agentic-awesome-skills 18.8.0 → 18.9.0
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/README.md +22 -14
- package/data/aas-v1/catalog-manifest.v1.json +1 -1
- package/data/aas-v1/skill-content-index.v1.json +1 -1
- package/data/aas-v1/skill-content.v1.ndjson +2 -0
- package/data/catalog.json +74 -2
- package/data/plugin-compatibility.json +41 -3
- package/data/skills_index.json +68 -0
- package/package.json +2 -2
- package/skills/loki-mode/examples/todo-app-generated/backend/package-lock.json +3 -3
- package/skills/loki-mode/examples/todo-app-generated/backend/package.json +2 -1
- package/skills/omentir-linkedin-outreach/SKILL.md +96 -0
- package/skills/since-cutoff/SKILL.md +68 -0
- package/skills_index.json +68 -0
- package/tools/bin/install.js +8 -4
- package/tools/lib/aas-v1/mcp/server.js +5 -0
package/README.md
CHANGED
|
@@ -1,11 +1,11 @@
|
|
|
1
|
-
<!-- registry-sync: version=18.
|
|
1
|
+
<!-- registry-sync: version=18.9.0; skills=2478; stars=47057; updated_at=2026-09-29T09:21:51+00:00 -->
|
|
2
2
|
# AAS Core — Agentic Awesome Skills
|
|
3
3
|
|
|
4
4
|
> **Find reusable instructions for your project, inspect their complete files, and keep an exact skill set you can review and reuse.**
|
|
5
5
|
|
|
6
|
-
Agentic Awesome Skills is a library of 2,
|
|
6
|
+
Agentic Awesome Skills is a library of 2,478+ installable `SKILL.md` playbooks. AAS Core helps Codex or Claude search the complete local catalog, record the skills the agent chooses, and preview a plan you can inspect before changing a target. Core does not rank or recommend skills.
|
|
7
7
|
|
|
8
|
-
**Current release: V18.
|
|
8
|
+
**Current release: V18.9.0.** AAS Core supports local catalog inspection, agent-owned selection, stack validation, and plan preview. Apply and recovery remain experimental. [Read the AAS Core preview guide](https://github.com/sickn33/agentic-awesome-skills/blob/v18.9.0/docs/users/aas-core.md) for setup and exact trust boundaries.
|
|
9
9
|
|
|
10
10
|
This README tracks `main`. Features listed under [Unreleased](CHANGELOG.md#unreleased) require a later release; the versioned guide describes the published package.
|
|
11
11
|
|
|
@@ -35,7 +35,7 @@ This is an independent community project, not affiliated with or endorsed by Goo
|
|
|
35
35
|
- [Choose Your Tool](#choose-your-tool)
|
|
36
36
|
- [Recommended Specialized Plugins](#recommended-specialized-plugins)
|
|
37
37
|
- [Bundles & Workflows](#bundles--workflows)
|
|
38
|
-
- [Browse 2,
|
|
38
|
+
- [Browse 2,478+ Skills](#browse-2478-skills)
|
|
39
39
|
- [Troubleshooting](#troubleshooting)
|
|
40
40
|
- [Stable Skills Manifest v1](#stable-skills-manifest-v1)
|
|
41
41
|
- [Contributing](#contributing)
|
|
@@ -56,11 +56,16 @@ If GitHub's player stalls, [watch the video on the AAS website](https://aaskills
|
|
|
56
56
|
|
|
57
57
|
## Support the Project
|
|
58
58
|
|
|
59
|
-
|
|
59
|
+
Help keep the catalog open, maintained, and available to the builders who use it.
|
|
60
60
|
|
|
61
|
-
|
|
61
|
+
<a href="https://vercel.com/open-source-program"><img alt="Vercel OSS Program" src="https://vercel.com/oss/program-badge-2026.svg" /></a>
|
|
62
62
|
|
|
63
|
-
|
|
63
|
+
| Support AAS | What it helps fund |
|
|
64
|
+
| --- | --- |
|
|
65
|
+
| [♥ Sponsor AAS](https://github.com/sponsors/sickn33) | Ongoing maintenance, reviews, and release work |
|
|
66
|
+
| [Buy Me a Coffee](https://buymeacoffee.com/sickn33) | Small, direct contributions from the community |
|
|
67
|
+
|
|
68
|
+
Every contribution helps us keep the skills curated, the tooling tested, and the catalog useful for the next project.
|
|
64
69
|
|
|
65
70
|
<a href="https://buymeacoffee.com/sickn33">
|
|
66
71
|
<img src="assets/buy-me-a-coffee-banner.png" alt="Support Agentic Awesome Skills on Buy Me a Coffee" width="420" />
|
|
@@ -81,7 +86,7 @@ Codex or Claude inspects your project and chooses exact skills. Every current ca
|
|
|
81
86
|
> [!IMPORTANT]
|
|
82
87
|
> Structural and identity validity does not certify semantic fit, compatibility, setup correctness, operational safety, or safety to apply. Apply and recovery require experimental opt-in and remain outside the supported preview.
