opencode-skills-collection 4.0.42 → 4.0.43

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.
Files changed (41) hide show
  1. package/bundled-skills/.antigravity-install-manifest.json +3 -1
  2. package/bundled-skills/docs/integrations/jetski-cortex.md +3 -3
  3. package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md +1 -1
  4. package/bundled-skills/docs/maintainers/repo-growth-seo.md +1 -1
  5. package/bundled-skills/docs/maintainers/skills-update-guide.md +1 -1
  6. package/bundled-skills/docs/users/aas-core.md +1 -1
  7. package/bundled-skills/docs/users/bundles.md +1 -1
  8. package/bundled-skills/docs/users/claude-code-skills.md +1 -1
  9. package/bundled-skills/docs/users/gemini-cli-skills.md +1 -1
  10. package/bundled-skills/docs/users/kiro-integration.md +1 -1
  11. package/bundled-skills/docs/users/usage.md +3 -3
  12. package/bundled-skills/docs/users/visual-guide.md +4 -4
  13. package/bundled-skills/lore/SKILL.md +104 -298
  14. package/bundled-skills/lore/references/audit-template.md +21 -4
  15. package/bundled-skills/lore/references/compatibility.md +51 -121
  16. package/bundled-skills/lore/references/config.md +22 -23
  17. package/bundled-skills/lore/references/entry-format.md +33 -3
  18. package/bundled-skills/lore/references/history-command.md +98 -2
  19. package/bundled-skills/lore/references/platform-mirrors.md +45 -16
  20. package/bundled-skills/lore/references/stale-new-markers.md +10 -8
  21. package/bundled-skills/lore/references/summary-template.md +8 -1
  22. package/bundled-skills/lore/references/workflows.md +192 -0
  23. package/bundled-skills/lore/scripts/README.md +14 -13
  24. package/bundled-skills/lore/scripts/README.zh-CN.md +14 -13
  25. package/bundled-skills/lore/scripts/find_duplicates.py +14 -4
  26. package/bundled-skills/lore/scripts/find_stale.py +68 -16
  27. package/bundled-skills/lore/scripts/history.py +235 -23
  28. package/bundled-skills/lore/scripts/id_hash.py +7 -4
  29. package/bundled-skills/lore/scripts/list_entries.py +82 -13
  30. package/bundled-skills/poka-yoke/SKILL.md +172 -0
  31. package/bundled-skills/project-state-governor/SKILL.md +1 -1
  32. package/bundled-skills/project-state-governor/references/project-state-schema.md +1 -1
  33. package/bundled-skills/spec-driven-loop/SKILL.md +203 -0
  34. package/bundled-skills/spec-driven-loop/references/agent-and-judge-contracts.md +120 -0
  35. package/bundled-skills/spec-driven-loop/references/document-templates.md +184 -0
  36. package/package.json +1 -1
  37. package/skills_index.json +67 -1
  38. package/bundled-skills/lore/README.md +0 -386
  39. package/bundled-skills/lore/README.zh-CN.md +0 -386
  40. package/bundled-skills/lore/WORKFLOWS.md +0 -216
  41. package/bundled-skills/lore/WORKFLOWS.zh-CN.md +0 -216
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "schemaVersion": 1,
3
- "updatedAt": "2026-08-25T00:33:41.568Z",
3
+ "updatedAt": "2026-08-26T00:34:21.858Z",
4
4
  "entries": [
5
5
  "00-andruia-consultant",
6
6
  "007",
@@ -1412,6 +1412,7 @@
1412
1412
  "playwright-skill",
1413
1413
  "plotly",
1414
1414
  "podcast-generation",
1415
+ "poka-yoke",
1415
1416
  "polars",
1416
1417
  "polis-protocol",
1417
1418
  "polis-protocol-a-self-optimizing-city-of-agents",
@@ -1709,6 +1710,7 @@
1709
1710
  "source-driven-development",
1710
1711
  "spark-optimization",
1711
1712
  "spec-driven-development",
1713
+ "spec-driven-loop",
1712
1714
  "spec-to-code-compliance",
1713
1715
  "speckit-updater",
1714
1716
  "speed",
@@ -1,9 +1,9 @@
1
1
  ---
2
2
  title: Jetski/Cortex + Gemini Integration Guide
3
- description: "Use agentic-awesome-skills with Jetski/Cortex without hitting context-window overflow with 2,026+ skills."
3
+ description: "Use agentic-awesome-skills with Jetski/Cortex without hitting context-window overflow with 2,028+ skills."
4
4
  ---
5
5
 
