flurdy

flurdy/agent-skills

Skill Claude Code

Read-only session orientation. Full/quick views show Jira, PRs, beads and working-copy state; resume mode gives a compact local resume-or-next recommendation without loading a handoff or claiming work.

flurdy/agent-skills

Skill Claude Code

Audit Pi startup defaults, model routing, discovery and coordinated migration previews across second-opinion and pi-spend; read-only by default, with separately confirmed native catalog refresh.

flurdy/agent-skills

Skill Claude Code

Derive a conventional session name from the branch ticket, active bead, open PR, and current work, then print the paste-ready rename command for the active client. Use when a session's auto-name is generic.

flurdy/agent-skills

Skill Claude Code

Rank ready beads across validated workspace stores or one local store. List read-only, or claim one selected bead, show its details, and continue into its work.

flurdy/agent-skills

Skill Claude Code

Ticket-scoped, read-only status dashboard that shows blockers, unmet requirements, verification evidence, working-copy state, tracking drift, and concrete untracked follow-ups.

flurdy/agent-skills

Skill Claude Code

Read-only craft review of changed code and test design: reuse, placement, complexity, and repository conventions. Requirements, coverage sufficiency, execution, and fixes have separate owners.

flurdy/agent-skills

Skill Claude Code

Read-only estimate of Pi model cost by provider and model for today, this week, this month, and all recorded history, separating metered credit usage from flat-rate subscription usage.

flurdy/agent-skills

Skill Claude Code

Materialize an approved cited plan into proportionate Beads tracking when the user asks for durable ownership. Recommends no item, one item, or a bounded epic; checks owners and duplicates; previews every write; applies only after exact confirmation.

flurdy/agent-skills

Skill Claude Code

Show enriched status of your open PRs — CI checks, approvals, unresolved review threads, and linked Jira discussion, with transition-driven suggested next actions.

flurdy/agent-skills

Skill Claude Code

Read-only workspace-level synthesis of project outcomes, requirement linkage, delivery evidence, coordination risks, and the single most important next coordination action.

flurdy/agent-skills

Skill Claude Code needs its repo

Pre-merge gate — verify a PR is green, approved, in sync, and free of obvious risk, then (on explicit approval) squash-merge it. Composes /pr-status, /contract-check, and /review-pr rather than reimplementing them.

flurdy/agent-skills

Skill Claude Code

Read-only release-readiness authority for one service. Collects normalized Git, CI, contract, ordering, toggle, and deployment evidence through one shared evaluator; renders its gate table and verdict without prompting or changing state.

flurdy/agent-skills

Skill Claude Code needs its repo

Attended release gatekeeper: consume shared readiness verdicts, offer confirmed single-service pushes (publishcommit in Pi), track CI failures and rollouts, and recommend watch cadence. Maintenance and restarts are separately owned.

flurdy/agent-skills

Skill Claude Code

Read-only release dashboard using the shared release-readiness authority. Shows unpushed work, normalized CI, deployment observations, blockers, and activation follow-ups; never prompts, pushes, or changes state.

flurdy/agent-skills

Skill Claude Code

Safely publish prepared PR-feedback outcomes through separately confirmed push, reply, and inline-thread resolution gates. Re-fetches normalized identities before every mutation and keeps retries idempotent.

flurdy/agent-skills

Skill Claude Code

Address PR review feedback through explicit item selection, independent validation, focused local fixes, verification, and a local commit. Never publishes remote actions; use reply-comments for separately confirmed push, reply, and resolution gates.

flurdy/agent-skills

Skill Claude Code

Review a repository-qualified pull request at an immutable head, compare it with Jira requirements, and return a read-only verdict with explicit evidence completeness.

flurdy/agent-skills

Skill Claude Code

Query an independent peer or a configurable local/OpenRouter review panel, with distinct quorum and evidence-backed consensus interpretation policies.

flurdy/agent-skills

Skill Claude Code

Multi-repo git workflow rules and setup. Provides mgit wrapper for safe permission patterns across independent service repositories. Use when setting up a new multi-repo workspace or when working with multi-repo git operations.

flurdy/agent-skills

Skill Claude Code

Create a new branch stacked on another PR. Use when you want to start work that depends on an existing PR that hasn't been merged yet.

flurdy/agent-skills

Skill Claude Code

Initialize work on a Jira ticket. Creates a new branch with conventional commit prefix based on the ticket type. Use when starting work on a new ticket.

flurdy/agent-skills

Skill Claude Code

Retrieve repository-scoped Thoughtbox Inbox captures, prepare a hostile-text-safe handoff to /triage in the configured Beads store, and render a separately confirmed scoped resolution command — without executing either workflow.

flurdy/agent-skills

Skill Claude Code

Sort, dedupe, and audit Claude settings.json / settings.local.json at user/project level. Flags risky permissions, broken references, glob-subsumed entries, and cross-file duplicates. Mechanical fixes auto-apply; judgment calls become triage items.

flurdy/agent-skills

Skill Claude Code

Read-only activity recap for today or the previous workday across commits, PRs, Jira touches, and Beads in validated repositories; same-day mode adds current-session context.