|
|
83
88
|
|
|
84
|
-
The [Workbench](https://aaskills.tech/workbench) reviews stack and plan artifacts in browser memory without accessing your filesystem. See the [Core guide](https://github.com/sickn33/agentic-awesome-skills/blob/v18.
|
|
89
|
+
The [Workbench](https://aaskills.tech/workbench) reviews stack and plan artifacts in browser memory without accessing your filesystem. See the [Core guide](https://github.com/sickn33/agentic-awesome-skills/blob/v18.9.0/docs/users/aas-core.md) for tool contracts, capability coverage, and limits.
|
|
85
90
|
|
|
86
91
|
## Installation
|
|
87
92
|
|
|
@@ -90,22 +95,22 @@ The [Workbench](https://aaskills.tech/workbench) reviews stack and plan artifact
|
|
|
90
95
|
Start with AAS Core in Codex or Claude. Configure the local MCP using the [Codex](docs/users/codex-cli-skills.md) or [Claude](docs/users/claude-code-skills.md) guide. With the MCP available, ask the agent to inspect your project, compare relevant skills, and save the exact selection. Then validate its manifest and review the resulting plan before any installation. The first configuration command previews a change and returns an approval digest:
|
|
91
96
|
|
|
92
97
|
```bash
|
|
93
|
-
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@18.
|
|
98
|
+
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@18.9.0 -- aas mcp configure \
|
|
94
99
|
--host codex \
|
|
95
100
|
--scope user \
|
|
96
101
|
--config /absolute/path/to/codex/config.toml \
|
|
97
102
|
--cache-root /absolute/path/to/aas-cache
|
|
98
103
|
```
|
|
99
104
|
|
|
100
|
-
Use `--host claude` and its configuration path for Claude. The [Core setup guide](https://github.com/sickn33/agentic-awesome-skills/blob/v18.
|
|
105
|
+
Use `--host claude` and its configuration path for Claude. The [Core setup guide](https://github.com/sickn33/agentic-awesome-skills/blob/v18.9.0/docs/users/aas-core.md#configure-the-local-mcp) explains approval, reconnection, validation, and planning. To hand the reviewed IDs to the direct installer, use `aas stack install-preview` as described in the [manifest handoff](docs/users/aas-core.md#use-the-reviewed-selection); that command only prepares a `--dry-run` preview and does not apply a Core plan.
|
|
101
106
|
|
|
102
107
|
### Install selected skills directly
|
|
103
108
|
|
|
104
109
|
If you already know the IDs, preview a focused install into your host's skill directory:
|
|
105
110
|
|
|
106
111
|
```bash
|
|
107
|
-
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@18.
|
|
108
|
-
agentic-awesome-skills --release 18.
|
|
112
|
+
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@18.9.0 -- \
|
|
113
|
+
agentic-awesome-skills --release 18.9.0 --path .agents/skills \
|
|
109
114
|
--skills brainstorming,systematic-debugging --dry-run
|
|
110
115
|
```
|
|
111
116
|
|
|
@@ -163,7 +168,7 @@ Bundles suggest related skills; workflows describe the order to use them. They a
|
|
|
163
168
|
- [Workflows](docs/users/workflows.md) give ordered playbooks for planning, shipping, testing, and auditing; [workflow metadata](data/workflows.json) is available for integrations.
|
|
164
169
|
- If too many installed skills overload Antigravity, follow the [selective activation guide](docs/users/agent-overload-recovery.md). For other hosts, preview a smaller exact install or use the installer's `--risk`, `--category`, and `--tags` filters.
|
|
165
170
|
|
|
166
|
-
## Browse 2,
|
|
171
|
+
## Browse 2,478+ Skills
|
|
167
172
|
|
|
168
173
|
Explore the complete library in the [hosted catalog](https://aaskills.tech/) or [`CATALOG.md`](CATALOG.md). The canonical playbooks live in [`skills/`](skills/); [`skills_index.json`](skills_index.json) provides machine-readable discovery. Use [Getting Started](docs/users/getting-started.md) and [Usage](docs/users/usage.md) for first steps, or the [Workbench](https://aaskills.tech/workbench) to inspect a saved Core stack and plan in your browser.
|
|
169
174
|
|
|
@@ -171,7 +176,7 @@ For narrower comparisons, see [Claude Code skills](docs/users/best-claude-code-s
|
|
|
171
176
|
|
|
172
177
|
## Troubleshooting
|
|
173
178
|
|
|
174
|
-
- [Core setup and trust boundaries](https://github.com/sickn33/agentic-awesome-skills/blob/v18.
