Toru Claude Agents

Skills

14 in the Claude listing

• Branch workflowBranch and commit conventions that keep an agent's work reviewable — one branch per task, main stays clean, nothing force-pushed.
• Cc docsLook up how Claude Code itself works — hooks, skills, subagents, MCP, plugins, settings — from the official docs, so answers come from the current spec instead of memory.
• Claude code masteryDesign better agents, skills and hooks for Claude Code, checking the current spec instead of guessing at fields.
• Dev cycleRun a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.
• Dev finishClose out a session — summarise what changed, capture what was learned, and prepare the commit.
• Dev full autoHand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.
• Dev qaRun the project's own tests, linter, type checker and build, and report what actually failed.
• Dev rcThe last gate before merge — QA, security audit, review and changelog, with objective pass conditions.
• Dev securityAudit the code for vulnerabilities, leaked secrets and risky dependencies before it ships.
• Megg learnSave a project fact, decision or gotcha so your next session already knows it.
• Megg stateHand off an unfinished session to the next one — what's done, what's next, what's blocked.
• Openspec workflowWrite the spec before the code, then check the built thing against it — so agents build what was agreed, not what they invented.
• scoutMap unfamiliar code or research an approach before planning, read-only and fast.
• Self improvementTurn friction you just hit into a concrete change to the workflow, so the same problem doesn't recur.