Skills for Real Engineers. Straight from my .agents directory.
self-awareness
Agent skill fromaipoch/open-science
Inspect Open-Science's JavaScript control REPL, discover managed Project files, Sessions, and Agent Frames, and safely feature-gate host.* calls with host.capabilities(). Use when an Agent needs to discover available host APIs, locate an Artifact or Upload Version, diagnose a Session, or read a Frame transcript in the current Project.
How to install self-awareness
npx skills add aipoch/open-science# or add only this skill to Claude Code: copy the folder
resources/skills/self-awareness/
# into
~/.claude/skills/self-awareness/ (all projects)
.claude/skills/self-awareness/ (one project)
1# Self-awareness23Use `repl_execute` for every `host.*` call. The `host` object exists only in the persistent4JavaScript control REPL; Python and R data kernels do not receive it.56## Inspect available capabilities78```javascript9const caps = await host.capabilities()10```1112The current project-native result contains 20 known boolean keys:1314- `mcp` gates connector calls through `host.mcp(server, method, args?)`.15- `compute` gates the `host.compute` namespace.16- `agents` gates the `host.agents` namespace.17- `skills` gates the `host.skills` namespace.18- `artifacts` gates managed-file discovery through `host.artifacts(options?)` and exact path19 resolution through `host.artifactPath(versionId)`.20- `lineage` gates the read-only `host.lineage` namespace.21- `frames` gates the read-only `host.frames` namespace.22- `sessions` gates Main-only, read-only Session diagnostics through `host.sessions.list(options?)`23 and exact lookup through `host.sessions.inspect(sessionId)` in the current Project.24- `llm` gates one-shot, tool-less inference through `host.llm(request, options?)`.25- `currentModel` gates exact current-model lookup through `host.currentModel()`. It returns the26 calling Session's exact current model id and fails when the live backend cannot establish one.27- `listModels` gates configured Host LLM model discovery through `host.listModels()`. It returns the28 frozen, stable-sorted configured model ids for the current Host LLM Provider and framework. It29…
Excerpt shown under the repository's Apache-2.0 license.
More skills in open-science
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
