An agent skill is a folder of instructions, scripts and resources that an agent loads on demand. Unlike an MCP server it runs no process of its own, which makes it cheaper in context and simpler to audit.
Showing 193–216 of 935
ramboz
Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions. Auto-triggers when you say review this design, review this architecture, review this proposal, review my RFC, poke holes in this proposal, is this design sound, or critique this tech spec. Defers to any other installed skill whose description identifies it as handling architectur
ramboz
Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this spec, explain this ADR, what does this output mean, or explain this snippet; invoke e
ramboz
Team baseline for PR and code review — produces scope, blockers, nits, and strengths. Auto-triggers when you say review this PR, check this diff, review these changes, pre-review before I share, what do you think of this PR, or review the diff on this branch. Defers to any other installed skill whose description identifies it as handling PR review, code review, or diff review — if such a skill is
ramboz
Re-baseline a jig corpus onto a moved load-bearing reference by drafting a keystone ADR and an affected-artifact disposition manifest. Use when a vendor/API contract moved and specs and decisions must be re-anchored. Auto-triggers when you say reframe onto this, we changed direction, the design moved, or re-baseline the project; invoke explicitly as `/jig:reframe`. Defers to any other installed sk
ramboz
Team baseline for security review — a best-effort heuristic security pass over a diff or change-set. Auto-triggers for review this for security, any vulnerabilities here, security pass on this diff, is this code secure, check this for security issues, or security review this. Uses installed scanners when available; installs nothing. Defers to any other installed skill whose description identifies
openshift-eng
Adversarial examination of the hypothesis currently under discussion
openshift-eng
Always-on commit structuring. Activates whenever the user asks to commit uncommitted changes — plans small, logical commits by default. The user chooses whether to create the commits or just see the proposals. Not for PR creation.
openshift-eng
Check LVMS release readiness by verifying branches, dependencies, and configuration
openshift-eng
Close stale, unlinked, unassigned AI-generated bugs that no longer match current CI failures (dry-run by default)
openshift-eng
Analyze a MicroShift Prow CI Test Job execution
openshift-eng
Analyze MicroShift Test Scenario results
openshift-eng
Check if a given MicroShift version is available and where to find it
openshift-eng
Use when preparing a branch or PR that changes marketplace plugins — analyzes commits vs a base ref, suggests a major/minor/patch version bump per changed plugin with reasoning, and applies the bumps on confirmation
openshift-eng
Analyze release health data and produce assessment
openshift-eng
Analyze sprint delivery, churn, and goal attainment for retrospective
openshift-eng
Check if a MicroShift CVE Jira ticket is fixed in the latest Brew nightly golang build
openshift-eng
Validate advisory promotion for QE sign-off — Konflux bootc images (default) or Errata Tool RPM advisory (--errata)
openshift-eng
Verify all artifacts and docs are publicly available after shipping — bootc images, RPMs, errata, documentation, and lifecycle page
openshift-eng
Triage CodeRabbit review comments on a PR — vet, apply valid fixes, reply
openshift-eng
Skeptical second pass on PR review findings — use after /review-pr to filter noise and validate real issues
openshift-eng
Close a project workspace, mark it done, and clean up its worktrees
openshift-eng
Consolidate a bloated project CLAUDE.md by archiving completed checklist items
ramboz
Orient a spec-driven jig/servo/shaper repository with a read-only, project-wide briefing: start from the `workflow.py orient` headline, then survey open pull requests and unmerged work, Proposed ADRs, DEFERRED triggers, refinement items, release plans, the inbox, and the bug board; render one readable headline, titled sections, one recommendation, and an owning-skill handoff. Use when the user inv
openshift-eng
Analyze sprint capacity and commitment health
