skilly

Delete remote branches whose PR was merged. Read-only dry-run, then confirm, then delete.

Translates shorthand git/GitHub workflow commands into the correct sequence of actions. ALWAYS trigger when the user's message contains a "--" prefixed shorthand like: "--c", "--p", "--cp", "--pr", "--prm", "--cppr", "--cpprm", "--ff", "--release", "--pub", "--close" — with or without a trailing "?". The "--" prefix is required — do NOT trigger on bare letters like "c" or "pr" appearing in normal sentences. NEVER invoke this skill autonomously — it MUST always be user-invoked via an explicit "--" shorthand in their message.

Walk the user through a manual procedure step by step, with every value spelled out and every link clickable.

Critiques an implementation plan — or a wayfinder map/ticket — from multiple angles (security, simplicity, edge cases, scope creep, codebase conflicts, tech-specific best practices) via parallel critic subagents. Trigger: user says "kritisiere den plan", "plan check", "plan-kritik", "blinde flecken", "/plan-critics" — also invoke when a planning agent wants to validate its own plan before presenting it, or a wayfinder session wants a resolution checked before closing a ticket. Must be called at top-level (not inside a subagent) — it uses the Task tool.

Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".

Frame a problem or decision as 1-3-1: one problem, three distinct solutions, one recommendation. Use when the user brings a non-trivial decision or fork and wants options weighed before a pick ("what should I do about X", "help me decide", "weigh the tradeoffs"), or names "1-3-1" or "do a 131". Skip questions with one right answer, just answer those.

Probe whether a candidate term carries its meaning alone, by asking three models to guess it from a bare scenario. Use when naming a field, an enum value, a table or a glossary word and several candidates are in play ("carry or carryOver", "does this name read", "which word is clearer").

Manage this repo's agent skills with the skilly CLI — add or remove bundles/skills, pull hub updates. Use when the user wants skills or bundles added, removed, or updated. For a skills.sh URL use the skills CLI directly, not skilly. Not for repo bootstrap (that is skilly setup, run once).

Orchestrate a multi-ticket feature: one /implement agent per sub-issue; orchestrator sequences, relays, merges.

The writing rules for every repo artifact: docs, code comments, commit messages, PR bodies, issue bodies. Use before writing or reviewing prose anywhere in a repo — README, docs, CLAUDE.md, skill files, commits, PRs, issues.

Mine the user's own agent session logs per model and per harness, count failure modes, and propose the top three as hazard rules. Use when the user asks to audit, review or mine agent history, session logs or transcripts for mistakes, failure modes or corrections, or asks why an agent keeps doing X.

The code-naming rules. Use before naming a variable, function, file, type, table, route, component, event, or env var, and when a request's word differs from the repo's.

Find where the repo's own instructions, the user's global instructions, hooks, lint and CI contradict or duplicate what skilly installed. Writes an HTML report, edits nothing.

Watch a PR until it is merge-ready: CI, review threads, fix-push loop. Use for "babysit", "watch the PR", "get it green".

The one definition of what each gate runs. Use to run a gate stage, to add or change a check, or to read why a step exists.

Operate Vercel with the CLI — pull env vars, inspect deployments, read runtime logs, list deploys. Use when a task needs Vercel deployment state, env vars, or logs. Not for writing app code.