agent-reliability-skills — Claude Code plugin: generate SKILL.md
This Claude Code plugin creates a repository skill with reliability rules for the agent SDKs it finds. Run /agent-reliability-skills:forge or ask for the skill before the coding agent starts work.
Apache-2.0 ★ 62 updated 2026-11-15
/plugin marketplace add trustabl/agent-reliability-skills
/plugin install agent-reliability-skills@agent-reliability-skillsWhat agent-reliability-skills does
The plugin checks dependency manifests for agent SDKs, then builds a SKILL.md with Trustabl rules for the SDKs it finds. It saves the file at .claude/skills/trustabl-pre-coding/SKILL.md. An existing file there is replaced only if Forge created it.
On first use, Claude downloads the Trustabl analyzer from GitHub to ~/.trustabl/cli/, checks it against checksums.txt, then runs trustabl forge with Bash. A checksum mismatch prevents installation. Repository code stays on the local machine; after downloading the analyzer and rules, the plugin can work offline from cache. No API key is needed.
What it helps with
- generate a reliability skill for the agent SDKs in a repository
- identify agent SDKs from dependency manifests
- write SDK-specific rules to
.claude/skills/trustabl-pre-coding/SKILL.md
Example prompts for the agent
- Run
/agent-reliability-skills:forgefor this repository. - Create a reliability skill before the agent starts writing code.
- Generate a reliability skill for
path/to/repo.
How to install agent-reliability-skills
Plugin marketplace
/plugin marketplace add trustabl/agent-reliability-skills/plugin install agent-reliability-skills@agent-reliability-skillsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about agent-reliability-skills
How do I install agent-reliability-skills in Claude Code?
Run these commands in order: /plugin marketplace add trustabl/agent-reliability-skills, then /plugin install agent-reliability-skills@agent-reliability-skills.
What does agent-reliability-skills do?
It detects agent SDKs from dependency manifests and writes a SKILL.md with Trustabl rules for those SDKs. Claude can apply the rules while writing code.
What does agent-reliability-skills need to run?
Claude Code is required; no API key is needed. On first use, it needs GitHub access to download the analyzer and rules repository.
Source text
claude-plugin · Apache-2.0
# agent-reliability-skills for Claude Code A Claude Code plugin for Trustabl Forge: Claude generates a pre-coding reliability skill for your repository, so it applies Trustabl's rules while it writes code instead of meeting them later as scan findings. Install in Claude Code: ``` /plugin install agent-reliability-skills --marketplace trustabl/agent-reliability-skills ``` Use it with `/agent-reliability-skills:forge [repo]`, or ask Claude for a reliability skill before agent work; the `generate-reliability-skill` skill takes it from there. ## What it does - Reads your repository's dependency manifests (`package.json`, `pyproject.toml`, `requirements.txt`, `go.mod` and others) and finds the agent SDKs it uses: the Claude Agent SDK, OpenAI Agents SDK, Google ADK, MCP, LangChain and LangGraph, CrewAI, Pydantic AI, the Vercel AI SDK, AutoGen and more. - Builds a `SKILL.md` from Trustabl's detection rules for exactly those SDKs and saves it to `.claude/skills/trustabl-pre-coding/SKILL.md`, replacing an existing file there only if Forge generated it. - Makes no model call and needs no API key. ## How it runs The plugin has no MCP server, hooks or scripts. On first use, Claude runs a short install block from the skill that downloads the pinned open-source [Trustabl analyzer](https://github.com/trustabl/agent-reliability-analyzer), which runs `trustabl forge`, into `~/.trustabl/cli/`, after checking it against the release's `checksums.txt` (a mismatch installs nothing), and then runs it with the Bash tool. It works on macOS, Linux and Windows (Git Bash). For Cursor and other MCP clients, use the MCP server instead: [plugin/README.md](../plugin/README.md). ## Requirements Nothing beyond Claude Code. ## Privacy - **Collection:** none by default. The plugin sends nothing to Trustabl. The analyzer's own `TRUSTABL_TELEMETRY` setting applies to the binary it runs, and it is off until you configure it. - **Your code:** read on your machine (only the dependency manifests are needed) and never uploaded. - **Network access:** only GitHub, to download the analyzer release and Trustabl's rules repository. After that it works offline from cache. - **Storage:** the analyzer binary in `~/.trustabl/cli/`, the analyzer's rules cache, and the `SKILL.md` it writes into your repository. Delete any of them at any time. - **Third parties:** nothing is shared with Trustabl or anyone else. - **Trustabl's privacy policy** (for its hosted services): https://trustabl.ai/privacy/ - **Contact:** https://github.com/trustabl/agent-reliability-skills/issues License: Apache-2.0.
© Trustabl · Apache-2.0 · trustabl/agent-reliability-skills