Skill
architect
Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can…
@sethgammonView SkillDevelopment
Skill
/pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
Install
$ npx -y skills add SethGammon/Citadel --skill pr-watch --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/pr-watch
Context preview
The summary Claude sees to decide when to auto-load this skill.
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
SKILL.md
pr-watch.SKILL.mdname: pr-watch
license: MIT
description: >-
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading
failure logs and applying targeted fixes, then optionally merges when all checks pass.
Local CLI analog to Claude Code's cloud auto-fix feature.
user-invocable: true
auto-trigger: false
trigger_keywords:
- watch pr
- watch ci
- monitor pr
- fix ci
- ci failing
- pr failing
- auto-fix
- auto fix pr
- pr is red
- checks failing
effort: high
last-updated: 2026-03-26
/pr-watch — Local PR Auto-fix
You are the PR watcher. You monitor a pull request's CI status, fix failing checks by reading failure logs and applying targeted fixes, and optionally merge when green.
This is the local CLI analog to Claude Code's cloud auto-fix feature. Use it when you want CI watch/fix behavior from the terminal without switching to web or mobile.
When to Use
**Don't use when:** monitoring local file changes (use /watch); reviewing code quality (use /review); triaging multiple issues at once (use /triage).
- `/pr-watch` — watch the PR for the current branch
- `/pr-watch 42` — watch PR #42 specifically
- After `/triage` creates a fix PR and you want to stay in the terminal
- When you don't have the Claude GitHub App installed for cloud auto-fix
Cloud Alternative
If you have the Claude GitHub App installed, use cloud auto-fix in Claude Code web or mobile — it survives machine sleep. Toggle **Auto fix** ON in the PR view. Use `/pr-watch` for in-terminal sessions.
In Codex, prefer the native PR review and automation surfaces when they fit:
node scripts/codex-pr-review.js plan --repo <owner/repo> --pr <number> --risk medium --write
node scripts/codex-automation.js plan --type pr-watch --command "/pr-watch <number>" --cadence "every 15 minutes" --write
Use `@codex review` for GitHub-visible review findings, then keep Citadel responsible for local verification, CI log fixes, merge readiness, and `.planning/pr-review/` state.
If `.planning/` does not exist, create it before writing PR review or automation state.
When Codex has already reviewed the PR, ingest its review output before polling or merging:
node scripts/codex-review-fetch.js --repo <owner/repo> --pr <number> --write
Use `--file <review-comments.json>` with the same script when working from exported/offline review data.
Inputs
| Input | Source | Required | |-------|--------|----------| | PR number | Argument (e.g., `/pr-watch 42`) | No — auto-detects from current branch | | Repo | Auto-detected from git remote | Yes (auto) | | gh CLI | `"/c/Program Files/GitHub CLI/gh.exe"` on Windows, `gh` otherwise | Yes (auto) |
Execution Protocol
Phase 0 — Setup
1. Detect gh CLI path:
- Windows: `"/c/Program Files/GitHub CLI/gh.exe"`
- Other: `gh`
- Store as `$GH`
2. Detect repo from `git remote get-url origin`. Extract `owner/repo`. 3. Resolve PR number:
- If argument provided: use it directly
- Otherwise: `$GH pr view --json number --jq '.number'` (PR for current branch)
- If no PR found: stop. Output: "No PR found for current branch. Create one first or pass a PR number."
4. Fetch PR details:
$GH pr view <number> --repo <owner/repo> --json number,title,url,headRefName,baseRefName,state,mergeable
5. Print watch summary:
Watching PR #<N>: <title>
Branch: <head> → <base>
URL: <url>
6. Initialize: `fix_attempts = 0`, `max_fix_attempts = 3`
Phase 1 — Watch Loop
Repeat until convergence or circuit break:
Step 1.1 — Fetch CI status
$GH pr checks <number> --repo <owner/repo>
Parse the output to identify check names, states (`pass`, `fail`, `pending`), and detail URLs.
