patchcue-resolve-issue
PatchCue worker workflow for Claude Code: resolve one GitHub issue solo in the worktree PatchCue provides, posting its marked plan and outcome comments.
Skill by fbserg
Chalk Labs
Need help deploying patchcue-resolve-issue?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fbserg-patchcue-resolve-issue
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/patchcue-resolve-issue
What's inside
- Skill name
patchcue-resolve-issue- Description
- PatchCue worker workflow for Claude Code: resolve one GitHub issue solo in the worktree PatchCue provides, posting its marked plan and outcome comments. Never merges. --resume continues a PatchCue run.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- protocol.md
SKILL.md (first lines)
# PatchCue Resolve Issue PatchCue launches this skill headless (`claude -p`) with one issue. The workflow, the marked `<!-- patchcue:plan -->` and `<!-- patchcue:outcome -->` comment protocol, the gate rules, and the resume rules live in `protocol.md` beside this file (the same text the Codex worker follows). Read `protocol.md` in full before any action, then follow it exactly. Claude-specific notes: - Work solo in the current directory. PatchCue already created the worktree; never create another and never spawn subagents. Ignore `--full`. - `gh` is authenticated as the PatchCue login. Every issue comment you post must use the exact marker lines from `protocol.md`; PatchCue parses them. - The launcher prompt adds `KIND:`, `UX_TWEAK:`, `REPORTER_ASK:`, and `OUTCOME: answered` on top of `protocol.md`. The launcher prompt wins where the two differ.
From fbserg/skill-issue, MIT.
More from fbserg/skill-issue
- 0.561score
epic-plan
fbserg
Scope a multi-deliverable or multi-session topic into a GitHub tracker issue plus child issues.
SkillAFreshness: AClaude Code +9 - 0.561score
simplify-sweep
fbserg
Batch-clean a range of pushed commits: headless Sonnet /simplify per area, review the edits, commit.
SkillAFreshness: AClaude Code +9 - 0.561score
resolve-issue
fbserg
One GitHub issue → review-ready PR via one worker in a worktree.
SkillAFreshness: AClaude Code +9 - 0.561score
deep-research
fbserg
Deep multi-source, fact-checked research report via the Workflow harness.
SkillAFreshness: AClaude Code +9 - 0.561score
blitz
fbserg
Run a batch of lanes, filed issues or ad-hoc, in parallel worktrees with adversarial review.
SkillAFreshness: AClaude Code +9 - 0.559score
herdr-share
fbserg
Share the current Herdr pane through a temporary browser link.
SkillAFreshness: AClaude Code +9 - 0.524score
resolve-issue
fbserg
Resolve one GitHub issue in Codex to a review-ready PR: one solo pass end to end in an isolated worktree — test-first, real checks, draft then ready.
SkillBFreshness: BClaude Code +9 - 0.524score
usage-review
fbserg
Review a body of AI-assistant transcripts (your own local Claude Code / Codex CLI sessions, or a shared exporter-markdown archive) into a red-teamed report…
SkillBFreshness: BClaude Code +9 - 0.524score
blitz
fbserg
Lightweight Codex executor for multiple ad-hoc tasks or lanes—fast, parallel, and adversarial—without the full issue or resolve-issue pipeline.
SkillBFreshness: BClaude Code +9 - 0.524score
issue
fbserg
Front door for GitHub issue work in Codex.
SkillBFreshness: BClaude Code +9 - 0.521score
adversary
fbserg
Cross-model adversarial review: dispatch Codex to attack a plan or diff before you commit to it.
SkillBFreshness: BClaude Code +9 - 0.521score
zero
fbserg
Zero out a repo — destructive cleanup of pending work, PRs, local and remote branches, worktrees, and main push.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- Oct 22, 2026 (10 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/fbserg/skill-issue
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fbserg
- 0.561score
deep-research
fbserg
Deep multi-source, fact-checked research report via the Workflow harness.
SkillAFreshness: AClaude Code +9 - 0.561score
epic-plan
fbserg
Scope a multi-deliverable or multi-session topic into a GitHub tracker issue plus child issues.
SkillAFreshness: AClaude Code +9 - 0.561score
resolve-issue
fbserg
One GitHub issue → review-ready PR via one worker in a worktree.
SkillAFreshness: AClaude Code +9 - 0.561score
simplify-sweep
fbserg
Batch-clean a range of pushed commits: headless Sonnet /simplify per area, review the edits, commit.
SkillAFreshness: AClaude Code +9 - 0.561score
blitz
fbserg
Run a batch of lanes, filed issues or ad-hoc, in parallel worktrees with adversarial review.
SkillAFreshness: AClaude Code +9 - 0.559score
herdr-share
fbserg
Share the current Herdr pane through a temporary browser link.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get patchcue-resolve-issue running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
patchcue-resolve-issue skill. Agent Mart. https://agentmart.dev/skills/fbserg-patchcue-resolve-issue (last updated 2026-10-24)