Claude Code: AI Agent Workflow Collection

Print a user-runnable script that bypasses branch protection (enforceadmins) to squash-merge a solo-owner PR, after verifying the merge gate. Claude NEVER modifies branch protection itself — it only prints (or clipboards) the command for the repo admin to run. Triggers on /admin-merge and when /wrap hits an enforceadmins-style block.

Cleanly stop an active /babysit-pr watcher for a PR. Sets the watcher's stop flag in session-state so its next tick terminates, cancels the recurring poll (CronDelete in durable mode), and confirms. Invoke as /babysit-pr-stop .

Verify all Test Plan checkboxes in a PR against the actual code, check off passing items, and report any failures.

Bounded-convergence PR cleanup — audit every review thread + every CI check-run, fix all issues, push once per sweep, dismiss stale bot CHANGESREQUESTED on old commits, resolve all threads via GraphQL, then wait (capped) for bot verdicts + CI on the new SHA, re-sweeping on new findings up to 5 iterations. Zero uncollapsed threads and zero failing checks when done.

Resume an interrupted or stalled review workflow. Detects where the agent left off — local CR review, push, PR creation, review polling, CR/Greptile feedback processing, thread resolution, merge gate verification, or acceptance criteria — and continues from the next incomplete step automatically. Invoke as /go-on.

Create GitHub issues following Pollinations team conventions. Use when asked to create issues, track work, or plan features.

Classify merge/rebase conflicts against main, auto-resolve safe (simple) hunks and stage clean files, and report complex hunks for human judgment. Does not commit.

Scan open issues for staleness and suggest closures. Detects issues solved by merged PRs, no-activity issues (30+ days), superseded issues, and potential duplicates of already-closed issues. Presents recommendations for user confirmation — never auto-closes. Triggers on "pm-clean", "stale issues", "clean backlog", "close stale".

Generate a PM handoff prompt for context-window turnover. Captures static config, live GitHub state, in-flight thread state, and memory summary into a self-contained prompt for a fresh PM thread. Bootstraps .claude/pm-config.md on first run. Triggers on "pm-handoff", "handoff", "context turnover", "new pm thread", "thread turnover".

Manage the OKRs section of .claude/pm-config.md. Show current objectives, set new ones, or get AI-suggested updates based on recent work. OKRs drive /pm-prioritize ranking and /pm-sprint-plan planning. Use this whenever you want to view, set, or update project OKRs, objectives, key results, or goals. Triggers on "pm okr", "set okrs", "show okrs", "suggest okrs", "project goals", "objectives".

Evaluate team member contributions over a configurable period (default 2 weeks). Produces per-contributor metrics — PRs merged, review cycles, issue throughput, review participation, and CR success rate — with constructive qualitative observations.

Generate a 2-week sprint plan from the open backlog with dependency detection, parallel tracks, team assignments, and OKR alignment. Reuses /prioritize ranking logic and pm-config.md for team/OKR context.

Sprint retrospective — what got done, what slipped, velocity metrics, blockers, per-contributor breakdown, and lessons learned. Reuses /pm-rate-team data-gathering approach and pm-config.md for team context.

Summarize what each contributor did in the past 24 hours — commits, PRs, issues, and reviews grouped by person. Multi-contributor version of /standup. Uses Team section from pm-config.md for display names and roles when available.

Re-scan the current repo and update .claude/pm-config.md with fresh infrastructure and architecture detection while preserving user-edited sections (Role, OKRs, Team, Notes, Dependency Rules, Workflow Rules), then run a stale-cleanup pass to prune long-abandoned worktrees and branches. Use this after major milestones, new service integrations, or significant directory restructuring. Triggers on "pm update", "update pm config", "refresh pm config", "rescan repo".

Thread-level PR fleet manager. Rediscovers your open PRs every tick, prints a status table, and auto-dispatches the per-PR decision tree (rebase / /fixpr / /wrap) until the fleet is clean or hard-blocked. Triggers on "/pr-monitor-and-manage", "/pmm", "manage PRs", "PR fleet", "watch PRs".

Clean-cancel companion to /pr-monitor-and-manage. Stops the PR-fleet-manager loop, tears down its /loop, clears monitoring state in session-state.json, and prints a final summary. Triggers on "/pr-monitor-and-manage-stop", "/pmm-stop", "stop monitoring PRs".

Executive PR review from a CTO/CPO/Chief Data Scientist lens. Analyzes multiple PRs in parallel for strategic fit, risk, issue alignment, and operational readiness. Use when reviewing PRs before merge, assessing merge readiness, or doing a leadership pass on open PRs.

End-to-end issue-to-coding workflow. Accepts an issue number or description, handles CR plan polling, merges plans into issue body, creates worktree and branch, outputs ready-to-code summary. Use to start work on an issue without manually walking through the issue-planning flow.