Watch Review Requests
Watch a read-only inbound PR request dashboard on an adaptive or fixed cadence; manual review only, unattended, with no submissions or disposition prompts.
Install
npx skills add flurdy/agent-skills --skill watch-review-requestsgit clone --depth 1 https://github.com/flurdy/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/watch-review-requests ~/.claude/skills/watch-review-requestsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Watch Review Requests Thin scheduler for [PR Review Requests](../pr-review-requests/SKILL.md), like `/watch-prs` for `/pr-status`. Each tick invokes `/pr-review-requests` and renders its full current dashboard, including unchanged outstanding requests. The summary owns collection, session-local comparison, errors, and manual next steps. This watcher does not analyze code or act on recommendations. Unattended: no questions, deep reviews, attempts budget, drafts, or external actions. ## Usage ```text /watch-review-requests # adaptive, stop at 18:00 /watch-review-requests 17 # adaptive, stop at 17:00 /watch-review-requests 10m 17 # fixed ten-minute cadence, stop at 17:00 /watch-review-requests status # report runtime and retained summary state /watch-review-requests reset # stop watch, then clear session-local summary state /watch-review-requests recheck owner/repo#123 # one summary recheck, never start a watcher ``` Parse at most one positive `\d+m` interval and one stop hour 0–23 (default `18`). Reject unknown, duplicate, or malformed arguments. Resolve today's stop hour in local time; at or past the deadline, do not start. State cadence and local deadline before starting. No shell/authentication preflight probes: the summary collector owns current/workspace scope and errors. Reject legacy scheduled prompts lacking `request-dashboard-v1`, even if they name this skill.
Details
- Skill name
watch-review-requests- Repository
- flurdy/agent-skills
- Path
skills/watch-review-requests/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Watch Review Requests skill do?
Watch a read-only inbound PR request dashboard on an adaptive or fixed cadence; manual review only, unattended, with no submissions or disposition prompts.
How do I install the Watch Review Requests skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add flurdy/agent-skills --skill watch-review-requests. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Watch Review Requests popular?
It lives in flurdy/agent-skills, which has 9 GitHub stars and 0 forks.
Related skills
Architect
9flurdy/agent-skills
Architecture and implementation planning gate for complex or high-blast-radius work. Produces evidence-backed decisions, reviewable slices, acceptance evidence, and conditional human review ownership without editing code.
Artifact Hygiene
9flurdy/agent-skills
Run a local-only, read-only advisory audit of publishable working-tree files and unpublished branch history with redaction-safe findings.
Backlog Groom
9flurdy/agent-skills
Auto-detects workspace unfinished backlogs across unique stores; otherwise local open beads. Flags thin prose, missing labels, drift, lifecycle and duplicates. Report-only; mutations need approval, destructive ones individually.
Workspace Sync
9flurdy/agent-skills
Guide attended Git and Beads synchronization at a validated workspace root, with accurate previews, separate fresh approvals and explicit failure boundaries. Never sync from status or wrap-up.
Watch Prs
9flurdy/agent-skills
Start a recurring PR status dashboard — runs /pr-status on an adaptive cadence (fast when CI is in flight, backing off when settled) until end of day. Unattended: renders tables and suggested next actions, never prompts or blocks.
Architect Review PR
5adelrioj/claude-skills
Use after a feature is built — e.g. the final step of a ship-it run, right after review-pr — to check it is actually complete and wired, not just line-correct. Dispatches a fresh-context Claude subagent that traces the whole repo to hunt completeness and integration gaps in the branch's changes, reports ranked, evidence-backed findings, then fixes the CRITICAL ones and verifies with a fresh re-review (capped at 3 passes; pass report-only to skip fixing). Triggers on: architect review, architecture review, completeness review, wiring review, is this wired, did we finish this, find the gaps, inc
Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.