Step 1.2 — Evaluate status
| Condition | Action | |-----------|--------| | All checks passing | → Phase 2 (offer merge) | | Any checks pending | Print "Waiting for checks... (N pending)". Wait 60 seconds. Loop. | | Any checks failed | → Step 1.3 (investigate and fix) | | PR closed or merged | Exit. Print "PR #<N> is already closed/merged." |
Step 1.3 — Fix failing checks
For each failed check:
**1. Get the run ID:**
$GH run list --repo <owner/repo> --branch <headRefName> --limit 5 \
--json databaseId,status,conclusion,workflowName
**2. Read failure logs:**
$GH run view <run-id> --repo <owner/repo> --log-failed
**3. Identify failure class and fix strategy:**
| Failure class | Signal in logs | Fix strategy | |---------------|---------------|--------------| | TypeScript errors | `error TS` | Fix the specific TS errors in named files | | Test failures | `FAIL`, assertion errors, `Expected` vs `Received` | Fix assertion or the code under test | | Lint errors | rule names, `@typescript-eslint/`, `eslint` | Fix the specific violations | | Build errors | `Cannot find module`, `SyntaxError`, missing exports | Resolve imports, configs | | Missing env / secrets | `undefined`, auth failures in setup steps | Surface to user — not fixable from code | | Infrastructure failure | Step itself failed (e.g., `actions/checkout`), network | Surface to user — not fixable from code |
**4. Apply fix:**
- Implement the minimum change to resolve the failing check
- Do NOT refactor, expand scope, or fix unrelated issues
- Run the equivalent check locally when possible to verify before pushing
**5. Commit and push:**
git add <only changed files>
git commit -m "fix: resolve CI failure — <check-name>"
git push
**6. Increment `fix_attempts++`**
**7. Check circuit breaker:**
If `fix_attempts >= max_fix_attempts`:
Circuit breaker triggered after 3 fix attempts on PR #<N>.
Last failing check: <check-name>
Log excerpt:
<first 25 lines of failure log>
Next steps:
• Review the failure above and investigate manually
• Run /pr-watch again after applying a manual fix
• Open the PR in Claude Code web/mobile and enable "Auto fix" for cloud-based resolution
Exit.
**8.** Wait 30 seconds for CI
Read more
name: pr-watch license: MIT description: >- Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature. user-invocable: true auto-trigger: false trigger_keywords: - watch pr - watch ci - monitor pr - fix ci - ci failing - pr failing - auto-fix - auto fix pr - pr is red - checks failing effort: high last-updated: 2026-03-26
/pr-watch — Local PR Auto-fix
You are the PR watcher. You monitor a pull request's CI status, fix failing checks by reading failure logs and applying targeted fixes, and optionally merge when green.
This is the local CLI analog to Claude Code's cloud auto-fix feature. Use it when you want CI watch/fix behavior from the terminal without switching to web or mobile.
When to Use
**Don't use when:** monitoring local file changes (use /watch); reviewing code quality (use /review); triaging multiple issues at once (use /triage).
- `/pr-watch` — watch the PR for the current branch
- `/pr-watch 42` — watch PR #42 specifically
- After `/triage` creates a fix PR and you want to stay in the terminal
- When you don't have the Claude GitHub App installed for cloud auto-fix
Cloud Alternative
If you have the Claude GitHub App installed, use cloud auto-fix in Claude Code web or mobile — it survives machine sleep. Toggle **Auto fix** ON in the PR view. Use `/pr-watch` for in-terminal sessions.
In Codex, prefer the native PR review and automation surfaces when they fit:
node scripts/codex-pr-review.js plan --repo <owner/repo> --pr <number> --risk medium --write node scripts/codex-automation.js plan --type pr-watch --command "/pr-watch <number>" --cadence "every 15 minutes" --write
Use `@codex review` for GitHub-visible review findings, then keep Citadel responsible for local verification, CI log fixes, merge readiness, and `.planning/pr-review/` state.
If `.planning/` does not exist, create it before writing PR review or automation state.
When Codex has already reviewed the PR, ingest its review output before polling or merging:
node scripts/codex-review-fetch.js --repo <owner/repo> --pr <number> --write
Use `--file <review-comments.json>` with the same script when working from exported/offline review data.
Inputs
| Input | Source | Required | |-------|--------|----------| | PR number | Argument (e.g., `/pr-watch 42`) | No — auto-detects from current branch | | Repo | Auto-detected from git remote | Yes (auto) | | gh CLI | `"/c/Program Files/GitHub CLI/gh.exe"` on Windows, `gh` otherwise | Yes (auto) |
Execution Protocol
Phase 0 — Setup
1. Detect gh CLI path:
- Windows: `"/c/Program Files/GitHub CLI/gh.exe"`
- Other: `gh`
- Store as `$GH`
2. Detect repo from `git remote get-url origin`. Extract `owner/repo`. 3. Resolve PR number:
- If argument provided: use it directly
- Otherwise: `$GH pr view --json number --jq '.number'` (PR for current branch)
- If no PR found: stop. Output: "No PR found for current branch. Create one first or pass a PR number."
