
+
- Auth setup goes in one place and is linked, not repeated with variations in every sample.
|
|
34
|
+
|
|
35
|
+
## Error-path examples
|
|
36
|
+
|
|
37
|
+
For any API that can fail in normal operation, show one failure: what the error object/exception/status looks like and the minimal correct response to it — using the error types the code actually raises (verify the raise site). Happy-path-only documentation produces catch-all error swallowing downstream, the exact failure clean-code-guard exists to stop.
|
|
38
|
+
|
|
39
|
+
## Language and environment tags
|
|
40
|
+
|
|
41
|
+
- Fenced blocks carry the correct language tag — broken highlighting is a trust signal readers notice.
|
|
42
|
+
- State the environment when it changes behavior: shell prompts (`$` vs `#`), OS-specific paths, version-gated syntax.
|
|
43
|
+
|
|
44
|
+
## Sample drift
|
|
45
|
+
|
|
46
|
+
Samples drift faster than prose because nobody re-runs them. On any code change touching a documented API, grep the docs for the old symbol (SKILL.md Rule 6) — samples are where the stale hits hide. Projects with executable-docs tooling (doctest and kin): prefer it; this skill's manual verification is the floor, not the ceiling.
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
# Docs Guard — Docstring, PHPDoc, and JSDoc Rules
|
|
2
|
+
|
|
3
|
+
In-code documentation has one extra constraint the other surfaces lack: it sits next to the truth. There is no excuse for a docstring that disagrees with the signature three lines below it.
|
|
4
|
+
|
|
5
|
+
## Contents
|
|
6
|
+
|
|
7
|
+
- When a docstring is justified
|
|
8
|
+
- The paraphrase test
|
|
9
|
+
- What a good docstring contains
|
|
10
|
+
- Tag accuracy (PHPDoc/JSDoc)
|
|
11
|
+
- Generated-docs hygiene
|
|
12
|
+
|
|
13
|
+
## When a docstring is justified
|
|
14
|
+
|
|
15
|
+
- Public API surface: always — it feeds IDEs, generated references, and agents.
|
|
16
|
+
- Internal helpers: only when the contract is not expressible in the signature (units, invariants, side effects, "why"). An internal one-liner with an intention-revealing name usually needs nothing — and clean-code-guard's comment rules apply.
|
|
17
|
+
|
|
18
|
+
## The paraphrase test
|
|
19
|
+
|
|
20
|
+
Delete any docstring whose entire information content is recoverable from the signature:
|
|
21
|
+
|
|
22
|
+
```php
|
|
23
|
+
// Fails the test — restates the obvious, documents nothing.
|
|
24
|
+
/**
|
|
25
|
+
* Gets the user by ID.
|
|
26
|
+
*
|
|
27
|
+
* @param int $user_id The user ID.
|
|
28
|
+
* @return WP_User The user.
|
|
29
|
+
*/
|
|
30
|
+
function get_user_by_id( $user_id ) { /* … */ }
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
AI generators emit these by the thousand; they are comment pollution wearing a suit. Either say something the signature cannot, or say nothing.
|
|
34
|
+
|
|
35
|
+
## What a good docstring contains
|
|
36
|
+
|
|
37
|
+
The contract the types cannot express:
|
|
38
|
+
|
|
39
|
+
- Units and ranges (`$timeout` in seconds? milliseconds? what happens at 0?)
|
|
40
|
+
- Error behavior: which exceptions/returns on failure, and when (verify the raise/return sites)
|
|
41
|
+
- Side effects: writes, cache invalidation, events fired, global state touched
|
|
42
|
+
- Null/empty semantics: what `null` means here, what an empty array does
|
|
43
|
+
- Ordering, idempotency, concurrency guarantees when callers depend on them
|
|
44
|
+
- The "why" for surprising design ("returns 1.0 on API failure so prices never disappear")
|
|
45
|
+
|
|
46
|
+
## Tag accuracy (PHPDoc/JSDoc)
|
|
47
|
+
|
|
48
|
+
- `@param` names and order match the signature exactly — drift here actively lies to IDEs.
|
|
49
|
+
- `@param` and `@return` types match the real types, including nullability (`int|WP_Error`, `?string`) and generics where the project uses them.
|
|
50
|
+
- `@throws` lists what the body actually throws — verify each raise site; remove what no longer throws.
|
|
51
|
+
- `@since` matches the changelog/tag where the project versions its API.
|
|
52
|
+
- `@deprecated` always names the replacement.
|
|
53
|
+
|
|
54
|
+
## Generated-docs hygiene
|
|
55
|
+
|
|
56
|
+
When docstrings feed a generated reference (phpDocumentor, JSDoc, Sphinx, TypeDoc):
|
|
57
|
+
|
|
58
|
+
- A wrong docstring becomes a published wrong reference page — Rule 1 severity applies as if it were the README.
|
|
59
|
+
- Check that examples inside docstrings obey [code-samples.md](code-samples.md) — they are the least-reviewed samples in any codebase.
|
|
60
|
+
- Markup must be valid for the generator in use; broken tags silently truncate published pages.
