Skills for Real Engineers. Straight from my .agents directory.
39 skills
research-observability
Agent skill from
Add file-based observability, tracing, and run analysis to LLM/agent experiments — per-turn transcripts, tool calls and results, reasoning traces, token/cost accounting, per-episode artifacts, plus terminal viewers and a run-comparison report. Platform-agnostic: one small adapter covers OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, vLLM, or any custom inference stack, and the same tooling then works unchanged. Use this skill whenever the user wants observability, tracing, logging, or run tracking for model experiments; asks why an agent failed a task or wants to replay/debug/diff an episode; wants to compare models, arms, or ablations; wants to instrument a new folder, repo, or platform ("add observability here", "do the same for Tinker/Gemini/OpenAI"); wants to import or tie in existing experiment results so old runs show up alongside new ones; or wants eval runner scripts where many models share one protocol. Reach for this even when they only say "log what the model is doing",
How to install research-observability
install research-observability
# install the gateway-skills pack with the skills CLI
npx skills add Leanmcp/gateway-skills# or add only this skill to Claude Code: copy the folder
skills/research-observability/
# into
~/.claude/skills/research-observability/ (all projects)
.claude/skills/research-observability/ (one project)
1# Research observability23Experiments you cannot replay are experiments you have to rerun. This skill4installs a small, file-based observability layer over any LLM/agent experiment5and the tools to read it: every generation, every tool call and result, every6reasoning trace, every reward — on disk as plain JSONL, greppable, diffable, and7re-gradable months later.89The design bet: **the recording format is fixed and platform-independent, so10adding a platform is writing one ~15-line normalizer, not re-plumbing11observability.** LiteLLM, OpenAI, Gemini, Anthropic, Tinker and a bespoke12inference server all produce identical files, and every viewer, report and diff13downstream works with no further changes.1415## Start here1617**Adding observability to a project.** Follow18[references/integration.md](references/integration.md) end to end — it is a19seven-step procedure, starting with a survey of the repo (which platform, where20the generations happen, where results go today) and ending with the existing21runs imported so old and new sit in the same viewer. Do the survey before22writing code; the answers determine every later choice.2324**A platform not yet wired.** [references/platforms.md](references/platforms.md)25has working recipes for OpenAI, Gemini/Vertex, Anthropic, LiteLLM, Tinker, and26vLLM/self-hosted, plus the 15-line template for anything else and the27framework-level patterns (subclass the model class, or use the callback API).2829**Understanding or extending the format.**30…
Excerpt shown under the repository's MIT license.
More skills in gateway-skills
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
CC1 skill
Public repository for Agent Skills
20 skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
CCCU6 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
CCCXGHGM+135 skills