Loading...
Loading...
Found 2,057 Skills
Roda o loop de implementação — implementar → revisar → corrigir → re-revisar — sobre uma unidade de trabalho, e abre branch e PR ao final. Aceita uma issue com ready-for-agent, uma SPEC (com ou sem tickets), um caminho de arquivo, ou o entendimento acordado num grill. Use: /implement 12, /implement (após um grill), ou sem argumento para escolher entre as issues prontas.
Run the software factory. Use when the user types /factory alone or /factory help (prints the help), /factory
Create the release notes and upgrade guide for a mariadb-operator release. Given the release PR whose body lists every PR included in the release, it gathers each PR, groups the changes by relevance, and produces `docs/releases/RELEASE_<version>_HEADER.md.gotmpl` and `docs/releases/UPGRADE_<version>.md` in the format the previous releases use, then opens a PR targeting `release-<version>`. If no release PR is provided it asks for the new version and infers the changes from git history since the last tag. Use whenever the user wants release notes, an upgrade/update guide, or docs for a new mariadb-operator version — "create the release notes for 26.10.0", "write the upgrade guide", "document this release", "prepare the release PR docs" — even if they don't mention a release PR.
Finish a PR by repeatedly requesting a Kelos review, waiting for its check, addressing valid review findings, squashing commits, and updating the PR until a review approves and that iteration is finalized. Use when the user says "finish-pr" or asks for this review-and-fix loop. Defaults to the PR for the current branch.
This skill should be used when the user is building electrobun features for the milady-ai/milady project, submitting PRs to milady that will be reviewed by the agent-review system, asks about "electrobun milady", "milady electrobun PR", trust tiers, Biome compliance, or the release-electrobun.yml workflow.
Provide a situation report on the current work: objective, done, in progress, blocked, next, and open questions. Default window is everything since the session start or the previous sitrep in this conversation, whichever is later. Evidence comes from session history plus read-only git/GitHub checks. Use when the user says "sitrep", "situation report", "status report", "where are we", "what's happened", "catch me up", or after a long run to summarise state.
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments. Identical to greploop, but triggers reviews by tagging @greptile-apps, which bypasses Greptile's file-count limit on huge PRs that the plain @greptile mention refuses to review. Use when the user wants to fully optimize a large PR/MR/CL against Greptile's code review standards.
Use when replying to an issue reporter or outside contributor, or reviewing someone else's pull request.
Watches a pull request through CI and review, fixes real findings and stops when it is ready, merged or blocked. Use when the user asks to watch, monitor or babysit a PR, or /ds-watch-pr.
Stack draft PRs for the tickets a still-open PR unblocks — the frontier computed as if that PR were merged, branched on its head — and hand each to Copilot. Use when the user wants to start tickets blocked by an open PR, delegate the issues a PR will unblock, or open stacked PRs on top of a PR.
Configura um repositório para o pipeline: issue tracker e vocabulário de labels, a seção `## Commands` (lint/typecheck/test/build/clean) que o implementer lê como gate, a seção `## Fluxo` com as saídas recomendadas depois de um grill, o remote, o template de PR, a CI com esses gates e `npm audit`, os rótulos de risco e o `review-rules-projeto.md`. Rode uma vez por repositório, antes do primeiro uso de to-spec, to-tickets ou implement. Use quando o usuário disser "setup do projeto", "setup-project", "configura o tracker", "prepara o repo para o pipeline" ou variações.
Autonomous PR review that posts high-signal, human-voiced comments under your account. Use when reviewing someone else's PR or your own manifest-driven PR, when you want a precision-tuned review you can walk away from, or when the user asks to review a PR, post a PR review, autoreview, loop review, or watch a PR.