6
- # Jetski/Cortex + Gemini: safe integration with 2,026+ skills
6
+ # Jetski/Cortex + Gemini: safe integration with 2,028+ skills
7
7
 
8
8
  > **Custom-host integration:** This guide documents a low-level, direct-manifest lazy loader for Jetski/Cortex and similar hosts. For Codex or Claude Code, the recommended path is [AAS Core](../users/aas-core.md), which provides neutral, deterministic catalog retrieval and validates exact agent-selected IDs through a bounded, read-only MCP server.
9
9
 
@@ -25,7 +25,7 @@ Never do:
25
25
  - concatenate all `SKILL.md` content into a single system prompt;
26
26
  - re-inject the entire library for **every** request.
27
27
 
28
- With 2,026+ skills, this approach fills the context window before user messages are even added, causing truncation.
28
+ With 2,028+ skills, this approach fills the context window before user messages are even added, causing truncation.
29
29
 
30
30
  ---
31
31
 
@@ -23,7 +23,7 @@ This example shows one way to integrate **agentic-awesome-skills** with a Jetski
23
23
  - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
24
24
  - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
25
25
 
26
- This pattern avoids context overflow when you have 2,026+ skills installed.
26
+ This pattern avoids context overflow when you have 2,028+ skills installed.
27
27
 
28
28
  Manifest contract references:
29
29
 
@@ -29,7 +29,7 @@ Preferred homepage:
29
29
  Preferred social preview:
30
30
 
31
31
  - lead with `AAS Core` and the profile → stack → plan flow;
32
- - present `2,026+ Agentic Skills` as supporting catalog evidence, not a second product;
32
+ - present `2,028+ Agentic Skills` as supporting catalog evidence, not a second product;
33
33
  - mention Codex and Claude as the current Core agent path, with broader host compatibility as distribution support;
34
34
  - avoid dense text and tiny logos that disappear in social cards.
35
35
 
@@ -72,7 +72,7 @@ The update process refreshes:
72
72
  - Canonical skills index (`skills_index.json`)
73
73
  - Compatibility mirror (`data/skills_index.json`)
74
74
  - Web app skills data (`apps\web-app\public\skills.json`)
75
- - All 2,026+ skills from the skills directory
75
+ - All 2,028+ skills from the skills directory
76
76
 
77
77
  ## When to Update
78
78
 
@@ -31,7 +31,7 @@ AAS MCP does not scan the repository and does not decide which skills are best.
31
31
  > **Release boundary:** AAS Core landed after release 14.6.0. Use an exact Core-capable release rather than an unreviewed moving tag.
32
32
 
