Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Ci Watch

ASecurity

Watch a CI run with live status + emoji dashboard; dump logs on failure; watch auto-merge if CI green + auto-merge enabled + "reviewed" label. Triggers: "watch ci" | "ci watch" | "watch the ci" | "watch run" | "monitor ci".

9 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsbashgit

Works with

terminal

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add Roxabi/roxabi-plugins --skill ci-watch --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ci Watch?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ci Watch
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/roxabi-ci-watch/badge)](https://www.skillsdirectory.com/skills/roxabi-ci-watch)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: R-ci-watch
description: 'Watch a CI run with live status + emoji dashboard; dump logs on failure; watch auto-merge if CI green + auto-merge enabled + "reviewed" label. Triggers: "watch ci" | "ci watch" | "watch the ci" | "watch run" | "monitor ci".'
version: 0.1.0
argument-hint: '[PR# | --run ID | --branch NAME] [--interval N]'
allowed-tools: Bash, Glob, Grep, Read
---

# CI Watch

Let:
  Φ  := `${CLAUDE_PLUGIN_ROOT}`
  SCR := `${Φ}/scripts/ci-watch.sh`
  R  := OWNER/REPO (auto-detected from git remote)
  AM := auto-merge

Poll a GitHub Actions run, render a live emoji dashboard, dump failed logs on exit, and watch AM if CI is green, AM is enabled on the PR, and the PR has a `reviewed` label.

## Instructions

### 1. Detect repo

```bash
git remote get-url origin
```

Extract R from the URL (handles both HTTPS `https://github.com/OWNER/REPO.git` and SSH `git@github.com:OWNER/REPO.git`).

### 2. Parse arguments

Map `$ARGUMENTS` to script flags:

| Input | Flags passed |
|-------|-------------|
| bare number (e.g. `42`) | `--pr 42` |
| `--run ID` | `--run ID` |
| `--branch NAME` | `--branch NAME` |
| `--pr NUMBER` | `--pr NUMBER` |
| `--workflow NAME` | `--workflow NAME` |
| `--interval N` | `--interval N` |
| (none) | (omit — script auto-detects branch + `ci.yml` workflow) |

### 3. Run the script

```bash
bash SCR --repo R [flags]
```

Use a 600000ms timeout (10 min). Stream output directly — do not buffer.

### 4. Report result

- Exit 0 → confirm run passed (and, if AM was watched, the PR merged).
- Exit 1 → confirm run failed; note that failed logs were printed above.
- Exit 2 → confirm run was cancelled.
- Exit 4 → **CI passed but the PR did not merge** (closed / conflicts / auto-merge disabled / watch timed out). ¬a CI failure — do not offer Retry-CI. Route to a merge follow-up: rebase, resolve conflicts, or re-enable auto-merge.
- Non-zero (other) → report the exit code and raw conclusion.

### 5. Watch auto-merge (if applicable)

AM_eligible(pr) ⟺ PR# known ∧ `autoMergeRequest` ¬null ∧ label `reviewed` ∈ PR.

¬AM_eligible → exit after reporting CI passed.

∀ AM_eligible: enter merge-wait loop (live spinner) → exit once merged (0) ∨ green-CI-unmerged (4).
- `MERGED` → confirm PR merged automatically (exit 0).
- `CLOSED` / `DIRTY` (conflicts) / auto-merge disabled / watch timeout → exit 4 (see §4).
- `BEHIND` / `BLOCKED` / `UNSTABLE` → transient, keep polling (¬terminal).

Timeout: the loop self-bounds at `MERGE_WAIT_TIMEOUT` (script, 15 min) → graceful exit 4. This is only reachable if the **Bash timeout you pass exceeds CI-watch time + that bound** — when a PR is expected to auto-merge, allow a Bash timeout ≥ 20 min so the script's exit 4 fires instead of a hard SIGKILL.

## Chain Position

- **Phase:** Verify
- **Predecessor:** `/R-pr` (via `/R-dev`) · or `reviewed` label step (via `/R-ship`)
- **Successor:** `/R-validate` (via `/R-dev`) · or `/R-cleanup` (via `/R-ship` after merge)
- **Class:** adv (continuous flow, no gate)

## Task Integration

- `/R-dev` owns the dev-pipeline task lifecycle externally
- This skill does NOT update its own dev-pipeline task
- Sub-tasks created: none
- Follow-up: CI failure → `/R-dev` may create a re-run / fix follow-up task

## Exit

- **CI green via `/R-dev`:** return control silently. ¬write summary. ¬ask user. ¬announce `/R-validate`. `/R-dev` re-scans and advances.
- **CI green standalone:** print one line: `CI passed. Next: /R-validate`. Stop.
- **CI failed/cancelled (exit 1/2):** return error. `/R-dev` presents Retry | Skip | Abort (or creates a follow-up fix task depending on failure type).
- **CI green but unmerged (exit 4):** ¬a CI failure — report the merge blocker (conflicts / closed / auto-merge off / timeout) and route to rebase / resolve / re-enable, ¬Retry-CI.

$ARGUMENTS

Attribution

RoxabiRoxabi
View sourceMore from Roxabi →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →