genie

learn

.genie/attic/skills/learn/SKILL.md

Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.

microagent-create

mikro/plugins/claude-code/skills/microagent-create/SKILL.md

PROPOSE-ONLY — mine this host's recent Claude Code transcripts for work that keeps recurring and keeps returning bulk into context, rank those families by the context they burn, and write ONE draft mikro microagent into `.mikro/agents/<name>.proposed/` (agent.yaml + SYSTEM.md + EVIDENCE.md) for the user to approve. Read this skill when the user asks to create, propose, draft or suggest an mikro microagent, asks what is worth offloading, asks where their tokens are going and wants an agent for it, or runs /mikro:microagent-create. It never activates anything: `.proposed` is a reserved suffix that mikro discovery skips, so a draft is neither listed nor callable until the USER renames the directory. Do not use it to edit an existing agent, to run an agent, or to answer a question about a codebase (that is `mikro_explore-r`).

offload-guidance

mikro/plugins/claude-code/skills/offload-guidance/SKILL.md

ROUTING RULE — when the question asks where something lives, how something works, what handles X, or how Y flows through a repository you have not already read into context, call the mikro microagent tool `mikro_explore-r` (namespaced `mcp__plugin_mikro_mikro__mikro_explore-r`) with the question as `prompt`, BEFORE running Grep/Glob/Read/Bash searches and BEFORE launching an Explore subagent. This rule outranks the habit of grepping first: it applies to multi-part questions even when each part looks small on its own, and the offloaded run costs this session almost none of its context, which is the entire reason to make it. Its citations are leads you then verify yourself. Read this skill for the protocol: the call shape and session resume, how to read the answer, and the three measured conditions that force escalation back to your own tools (citations that do not resolve; an errored or timed-out run; work where completeness matters more than cost). Read it also when an mikro result comes back errored, uncited, or thin. Does not apply when the answer is already in context, the question is about one known line or a diff you just made, or the work is a mutation.

authoring

skills/authoring/SKILL.md

Write or revise a Genie skill so it survives the shipped contract — frontmatter, house size, starter card, and runtime-neutral voice.

brainstorm

skills/brainstorm/SKILL.md

Explore an ambiguous idea with the user, settle scope and success criteria, and produce an independently reviewed design for wish.

council

skills/council/SKILL.md

Assess a proposal through independent technical, product, risk, and dissenting lenses, then synthesize a decision without mutating unless explicitly requested.

deslop

skills/deslop/SKILL.md

Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for.

docs

skills/docs/SKILL.md

Audit documentation and developer experience against the live product — drift, onboarding, error messages — and write or fix docs when asked.

fix

skills/fix/SKILL.md

Resolve blocking review gaps through bounded repairs and independent re-review; diagnose stalled attempts without expanding scope.

genie-hacks

skills/genie-hacks/SKILL.md

Browse, search, and contribute community hacks — real-world patterns for provider switching, teams, skills, hooks, cost optimization, and more.

genie

skills/genie/SKILL.md

Route Genie questions, operations, bugs, and planned work. Resume related wishes; handle ordinary requests directly unless Genie planning or coordination adds value.

merge

skills/merge/SKILL.md

Resolve an in-progress merge or rebase by the intent of both sides, re-run the full gate on the merged tree, and finish the operation.

refine

skills/refine/SKILL.md

Improve a prompt using official OpenAI or Claude guidance. Text or @file mode; --for openai or --for claude selects guidance, not a runtime model.

report

skills/report/SKILL.md

Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.

research

skills/research/SKILL.md

Investigate a question against primary sources, cite every claim, and write the findings into the repository's own notes.

review

skills/review/SKILL.md

Independently assess designs, plans, implementations, PRs, or repository quality; return evidence and SHIP, FIX-FIRST, or BLOCKED without applying fixes.

skill-audit

skills/skill-audit/SKILL.md

Audit the shipped skill catalogue for overlap, staleness, and drift against the install record, and propose keep, improve, merge, or retire per skill.

verify

skills/verify/SKILL.md

Prove a completion claim with fresh evidence before making it — the gate's exit code, the real diff, the remote's checks, the reviewer's verdict.

wish

skills/wish/SKILL.md

Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.

work

skills/work/SKILL.md

Execute an approved wish in dependency order with scoped workers, independent review, bounded repairs, and verified completion.

workfly

skills/workfly/SKILL.md

Discover a procedure and build its saved workflow — dynamic discovery, drafted script, adversarial verification, landed in the catalog.