self-improve
/self-improve
Sprawdza przed zamknięciem pracy agenta niepotwierdzone twierdzenia, brakujące kody wyjścia i nieaktualne założenia oraz zapisuje trwałe wnioski.
- Autor
- DYNO-SOFT ↗
- Repozytorium
- self-improving-loop ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 05.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 05.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Sprawdza przed zamknięciem pracy agenta niepotwierdzone twierdzenia, brakujące kody wyjścia i nieaktualne założenia oraz zapisuje trwałe wnioski.
Oryginalny opis (EN)
Run before finalizing any session with real work, and whenever the agent is about to claim something is done, fixed, or verified — to (1) audit for cognitive errors (unverified claims, missing exit-code checks, stale assumptions, unproven works) and (2) capture durable lessons so future sessions need less steering. Also run after the user corrects the agent.
Jak działa
- The loop (Hermes-style)
- Cognitive-error audit (run before claiming done)
- Routing: fact vs procedure
- Claude Code auto-memory (curate, do not duplicate)
- Skills degrade — observe and repair
- What to save / what NOT to save
- Match effort to task
- Memory rules
- Skill rules (procedures)
- Failure modes to avoid
Podgląd SKILL.md
--- name: self-improve description: Run before finalizing any session with real work, and whenever the agent is about to claim something is done, fixed, or verified — to (1) audit for cognitive errors (unverified claims, missing exit-code checks, stale assumptions, unproven works) and (2) capture durable lessons so future sessions need less steering. Also run after the user corrects the agent. --- # Self-Improve (self-learning + cognitive-error guard) Weights do not change between sessions; improvement happens at the agent layer: durable memory + reusable skills + verification habits. This skill closes the loop and catches the mistakes that cost time twice. Every serious task should leave behind better operating context: a durable memory, a corrected preference, or a reusable skill. ## The loop (Hermes-style) 1. Understand the task; inspect the real environment with tools, not guesses. 2. Act with tools. 3. Verify — run the thing with a real test, browser check, or command output; check the exit code. A syntax/lint check is not a run. 4. Save durable facts as memory. 5. Convert a repeatable procedure into (or patch) a skill. 6. Next run, load memory + skill automatically before acting. ## Cognitive-error audit (run before claiming done) Answer each before saying done, fixed, works, or verified: - Did I actually execute it? If not, say so. `Verified:` only when the command ran and its exit code was checked. - Numbers, not adjectives: did I state the measured result, not a guess? - Did I check every exit code, including the ones that look fine? - Is the config actually picked up? Prove the running thing changed, not just the file. A switch set in one shell is not state. - Did I reproduce the fixed state? A verification that never re-enters the broken state proves nothing. - Did I execute every branch the change adds, including the fresh-checkout one? - Is any statement stale? Did the environment change since I learned it? - Did I widen scope silently? Say what was left undone. - Did I treat removing or trusting something as a claim and check references? If any answer is no, fix the claim or the verification before finishing. ## Routing: fact vs procedure - Durable FACT (preference, env path, quota, tool quirk, a correction) -> memory: machine-wide -> `~/.claude/LEARNED.md`; project-wide -> `<repo>/AGENTS.md`. - Repeatable PROCEDURE (multi-step workflow, checklist, commands, known failures) -> a skill under `~/.claude/skills/<name>/SKILL.md` (frontmatter name + description). ## Claude Code auto-memory (curate, do not duplicate) Claude Code 2.1.x already writes an auto-memory: MEMORY.md plus topic files. Do not re-invent it — curate it on every review: 1. Review MEMORY.md for candidates worth promoting, stale entries, and duplicates. 2. Promote a proven pattern that recurs 2-3 times: MEMORY.md (background context) -> CLAUDE.md (enforced instruction) or .claude/rules/<topic>.md (scoped rule). 