diagnose-ci
Diagnose a failing CI run using the current revision and complete failure evidence.
Skill by MarkoArsov
Chalk Labs
Need help deploying diagnose-ci?
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/markoarsov-diagnose-ci
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: devops
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 and code. Checked Nov 2, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/diagnose-ci
What's inside
- Skill name
diagnose-ci- Description
- Diagnose a failing CI run using the current revision and complete failure evidence.
- License
- MIT
- Instructions
- 18 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- resolve.py · scripts/
SKILL.md (first lines)
<!-- resolver:start --> Run this skill folder's scripts/resolve.py from the active project once. If it returns a different effective skill, follow that file instead. Otherwise continue below. Use the selected package's bin/plovi for commands. <!-- resolver:end --> # diagnose ci 1. Resolve repository, branch, and exact run ID. Use GitHub checks and failure-log or the project's configured CI adapter. 2. Confirm the run's head revision matches the change being discussed. Read the failed job/step and relevant logs before guessing. 3. Distinguish code defects, test failures, infrastructure problems, dependency/authentication issues, and flaky evidence. Never disable checks to obtain green. 4. Reproduce the narrow failure locally where practical, implement an in-scope fix, and run the relevant checks. 5. Report observed cause, changed files, verification, and any external action still needed. Reruns, deployment changes, and comments follow the user's actual authorization.
From MarkoArsov/agent-workflow, MIT.
More from MarkoArsov/agent-workflow
- 0.564score
implement-tests
MarkoArsov
Author independent tests and obtain behavioral red evidence before product implementation.
SkillAFreshness: AClaude Code +9 - 0.564score
add-rule
MarkoArsov
Capture a recurring project convention with appropriate enforcement and a reviewable example.
SkillAFreshness: AClaude Code +9 - 0.564score
commit-and-push
MarkoArsov
Deliver verified task changes through guarded commits and normal pushes.
SkillAFreshness: AClaude Code +9 - 0.564score
draft-pr
MarkoArsov
Create an approved draft pull request for verified, pushed task branches.
SkillAFreshness: AClaude Code +9 - 0.564score
address-pr-comments
MarkoArsov
Retrieve complete PR feedback, implement selected fixes, and draft factual replies.
SkillAFreshness: AClaude Code +9 - 0.564score
implement
MarkoArsov
Implement an approved change and complete the named verification and correction loop.
SkillAFreshness: AClaude Code +9 - 0.564score
implement-pipeline
MarkoArsov
Preflight, start, observe, and recover a fresh-session implementation pipeline from an approved plan.
SkillAFreshness: AClaude Code +9 - 0.558score
peer-pr-review
MarkoArsov
Independently review another pull request and prepare actionable, unsent feedback.
SkillAFreshness: AClaude Code +9 - 0.558score
peer-rfc-review
MarkoArsov
Review a design proposal for requirements, tradeoffs, migration, and verification gaps.
SkillAFreshness: AClaude Code +9 - 0.558score
draft-rfc
MarkoArsov
Draft a focused design proposal with alternatives, rollout, and measurable acceptance.
SkillAFreshness: AClaude Code +9 - 0.558score
environment-status
MarkoArsov
Inspect configured local or shared test-environment readiness and ownership.
SkillAFreshness: AClaude Code +9 - 0.558score
checkout-branch
MarkoArsov
Resolve and switch to an existing requested branch or its registered worktree.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 28, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/MarkoArsov/agent-workflow
- Website
- stageway.markoarsov.com/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MarkoArsov
- 0.564score
draft-pr
MarkoArsov
Create an approved draft pull request for verified, pushed task branches.
SkillAFreshness: AClaude Code +9 - 0.564score
implement
MarkoArsov
Implement an approved change and complete the named verification and correction loop.
SkillAFreshness: AClaude Code +9 - 0.564score
commit-and-push
MarkoArsov
Deliver verified task changes through guarded commits and normal pushes.
SkillAFreshness: AClaude Code +9 - 0.564score
add-rule
MarkoArsov
Capture a recurring project convention with appropriate enforcement and a reviewable example.
SkillAFreshness: AClaude Code +9 - 0.564score
address-pr-comments
MarkoArsov
Retrieve complete PR feedback, implement selected fixes, and draft factual replies.
SkillAFreshness: AClaude Code +9 - 0.564score
implement-pipeline
MarkoArsov
Preflight, start, observe, and recover a fresh-session implementation pipeline from an approved plan.
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 diagnose-ci 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
diagnose-ci skill. Agent Mart. https://agentmart.dev/skills/markoarsov-diagnose-ci (last updated 2026-10-24)