List the built-in skills, or browse, install and curate skill cards with a subcommand.
Approve/reactivate a learned skill after review (activates retrieval). Works for both a pending skill (held from a tainted run) and a retired one (un-retire).
NAMEstrrequiredName of the pending or retired skill to activate.
This command takes no options.
Switch a bundle off, keeping it on disk. Off is not uninstalled, deliberately: trying several and leaving two running is the normal way to use these, and making "off" mean "delete" would charge a download for every change of mind. Use ``skills-uninstall`` when you want the files gone.
NAMEstrrequiredAn installed bundle from `chimera skills-bundles`.
This command takes no options.
Switch an installed bundle on, so the agent may use it. Do this after reading it. An enabled bundle's name and description reach the agent's prompt when they match a task, and its instructions can tell the agent to run the scripts that came with it — which is why nothing is on by default.
NAMEstrrequiredAn installed bundle from `chimera skills-bundles`.
This command takes no options.
List the skill bundles installed on this machine, and where each came from.
This command takes no options.
Browse the installable skills from the wider Agent Skills ecosystem. These are other people's skills, fetched from their repositories on request — not bundled here. The table says what each one NEEDS, because most were written for a different harness and a catalogue that hid that would be advertising features that fail after the download.
QUERYstrFilter by name or description.
--topicstrOnly this topic.
Reflectively evolve a skill's prompt template against graded instances (GEPA). Each instance is a `{input, expect}` pair; the (simple, honest) scorer gives 1.0 when the produced output contains the `expect` substring, else 0.0. GEPA reflects on a failing case to rewrite the template and keeps a Pareto frontier of candidates. Dry-run by default: the improved skill is only written back to the store with ``--apply``, and only if it beats the seed.
NAMEstrrequiredName of the learned skill whose prompt to GEPA-evolve.
--instancesstrrequiredJSON file: a list of {"input": {...}, "expect": "substring"}.
--budgetintdefault: 20Rollout budget (evaluations across the search).
--modelstrModel slug for the executor + reflector.
--applybooleanSave the improved skill (default: dry-run).
Export a learned skill to the open SKILL.md format (portable to the agent-skills ecosystem).
NAMEstrrequiredName of the learned skill to export.
--out, -ostrWrite to this path (default: <name>/SKILL.md).
Import a SKILL.md into the store. A file imported by path is held pending for review. Accepts the plain name of a curated card (``chimera skills-import verify-before-claiming``) as well as a path. The documented form was ``skills/<name>``, a repo-relative path that resolves only inside a checkout — so the one line the README gives for using the shipped library failed for everybody who installed Chimera instead of cloning it. A file by path lands tainted and pending whatever its frontmatter says, until ``chimera skills-approve <name>``. Its ``provenance`` and ``status`` were written by its author, so reading them let the stranger decide whether anybody reads the card before the agent does. Only a curated card keeps what it declares: by name, or by a path whose content is exactly the shipped card. Validated on the way in. This is the only path by which a skill written by somebody else enters the store, and it was the only one that skipped the validator the agent's own proposals must pass — the gate was applied to the code we wrote and not to the code we were handed, which is backwards. A skill card ends up in the system prompt, so an unvalidated one is an instruction from a stranger with the standing of an instruction from the owner.
PATHstrrequiredA curated card name, or a path to a SKILL.md / its directory.
This command takes no options.
Download a skill bundle from its source repository into your skills directory. Fetches; runs nothing. The bundle lands **pending**: its files are on disk and no part of it reaches a prompt until you approve it. That is the same rule an imported card follows — a skill from a stranger has the standing of an instruction from the owner — and a bundle is that plus executable scripts, so it holds with more reason, not less.
NAMEstrrequiredA skill name from `chimera skills-catalog`.
--forcebooleanReplace it if it is already installed.
Browse the curated skill cards that ship with Chimera. Data, not code: each is a markdown page of Trigger/Do/Avoid/Check/Risk. Load one into your own store with ``chimera skills-import <name>``. The agent reads a matching card from that store into its prompt only with CHIMERA_SKILL_CARDS=on (or ``chimera solve --skill-cards``); it is off by default, so an imported card is otherwise reference for you, not advice to the agent.
NAMEstrShow one card in full; omit to list the library.
This command takes no options.
Run the measured skill-lifecycle loop (M18-4): promote proven provisionals, demote regressions. Decisions come from the store's MEASURED usage stats (never a model's self-report): a provisional skill that earns a high win rate over enough uses is promoted to active; a provisional that fails probation or an active skill whose win rate regresses is retired (kept for review). Dry-run by default; ``--apply`` closes the loop — cron it for a hands-off promote/demote cycle.
--applybooleanActually promote/demote (default: dry-run preview).
--promote-min-usesintdefault: 5Provisional probation length.
--promote-min-ratefloatdefault: 0.7Win rate to promote a provisional skill.
--demote-min-usesintdefault: 5Uses before a skill can be demoted.
--demote-max-ratefloatdefault: 0.3333333333333333Win rate at/below which a skill is demoted.
List learned skills held for review (e.g. distilled during a tainted run).
This command takes no options.
Propose retiring under-performing skills — review-gated, never a delete. Retiring only flips status to 'retired' (excluded from retrieval, still inspectable and reactivatable with ``skills-approve``). With no name, acts on the ``retirement_candidates`` signal (used often, low win rate). Dry-run by default; pass ``--apply`` to commit.
NAMEstrSkill to retire; omit to act on all candidates.
--applybooleanActually retire (default: dry-run preview).
--min-usesintdefault: 5Only propose skills used at least this often.
--max-ratefloatdefault: 0.3333333333333333Only propose skills whose win rate is at or below this.
Per-skill usage stats (uses, successes, win rate) + retirement candidates.
This command takes no options.
Delete an installed skill bundle and its files.
NAMEstrrequiredAn installed bundle from `chimera skills-bundles`.
This command takes no options.