33
33
  ```bash
34
- npm exec --yes --ignore-scripts --package=agentic-awesome-skills@16.0.0 -- aas mcp configure \
34
+ npm exec --yes --ignore-scripts --package=agentic-awesome-skills@16.1.0 -- aas mcp configure \
35
35
  --host codex \
36
36
  --scope user \
37
37
  --config /absolute/path/to/codex/config.toml \
@@ -1064,4 +1064,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
1064
1064
 
1065
1065
  ---
1066
1066
 
1067
- _Last updated: June 2026 | Total Skills: 2,026+ | Total Bundles: 58_
1067
+ _Last updated: June 2026 | Total Skills: 2,028+ | Total Bundles: 58_
@@ -17,7 +17,7 @@ Configure AAS Core for Claude Code, describe the task and constraints, let Claud
17
17
  - It lets Claude search the verified local catalog without loading the full library into context.
18
18
  - It preserves Claude's exact selection without using metadata as an eligibility gate.
19
19
  - It keeps MCP discovery read-only and CLI changes approval-gated.
20
- - It includes 2,026+ skills instead of a narrow single-domain starter pack.
20
+ - It includes 2,028+ skills instead of a narrow single-domain starter pack.
21
21
  - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
22
22
  - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
23
23
  - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.
@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
12
12
 
13
13
  - It installs directly into the expected Gemini skills path.
14
14
  - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
15
- - It helps new users get started with bundles and workflows rather than forcing a cold start from 2,026+ files.
15
+ - It helps new users get started with bundles and workflows rather than forcing a cold start from 2,028+ files.
16
16
  - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
17
17
 
18
18
  ## Install Gemini CLI Skills
@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
18
18
 
19
19
  Kiro's agentic capabilities are enhanced by skills that provide:
20
20
 
21
- - **Domain expertise** across 2,026+ specialized areas
21
+ - **Domain expertise** across 2,028+ specialized areas
22
22
  - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
23
23
  - **Workflow automation** for common development tasks
24
24
  - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture
@@ -39,7 +39,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of AAS Core
39
39
 
40
40
  When you ran `npx agentic-awesome-skills` or cloned the repository, you:
41
41
 
42
- ✅ **Downloaded 2,026+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
42
+ ✅ **Downloaded 2,028+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
43
43
  ✅ **Made them available** to your AI assistant
44
44
  ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
45
45
 
@@ -231,7 +231,7 @@ Let's actually use a skill right now. Follow these steps:
231
231
 
232
232
  ## Direct-install Step 5: Pick Skills Manually
233
233
 
234
- Don't try to use all 2,026+ skills at once. Here's a sensible approach:
234
+ Don't try to use all 2,028+ skills at once. Here's a sensible approach:
235
235
 
236
236
  If you want a tool-specific starting point before choosing skills, use:
237
237
 
@@ -362,7 +362,7 @@ Usually no, but if your AI doesn't recognize a skill:
362
362
 
363
363
  ### "Can I load all skills into the model at once?"
364
364
 
365
- No. Even though you have 2,026+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
365
+ No. Even though you have 2,028+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
366
366
 
367
367
  The intended pattern is:
368
368
 
@@ -40,7 +40,7 @@ agentic-awesome-skills/
40
40
  ├── 📄 CONTRIBUTING.md ← Contributor workflow
41
41
  ├── 📄 CATALOG.md ← Full generated catalog
42
42
 
43
- ├── 📁 skills/ ← 2,026+ skills live here
43
+ ├── 📁 skills/ ← 2,028+ skills live here
44
44
  │ │
45
45
  │ ├── 📁 brainstorming/
46
46
  │ │ └── 📄 SKILL.md ← Skill definition
@@ -53,7 +53,7 @@ agentic-awesome-skills/
53
53
  │ │ └── 📁 2d-games/
54
54
  │ │ └── 📄 SKILL.md ← Nested skills also supported
55
55
  │ │
56
- │ └── ... (2,026+ total)
56
+ │ └── ... (2,028+ total)
57
57
 
58
58
  ├── 📁 apps/
59
59
  │ └── 📁 web-app/ ← Interactive browser
@@ -106,7 +106,7 @@ agentic-awesome-skills/
106
106
 
107
107
  ```
108
108
  ┌─────────────────────────┐
109
- │ 2,026+ SKILLS │
109
+ │ 2,028+ SKILLS │
110
110
  └────────────┬────────────┘
111
111
 
112
112
  ┌────────────────────────┼────────────────────────┐
@@ -207,7 +207,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
207
207
  │ ├── 📁 brainstorming/ │
208
208
  │ ├── 📁 stripe-integration/ │
209
209
  │ ├── 📁 react-best-practices/ │
210
- │ └── ... (2,026+ total) │
210
+ │ └── ... (2,028+ total) │
211
211
  └─────────────────────────────────────────┘
212
212
  ```
213
213