Install
$ agentstack add skill-aws-samples-sample-ai-agent-skills-codecatalyst-troubleshooting ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Amazon CodeCatalyst Diagnostics
When to use
Any Amazon CodeCatalyst investigation — space creation, project configuration, workflow failures, action errors, dev environments, IDE connectivity, source repositories, pull requests, deployments, environment configuration, AWS connections, IAM roles, or blueprint errors.
Investigation workflow
Step 1 — Collect and triage
aws codecatalyst list-spaces
aws codecatalyst get-space --name
aws codecatalyst list-projects --space-name
Step 2 — Domain deep dive
aws codecatalyst get-project --space-name --name
aws codecatalyst list-workflow-runs --space-name --project-name --sort-by START_TIME
aws codecatalyst list-dev-environments --space-name --project-name
Step 3 — Detailed investigation
aws codecatalyst get-workflow-run --space-name --project-name --id
aws codecatalyst get-dev-environment --space-name --project-name --id
aws cloudtrail lookup-events --lookup-attributes AttributeKey=EventSource,AttributeValue=codecatalyst.amazonaws.com --max-results 20
Read references/guardrails.md before concluding on any CodeCatalyst issue.
Tool quick reference
| Tool / API | When to use | |------------|-------------| | codecatalyst list-spaces | List CodeCatalyst spaces | | codecatalyst get-space | Get space details | | codecatalyst list-projects | List projects in a space | | codecatalyst get-project | Get project details | | codecatalyst list-workflow-runs | List workflow runs | | codecatalyst get-workflow-run | Get workflow run details | | codecatalyst list-dev-environments | List dev environments | | codecatalyst get-dev-environment | Get dev environment details |
Gotchas: Amazon CodeCatalyst
- CodeCatalyst uses AWS Builder ID for authentication, NOT IAM users. Builder ID is a separate identity system from AWS IAM.
- Spaces are the top-level organizational unit. They are NOT AWS accounts. A space can be connected to multiple AWS accounts.
- Workflows use YAML definitions similar to but NOT identical to GitHub Actions. Do not assume GitHub Actions syntax works directly.
- Dev environments are cloud-based compute instances. They have configurable instance types and storage but are NOT EC2 instances you manage.
- AWS connections link CodeCatalyst spaces to AWS accounts. They require an IAM role in the target account with a trust policy for CodeCatalyst.
- Blueprints are project templates. They generate initial project structure but do NOT continuously manage the project after creation.
- Source repositories in CodeCatalyst are managed Git repositories. They support linking to external repositories (GitHub, Bitbucket) but these are separate from CodeCatalyst-native repos.
Anti-hallucination rules
- Always cite specific space names, project names, workflow run IDs, or API responses as evidence.
- CodeCatalyst uses Builder ID, NOT IAM users. Never suggest IAM user login for CodeCatalyst.
- Workflows are NOT GitHub Actions. Never assume GitHub Actions syntax or features.
- Dev environments are NOT EC2 instances. Never suggest EC2 management commands.
- Spend no more than 2 minutes on any single hypothesis. Pivot if inconclusive.
14 runbooks
| Category | IDs | Covers | |----------|-----|--------| | A — Space & Project | A1–A2 | Space creation, project configuration | | B — Workflows | B1–B2 | Workflow failures, action errors | | C — Dev Environments | C1–C2 | Dev environment issues, IDE connectivity | | D — Source Control | D1–D2 | Repository issues, pull request problems | | E — Deployment | E1–E2 | Deployment failures, environment configuration | | F — AWS Integration | F1–F2 | Connection to AWS, IAM role issues | | G — Blueprints | G1 | Blueprint errors | | Z — Catch-All | Z1 | General troubleshooting |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aws-samples
- Source: aws-samples/sample-ai-agent-skills
- License: MIT-0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.