Diagnose failing GitHub Actions runs from bounded run, job, and step evidence, propose a focused fix, and modify the local checkout only when the requested task includes implementation.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add Devin-AXIS/iPolloWork --skill github-ci-debug --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Github Ci Debug?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/devin-axis-github-ci-debug)More formats (shields.io, HTML) on the badges page.
---
name: github-ci-debug
description: Diagnose failing GitHub Actions runs from bounded run, job, and step evidence, propose a focused fix, and modify the local checkout only when the requested task includes implementation.
disable-model-invocation: false
---
# GitHub CI Debug
Use this skill only for GitHub Actions failures.
## Workflow
1. Resolve the repository and Actions run ID from the supplied URL, PR, or current branch context.
2. Call `actions-failure` through the connected GitHub service.
3. Report the run URL, failing jobs, failing steps, and the most likely root cause supported by the returned evidence.
4. If the check belongs to an external provider, report its URL and do not pretend the GitHub service controls it.
5. Propose the smallest fix tied directly to the failing step.
6. When the user asked for a fix, implement it locally and run the relevant local check.
7. Summarize remaining uncertainty and what needs a remote rerun.
## Guardrails
- Do not rerun or cancel workflows; those actions are not part of this plugin version.
- Do not claim complete log coverage when the service returned only job and step summaries.
- Do not change code when the evidence points to an unrelated infrastructure or flaky failure unless the user chooses that scope.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
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', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