|
|
179
|
+
- [Core setup and trust boundaries](https://github.com/sickn33/agentic-awesome-skills/blob/v18.9.0/docs/users/aas-core.md)
|
|
175
180
|
- [Installation and everyday use](docs/users/usage.md)
|
|
176
181
|
- [Windows context and truncation recovery](docs/users/windows-truncation-recovery.md)
|
|
177
182
|
- [Linux/macOS overload and selective activation](docs/users/agent-overload-recovery.md)
|
|
@@ -214,6 +219,7 @@ Key source families include:
|
|
|
214
219
|
|
|
215
220
|
### Official Sources
|
|
216
221
|
|
|
222
|
+
- **[vanshyadav1408/Omentir](https://github.com/vanshyadav1408/Omentir)**: Official Omentir source for the [`omentir-linkedin-outreach`](skills/omentir-linkedin-outreach/SKILL.md) skill - LinkedIn prospecting and outreach through the hosted Omentir MCP server (OAuth): find and score leads, draft messages, and check campaigns, research and drafts only by default, never signs into LinkedIn (MIT).
|
|
217
223
|
- **[Spicy-API/nsfw-ai-skill](https://github.com/Spicy-API/nsfw-ai-skill)**: Official SpicyAPI source for the [`nsfw-ai-spicyapi`](skills/nsfw-ai-spicyapi/SKILL.md) skill — adult (18+) image, image-to-video and image-edit generation through the SpicyAPI API with quote-before-spend and adults-only / consent rules (MIT).
|
|
218
224
|
- **[Atlas Cloud](https://atlascloud.ai/)**: Official source for the [`atlas-cloud-media`](skills/atlas-cloud-media/SKILL.md) skill — asynchronous image and video generation through the Atlas Cloud API.
|
|
219
225
|
- **[sandbaseai/cli](https://github.com/sandbaseai/cli)**: Official source for the `sandbase-mcp` skill - discover, inspect, and invoke 2,000+ AI models and APIs through a local MCP bridge with explicit schema and cost checks (Apache-2.0).
|
|
@@ -258,6 +264,8 @@ Key source families include:
|
|
|
258
264
|
- **[testdriverai/testdriverai](https://github.com/testdriverai/testdriverai)**: Official TestDriver source for the `testdriver-e2e-testing` skill - author, run, and debug end-to-end tests that drive browsers and native apps in a real desktop sandbox with AI vision and natural-language element descriptions (Apache-2.0).
|
|
259
265
|
- **[HEOJUNFO/ai-film-crew](https://github.com/HEOJUNFO/ai-film-crew)**: Official source for the `film-crew` skill - run a video idea past seven film-crew roles and get a shot list with one model-ready prompt per shot, plus prompt fixes and reroll diagnosis for Wan, LTX, Kling, Veo, Seedance, Hailuo, and Runway (MIT).
|
|
260
266
|
- **[hermes-labs-ai/lintlang](https://github.com/hermes-labs-ai/lintlang)**: Official source for the `lintlang-audit` skill - deterministic, zero-LLM static auditing of agent instructions, tool definitions, and embedded Python prompts, reporting finding codes and locations without editing files or calling a model (Apache-2.0).
|
|
267
|
+
- **[target1m/traderspy-mcp](https://github.com/target1m/traderspy-mcp)**: Official TraderSpy source for six crypto market research skills (`traderspy-*`) - market briefings, technical analysis, screening and backtests, AI signals, top-trader positioning, and position checks through the hosted, read-only TraderSpy MCP server (MIT).
|
|
268
|
+
- **[MohammadHijjawi97/since-cutoff](https://github.com/MohammadHijjawi97/since-cutoff)**: Official source for the `since-cutoff` skill - lists which APIs of a project's pinned Python dependencies changed after the model's training cutoff, from a static diff of the two releases with no model calls, shows where the code uses them, and writes short AGENTS.md or CLAUDE.md notes (MIT).
|
|
261
269
|
|
|
262
270
|
</details>
|
|
263
271
|
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"assets":[{"path":"data/aas-v1/skill-content-index.v1.json","sha256":"sha256-
|
|
1
|
+
{"assets":[{"path":"data/aas-v1/skill-content-index.v1.json","sha256":"sha256-8fb3be6dfdf6bb39e9a2e260447d496edaf0162992c727c7edde84361f0f4b58","size":1541655},{"path":"data/aas-v1/skill-content.v1.ndjson","sha256":"sha256-bb67559a376a7405fbde16f4e4f66841d6bdf4508ff09cf20a74b91ad54b4545","size":20802385},{"path":"data/catalog.json","sha256":"sha256-74c911dea21955ba39a75470323fcf53d3dd8c134e1d1c9170ee37cae75cf2fd","size":2088590},{"path":"tools/lib/aas-v1/ontology.v1.json","sha256":"sha256-aaecc6a7e1b5fc7d1f8d5577b797982974aca2642e2d716e05fa2aab6a4fa885","size":7221}],"catalogDigest":"sha256-c2e3e4d668a055de16cc4ba77f6457b54aabf294114d41944ac97ebcf4d95b50","catalogSchemaVersion":"2.0.0","digestVersion":1,"package":"agentic-awesome-skills","packageVersion":"18.9.0","schemaVersion":1,"skillCount":2478}
|