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
# Docs Guard — Review Checklist
|
|
2
|
+
|
|
3
|
+
Structured walk for review mode. Findings first, file:line evidence always. Priorities: false claims → drift → substance → navigation.
|
|
4
|
+
|
|
5
|
+
## Contents
|
|
6
|
+
|
|
7
|
+
- Pass 1: Claim verification
|
|
8
|
+
- Pass 2: Code samples
|
|
9
|
+
- Pass 3: Drift scan
|
|
10
|
+
- Pass 4: Substance
|
|
11
|
+
- Pass 5: Navigation
|
|
12
|
+
- Reporting
|
|
13
|
+
|
|
14
|
+
## Pass 1: Claim verification (must fix)
|
|
15
|
+
|
|
16
|
+
Run the full procedure in [verification.md](verification.md):
|
|
17
|
+
|
|
18
|
+
- Extract every symbol, flag, endpoint, config key, path, version, and behavioral claim.
|
|
19
|
+
- Verify each against its source of truth (definition site, parser, route table, changelog).
|
|
20
|
+
- Every unverified or contradicted claim is a Rule 1/3 finding with the contradicting file:line.
|
|
21
|
+
- Numbers and superlatives without a repo source are Rule 4 findings.
|
|
22
|
+
|
|
23
|
+
## Pass 2: Code samples (must fix)
|
|
24
|
+
|
|
25
|
+
For every fenced block, run the [code-samples.md](code-samples.md) checklist: imports, signatures, self-containment, local residue, secrets, shown output. Samples in docstrings count.
|
|
26
|
+
|
|
27
|
+
## Pass 3: Drift scan (should fix)
|
|
28
|
+
|
|
29
|
+
- Take the public API surface (or the diff, when reviewing a change) and grep the docs for renamed/removed symbols, old defaults, and dead flags.
|
|
30
|
+
- Check the changelog mentions what the docs claim is new, and versions agree (Rule 5).
|
|
31
|
+
- Cross-surface consistency: README vs reference vs docstrings vs config samples — one claim per fact, surfaces agreeing (Rule 6).
|
|
32
|
+
|
|
33
|
+
## Pass 4: Substance (should fix)
|
|
34
|
+
|
|
35
|
+
- Paraphrase docstrings, heading-restating sections, marketing adjectives, intro padding (Rule 7).
|
|
36
|
+
- Paraphrased upstream documentation that should be a link (Rule 8).
|
|
37
|
+
- Happy-path-only tutorials and API examples (Rule 9).
|
|
38
|
+
|
|
39
|
+
## Pass 5: Navigation (worth noting)
|
|
40
|
+
|
|
41
|
+
- TOC vs actual headings; internal links and anchors resolve; no TODO stubs or "coming soon" in published docs (Rule 10).
|
|
42
|
+
|
|
43
|
+
## Reporting
|
|
44
|
+
|
|
45
|
+
Use the SKILL.md reporting format (Claim / Reality / Fix). Lead with the count: "N claims checked, M false, K unverifiable." End with a verdict — publish / fix first / do not publish — and at most three things the docs do well. A review that verifies 40 claims and finds 2 false is a *good* result; say so.
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
# Docs Guard — Sources
|
|
2
|
+
|
|
3
|
+
Central bibliography. Operational guidance lives in the other references; read this file only when a source URL is needed.
|
|
4
|
+
|
|
5
|
+
## Contents
|
|
6
|
+
|
|
7
|
+
- Research on AI-generated documentation defects
|
|
8
|
+
- Documentation craft references
|
|
9
|
+
|
|
10
|
+
## Research on AI-generated documentation defects
|
|
11
|
+
|
|
12
|
+
- Kabir et al., "Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions", CHI 2024 — 52% of answers contained incorrect information; evaluators missed AI errors 39% of the time: https://dl.acm.org/doi/10.1145/3613904.3642596
|
|
13
|
+
- CloudAPIBench, "On Mitigating Code LLM Hallucinations with API Documentation" (AWS, 2024) — 38.58% valid invocations for low-frequency APIs: https://arxiv.org/abs/2407.09726
|
|
14
|
+
- De-Hallucinator (2024) — LLMs routinely invent non-existent APIs; project-API grounding fixed 63.2% of hallucination-caused failures: https://arxiv.org/abs/2401.01701
|
|
15
|
+
- Spracklen et al., "We Have a Package for You!" (USENIX Security 2025) — package hallucination averages 19.6% across 16 models: https://www.usenix.org/conference/usenixsecurity25/presentation/spracklen
|
|
16
|
+
|
|
17
|
+
## Documentation craft references
|
|
18
|
+
|
|
19
|
+
- Diátaxis — the four documentation modes (tutorial, how-to, reference, explanation): https://diataxis.fr/
|
|
20
|
+
- Write the Docs — style guide collection: https://www.writethedocs.org/guide/writing/style-guides/
|
|
21
|
+
- RFC 5737 — IPv4 address blocks reserved for documentation: https://www.rfc-editor.org/rfc/rfc5737
|
|
22
|
+
- Google developer documentation style guide: https://developers.google.com/style
|