Skip to content
cccskills
FreePublished on GitHub

auto-improve

Run the propose-then-apply self-improvement loops in abi (`abi improve`) and abbey (`abbey learn improve`). Use when asked to "self-improve", "auto-improve", or preview/apply what abi or abbey would learn from recent activity. Both default to a dry run; applying is an explicit, gated step. Not a trainer, not LoRA, and not skill-loop.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19 stars(GitHub 19 + cccskills 0)

Run score Not tested

See how to install

Files included (1)

  • SKILL.md2.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

auto-improve — preview, then apply, what abi and abbey would learn

Two local CLIs, one contract: a dry run is the default, and --apply performs only the steps its gate allows. Neither command edits code, skills, or prompts.

abi — abi improve [--apply] [--model <id>] <input>

Run from /Users/donald/sources/repos/abi. It wraps the SEA learn loop (abi-sea run_learn_loop).

  • Dry run runs the loop with persist and adapt_router off. It recalls evidence and reports task=, profile=, evidence_count=, audit_passed=, audit_vetoed=, and apply_allowed=, and it writes nothing.
  • --apply re-runs the loop with the default config only when audit_passed=true and audit_vetoed=false. Otherwise it prints skipped: and persists nothing, so a rejected completion never becomes evidence.
  • It needs a persistent WDBX store and exits 1 without one. For experiments, point ABI_WDBX_PATH at a scratch directory, never the live ~/.abi/wdbx.
./tools/cargo.sh build -p abi-cli
ABI_WDBX_PATH=target/skill-scratch/wdbx target/debug/abi improve "plan next repair"
ABI_WDBX_PATH=target/skill-scratch/wdbx target/debug/abi improve --apply "plan next repair"

abbey — abbey learn improve [n] [--apply]

Run from ~/dev/active/abbey. It reads the last n route records (default 20), the memory reflect report, and train_candidate curation counts.

  • Output rows tagged [auto] are applied by --apply. Today the only auto step is promoting recent routes into the activity layer.
  • Rows tagged [review] are for a human: routes below 0.6 confidence, duplicate or low-confidence or superseded memories, and candidates missing provenance. --apply never touches them.
  • A dry run with no memory store does not create one.

Gotchas

  • In abi, run tests and ./tools/check.sh with < /dev/null (an auth test reads stdin).
  • abi's improve is the 14th frozen command. Its help, help.json, completion files, and site/index.html chip list are golden-tested, so a change to its wording means updating those files together.
  • The abbey help text calls LoRA "Proposed". Neither loop trains weights beyond abi's adaptive router, so do not describe either as fine-tuning.
  • skill-loop's review/fix flags are unrelated and unreliable; do not use them as the improvement signal.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

abbey-system-prompt

Free

Maintain the Abbey / Aviva / Abi Discord system prompts in the Rust abbey-bot (`src/ask.rs`) and keep the hosted Grok bots (Grok Bot Abbey, Aviva Grok) in step with them. Use when the user says "improve grok bots", "abbey prompt", "persona prompt", "ask.rs", "system prompt", "tip floor", asks to change how Abbey/Aviva/Abi speak on Discord, or after an abbey-bot PR merges and the hosted bot's tip floor needs bumping. Runs as /abbey-system-prompt.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-claims-validator

Free

Validate ABI docs and external collateral against repo evidence and docs/contracts/external-claims-audit.mdx. Use when auditing claims, scanning docs for unsupported QPS/sharding/FHE/AES language, checking one claim before publish, or re-confirming the external-claims audit. Agent procedure only — not a CLI or slash command. Pair with abi-doc-claims-sync when editing docs.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-doc-claims-sync

Free

Synchronize ABI Markdown and docs claims with executable behavior. Use before editing README, AGENTS.md, CLAUDE.md, GEMINI.md, docs/**/*.mdx, walkthroughs, changelogs, or any old ABI Markdown that mentions WDBX, MCP, GPU, clustering, compression, FHE, agents, or benchmarks.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-goal-orchestrator

Free

Plan and execute ABI repo work from the TODO board, roadmap/spec docs, stable Rust 1.99.1 constraints, and validation gates. Use when the user asks to find ABI todos/roadmaps, organize a large implementation from tasks/todo.md, or decide the next safe work slice. Distinct from the goals skill — that skill owns the persistent ledger tasks/goals.md; this skill plans from the active board and north-star specs.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-mcp-transport

Free

Validate ABI MCP JSON-RPC stdio and its custom loopback HTTP compatibility endpoint, including auth, limits, notifications, and shutdown.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

abi-plugin-system

Free

Review ABI's 16 compiled-in plugin fixtures, manifest validation, manual bundled registry, and real CLI/MCP run dispatch without claiming dynamic loading.

The English summary is being prepared. Showing the original description.

donaldfilimon/abi19Updated Oct 27, 2026

See all skills by donaldfilimon

Report a problem with this skill