4. Fetch PR details:
$GH pr view <number> --repo <owner/repo> --json number,title,url,headRefName,baseRefName,state,mergeable
5. Print watch summary:
Watching PR #<N>: <title> Branch: <head> → <base> URL: <url>
6. Initialize: `fix_attempts = 0`, `max_fix_attempts = 3`
Phase 1 — Watch Loop
Repeat until convergence or circuit break:
Step 1.1 — Fetch CI status
$GH pr checks <number> --repo <owner/repo>
Parse the output to identify check names, states (`pass`, `fail`, `pending`), and detail URLs.
Step 1.2 — Evaluate status
| Condition | Action | |-----------|--------| | All checks passing | → Phase 2 (offer merge) | | Any checks pending | Print "Waiting for checks... (N pending)". Wait 60 seconds. Loop. | | Any checks failed | → Step 1.3 (investigate and fix) | | PR closed or merged | Exit. Print "PR #<N> is already closed/merged." |
Step 1.3 — Fix failing checks
For each failed check:
**1. Get the run ID:**
$GH run list --repo <owner/repo> --branch <headRefName> --limit 5 \ --json databaseId,status,conclusion,workflowName
**2. Read failure logs:**
$GH run view <run-id> --repo <owner/repo> --log-failed
**3. Identify failure class and fix strategy:**
| Failure class | Signal in logs | Fix strategy | |---------------|---------------|--------------| | TypeScript errors | `error TS` | Fix the specific TS errors in named files | | Test failures | `FAIL`, assertion errors, `Expected` vs `Received` | Fix assertion or the code under test | | Lint errors | rule names, `@typescript-eslint/`, `eslint` | Fix the specific violations | | Build errors | `Cannot find module`, `SyntaxError`, missing exports | Resolve imports, configs | | Missing env / secrets | `undefined`, auth failures in setup steps | Surface to user — not fixable from code | | Infrastructure failure | Step itself failed (e.g., `actions/checkout`), network | Surface to user — not fixable from code |
**4. Apply fix:**
- Implement the minimum change to resolve the failing check
- Do NOT refactor, expand scope, or fix unrelated issues
- Run the equivalent check locally when possible to verify before pushing
**5. Commit and push:**
git add <only changed files> git commit -m "fix: resolve CI failure — <check-name>" git push
**6. Increment `fix_attempts++`**
**7. Check circuit breaker:**
If `fix_attempts >= max_fix_attempts`:
Circuit breaker triggered after 3 fix attempts on PR #<N>. Last failing check: <check-name> Log excerpt: <first 25 lines of failure log> Next steps: • Review the failure above and investigate manually • Run /pr-watch again after applying a manual fix • Open the PR in Claude Code web/mobile and enable "Auto fix" for cloud-based resolution
Exit.
**8.** Wait 30 seconds for CI
Ships withcitadel
An open-source operating layer for Claude Code and OpenAI Codex. Citadel routes requests, preserves repository state between sessions, coordinates parallel work, applies repository safeguards, and records evidence and handoffs around the coding agent you
Get the whole plugin
Stats
922
Stars
83
Forks
Active
Maintenance
JavaScript
Language
MIT
License
1d ago
Last commit
5mo ago
Created
Repo: SethGammon/Citadel
Other skills on citadel.
@sethgammonView SkillSkill
archon
Autonomous multi-session campaign agent. Decomposes large work into phases, delegates to sub-agents, reviews output, and maintains campaign state across…
@sethgammonView SkillSkill
ascii-diagram
Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed…
@sethgammonView SkillSkill
autopilot
Intake-to-delivery pipeline. Processes pending items from .planning/intake/: briefs new ideas, executes approved work through research → plan → build → verify.…
@sethgammonView SkillSkill
cost
Deep cost exploration and transparency. Shows real token usage, session costs, campaign spend, burn rates, and model breakdown. Reads Claude Code's native…
@sethgammonView SkillSkill
create-app
End-to-end app creation from a single description. Five tiers: blank project, guided, templated, fully generated, or feature addition to existing codebase.…
@sethgammonView Skill