3. Extract a recurring fix into its own skill. 4. Prune stale or duplicate entries immediately. Do not write the same fact into three places. Machine-level lessons go to ~/.claude/LEARNED.md; project-level go to <repo>/AGENTS.md, and MEMORY.md only when the fact is that project own. ## Skills degrade — observe and repair A skill is a static file in a dynamic environment: it degrades silently when its commands, paths, or assumptions go stale. Close the loop instead of trusting it: 1. OBSERVE — telemetry logs every skill use to ~/.claude/debug/skill-telemetry.jsonl. 2. INSPECT — audit: usage frequency, unused or stale skills, failure patterns. 3. AMEND — edit the skill from evidence, keeping a backup before changing it. 4. EVALUATE — re-run the task and confirm the amendment actually helped. When a skill misbehaves, amend it immediately (with a backup) rather than working around it; a broken skill is worse than no skill. ## What to save / what NOT to save Save: user communication preferences and corrections you should not repeat, stable environment paths, deploy/run conventions, tool quirks and integration gotchas. A correction the user already made is the highest-value memory — save it first, so they never have to make it twice. Do NOT save: temporary task progress, PR numbers, stale run logs, raw secrets, anything that expires quickly. If the lesson is a procedure, make it a skill, not a memory note. ## Match effort to task A small formatting edit should not burn the same reasoning budget as a multi-repo debugging task. Spend thinking depth in proportion to the size and risk of the job. ## Memory rules 1. Read the target file before appending; never overwrite. 2. One lesson = one short bullet under `## <topic> (learned YYYY-MM-DD)`. 3. Exact ids, codes, slugs, ports; `Verified:` only when executed. 4. Dedupe and prune: extend instead of repeating; remove contradictory entries. 5. Keep additions under ~12 lines; no secrets or tokens. ## Skill rules (procedures) 1. Create a skill only for a workflow likely to recur and multi-step. 2. Include commands, paths, known failures, and the verification step. 3. Patch the skill immediately when a command in it stops working. ## Failure modes to avoid - Saving too much, or saving run logs instead of preferences. - Citing stale facts after the environment changed. - Claiming success without testing. - Treating "I remembered it in-session" as learning — if it is not in a file a future session loads, it is not persisted. ## After running State in the final answer: what was verified, what fact was saved where, whether a skill was created or patched. Success = less steering on the next similar task.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · DYNO-SOFT/self-improving-loop | 90 | MIT |
| zereight/gitlab-mcp | 100 | MIT |
| grandamenium/self-improve-skill | 100 | MIT |
| shafthq/shaft_engine | 100 | MIT |
| kennykennethkkang/switchboard | 100 | Apache-2.0 |
| randomittin/heimdall | 100 | MIT |
| itestflow/itestflow-agent | 100 | MIT |
| nitinjain999/platform-skills | 98 | Apache-2.0 |
| Hrutin-Suriya-Kotni/until-hired | 90 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki e7250fd61ed0 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100sweep-verification
Sprawdza dowody przed każdym stwierdzeniem, że zadanie jest gotowe albo działa, bo niepotwierdzone twierdzenia nie mają wartości. - 90agent-memory
Przypomina trwałe decyzje projektu, zapisuje wyraźnie zatwierdzone wnioski i przegląda historię pamięci przez lokalny serwer. - 100self-improvement
Zapisuje poprawki i preferencje użytkownika jako wnioski, by przyszłe odpowiedzi były lepsze, gdy ktoś koryguje błąd. - 98learner
Zamienia rzeczywiste błędy agenta, powtarzane prompty i trwałe lekcje projektu w lepsze skille SDD lub wpisy pamięci, ulepszając ich routing i proces zespołu. - 90verify-claims
Wyszukuje w odpowiedziach niepotwierdzone tezy, zwłaszcza te, na których opiera się decyzja, diagnoza albo rekomendacja. - 100lessons
Zapisuje i porządkuje trwałe lekcje w katalogu .agent/lessons: jeden plik na lekcję z indeksem w README, po powtarzalnym błędzie, trudnym debugowaniu lub przy czyszczeniu indeksu.