selftune

Self-improving skills for AI agents.

Your agent skills learn how you work. Detect what's broken. Fix it automatically.

Install · Use Cases · How It Works · Commands · Platforms · Docs

Your skills don't understand how you talk. You say "make me a slide deck" and nothing happens — no error, no log, no signal. selftune watches your real sessions, learns how you actually speak, and rewrites skill descriptions to match. Automatically.

Works with Claude Code (primary). Codex, OpenCode, and OpenClaw adapters are experimental. Zero runtime dependencies.

Install

npx skills add selftune-dev/selftune

Then tell your agent: "initialize selftune"

Two minutes. No API keys. No external services. No configuration ceremony. Uses your existing agent subscription. You'll see which skills are undertriggering.

CLI only (no skill, just the CLI):

npx selftune@latest doctor

Updating

The skill and CLI ship together as one npm package. To update:

npx skills add selftune-dev/selftune

This reinstalls the latest version of both the skill (SKILL.md, workflows) and the CLI. selftune doctor will warn you when a newer version is available.

Before / After

selftune learned that real users say "slides", "deck", "presentation for Monday" — none of which matched the original skill description. It rewrote the description to match how people actually talk. Validated against the eval set. Deployed with a backup. Done.

Built for How You Actually Work

I write and use my own skills — Your skill descriptions don't match how you actually talk. Tell your agent "improve my skills" and selftune learns your language from real sessions, evolves descriptions to match, and validates before deploying. No manual tuning.

I publish skills others install — Your skill works for you, but every user talks differently. selftune ships skills that get better for every user automatically — adapting descriptions to how each person actually works.

I manage an agent setup with many skills — You have 15+ skills installed. Some work. Some don't. Some conflict. Tell your agent "how are my skills doing?" and selftune gives you a health dashboard and automatically improves the skills that aren't keeping up.

I use skills for non-coding work — Marketing workflows, research pipelines, compliance checks, slide decks. You say "make me a presentation" and nothing happens. selftune learns that "slides", "deck", and "presentation for Monday" all mean the same skill — and fixes the routing automatically.

How It Works

A continuous feedback loop that makes your skills learn and adapt. Automatically. Your agent runs everything — you just install the skill and talk naturally.

Observe — Seven real-time hooks capture every query, every skill invocation, and every correction signal. Structured telemetry — not raw logs. On Claude Code, hooks install automatically during selftune init. Backfill existing transcripts with selftune ingest claude.

Detect — Finds the gap between how you talk and how your skills are described. You say "make me a slide deck" and your pptx skill stays silent — selftune catches that mismatch. Clusters missed queries by invocation type. Detects correction signals ("why didn't you use X?") and triggers immediate improvement.

Evolve — Generates multiple proposals biased toward different invocation types, validates each against your real eval set with majority voting, runs constitutional checks, then gates with an expensive model before deploying. Not guesswork — evidence. Automatic backup on every deploy.

Watch — After deploying changes, selftune monitors trigger rates, false negatives, and per-invocation-type scores. If anything regresses, it rolls back automatically. No manual monitoring needed.

Automate — Run selftune cron setup to install OS-level scheduling. selftune syncs, grades, evolves, and watches on a schedule — fully autonomous.

How Is This Different from Agents That "Learn"?

Some agents claim self-improvement by saving notes about what worked. That's knowledge persistence — not a closed loop. There's no measurement, no validation, and no way to know if the saved notes are actually correct.

selftune is empirical. It observes real sessions, grades execution quality, detects missed triggers, proposes changes, validates them against eval sets, deploys with automatic backup, monitors for regressions, and rolls back on failure. Twelve interlocking mechanisms — not one background thread writing markdown.

Commands

Your agent runs these — you just say what you want ("improve my skills", "show the dashboard").

Full command reference: selftune --help

Why Not Just Rewrite Skills Manually?

Different Layer, Different Problem

LLM observability tools trace API calls. Infrastructure tools monitor servers. Neither knows whether the right skill fired for the right person. selftune does — and fixes it automatically.

selftune is complementary to these tools, not competitive. They trace what happens inside the LLM. selftune makes sure the right skill is called in the first place.

Platforms

Claude Code (fully supported) — Hooks install automatically. selftune ingest claude backfills existing transcripts. This is the primary supported platform.

Codex (experimental) — selftune ingest wrap-codex -- <args> or selftune ingest codex. Adapter exists but is not actively tested. Skill attribution is conservative: selftune only records explicit Codex skill evidence, not incidental assistant/meta mentions.

OpenCode (experimental) — selftune ingest opencode. Adapter exists but is not actively tested.

OpenClaw (experimental) — selftune ingest openclaw + selftune cron setup for autonomous evolution. Adapter exists but is not actively tested.

Requires Bun or Node.js 18+. No extra API keys.