- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add mxyhi/ok-skills --skill autoresearch -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add mxyhi/ok-skills --skill autoresearch -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add mxyhi/ok-skills --skill autoresearch -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add mxyhi/ok-skills --skill autoresearch -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/mxyhi/ok-skills/tree/HEAD/autoresearchDe l'éditeur
Iterations: unlimited.autoresearch/{subcommand}-{YYMMDD}-{HHMM}/ directory.handoff.json. Evals reads *-results.tsv.$autoresearch)Parse the invocation in this order:
Print a banner on every invocation: [autoresearch] mode: classic | orchestrator | wizard.
Activated when a plain-language goal is given without Metric:/Verify:. Classifies the goal into a Goal archetype — see references/orchestrator-routing.md for the archetype table and router decision table.
Resolve every scripts/... path below relative to this installed skill directory, never relative to the caller's working directory.
Two modes based on archetype:
Backed by scripts/orchestrate.sh (deterministic seam — all routing logic lives there). Subcommands exposed: classify, next-hop, units, plateau, screen-cmd, verdict, validate-state, screen-state-predicate.
scripts/orchestrate.sh classify "<goal>" → archetype label + mode.plan logic to produce a concrete Success predicate: exact shell command + expected output. For optimize-metric, run the full plan/wizard derivation internally.request_user_input showing: archetype, mode, concrete predicate (command + expected output), terminal choice (stop-at-verified vs proceed-to-ship). Misclassifications are caught here, not mid-run.screen-cmd; print projected cycle budget. Stop here if --dry-run.handoff.json, regression verdict, error count) + affected-test verify.
b. scripts/orchestrate.sh next-hop orchestrator-state.json → next subcommand.
c. Run subcommand (its own bounded inner loop).
d. Record per-hop outcome ∈ {progressed, no-op, failed, blocked}.
e. Fold hop's handoff.json into orchestrator-state.json.
f. scripts/orchestrate.sh units → recompute Units remaining.CONVERGED.scripts/orchestrate.sh plateau orchestrator-state.json → true → stop + report PLATEAU.--max-cycles N) → stop + report CEILING.blocked/failed with no alternative route → checkpoint + stop + report BLOCKED.orchestrator-state.json — orchestrator-owned, additive. Tracks: goal, archetype, predicate, terminal-choice, units_remaining history, cycle count, per-hop pipeline log with outcomes, current incumbent. Each hop's handoff.json is unchanged (single-hop bridge); the orchestrator reads it and folds it in. Two clearly-owned state objects, no overlap.
--auto to ship; deploy always requires explicit user approval.localhost/127.0.0.1/container hostname, or database name carries _test/_ci suffix. Bare substring match does not qualify. Anything else refused.screen-state-predicate and refuses on refuse.screen-cmd.orchestrator-state.json; every cycle and every resume reuses that exact string so "done" is reproducible across runs.validate-state gates orchestrator-state.json (required fields + coarse types); a malformed ledger is not trusted to route from.pending_verify; next-hop routes to a verify hop (held-out / adversarial check) before DONE or ship. The verify hop never auto-approves ship.units returns unknown (e.g. runner crash) is not counted as zero-progress; repeated unknown routes to BLOCKED.Autonomous iteration loop: modify, verify, keep/discard against any metric
---name: autoresearchdescription: Autonomous iteration loop: modify, verify, keep/discard against any metric---# autoresearch/SKILL.mdFAQ
Téléchargez autoresearch/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/mxyhi/ok-skills.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.