Automated summary
Uses BuildBuddy to debug CI/CD failures by analyzing build invocations, logs, and targets via MCP tools.
Strengths
- Direct MCP integration without needing API keys
- Structured access to build metadata, logs, and artifacts
- Ideal for CI pipelines using BuildBuddy with Bazel
Limitations
- Requires manual extraction of invocation ID from links
- Only works for builds instrumented by BuildBuddy
- Large logs may require pagination
When you need to diagnose a CI build failure on a platform using BuildBuddy.
For local CI builds or those using a different remote build service.
Security analysis
SafeThe skill only uses safe, read-only commands (gh CLI to extract metadata) and MCP tools for build analysis. It explicitly discourages direct curl calls, and performs no destructive actions or data exfiltration.
No concerns found
How this analysis is madeExamples
Our CI build failed on invocation abc123 in BuildBuddy. Can you investigate why and show me the error logs?Get the target details for the last failed build in this PR and tell me which test failed and why.name: buildbuddy description: Use when debugging failed CI/CD jobs, analyzing build logs, or investigating GitHub Actions failures. Access BuildBuddy remote build execution and caching service for detailed build insights.
BuildBuddy - Remote Build Execution & CI Debugging
MCP Tools (Primary Interface)
Use BuildBuddy MCP tools via Context Forge. MCP handles authentication automatically.
Load tools with: ToolSearch query +buildbuddy
| Tool | Purpose |
| --------------------------------- | ---------------------------------- |
| buildbuddy-mcp-get-invocation | Build metadata, status, duration |
| buildbuddy-mcp-get-log | Full build logs (stdout/stderr) |
| buildbuddy-mcp-get-target | Target information and results |
| buildbuddy-mcp-get-action | Action details and execution info |
| buildbuddy-mcp-get-file | Download files by URI |
| buildbuddy-mcp-execute-workflow | Trigger a BuildBuddy workflow |
Debugging Failed CI
Workflow
GitHub PR fails
│
▼
gh pr checks ──► extract invocation ID from BuildBuddy URL
│
▼
ToolSearch +buildbuddy ──► load MCP tools
│
▼
buildbuddy-mcp-get-invocation ──► check success/failure, duration
│
▼
buildbuddy-mcp-get-log ──► find error messages
│
▼
Parse errors ──► fix root cause
Step 1: Get the Invocation ID
# Extract invocation ID from PR check links
gh pr checks --json link | jq -r '.[] | select(.link | contains("buildbuddy")) | .link' | grep -o '[^/]*$' | head -1
The invocation ID is the last path segment of the BuildBuddy URL:
https://jomcgi.buildbuddy.io/invocation/<invocation_id>
Step 2: Investigate with MCP Tools
Use the invocation ID with MCP tools — no API key or curl needed:
- Get overview:
buildbuddy-mcp-get-invocation— check.invocation.success, command, duration - Get logs:
buildbuddy-mcp-get-log— search for error/fail/fatal messages - Get targets:
buildbuddy-mcp-get-target— find which targets failed - Get actions:
buildbuddy-mcp-get-action— dig into specific action failures - Get files:
buildbuddy-mcp-get-file— download test outputs or artifacts
Tips
- Reproduce locally with
bazel test //... --config=ci - BuildBuddy logs may be paginated — use page tokens for large logs
- Check
.invocation.successboolean to quickly determine pass/fail - A PreToolUse hook blocks direct
curlto the BuildBuddy API — use MCP tools instead
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/buildbuddy-remote-ci-cd-debugging-mmbiziyd/download' --output '.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd/SKILL.md.part' && mv '.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd/SKILL.md.part' '.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd/SKILL.md' && test -s '.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/buildbuddy' && cp -R '.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd' '.claude/skills/buildbuddy'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd'openskills read 'buildbuddy-remote-ci-cd-debugging-mmbiziyd'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/buildbuddy-remote-ci-cd-debugging-mmbiziyd/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.