debugging-workflows
Systematic troubleshooting for Falcon Foundry CLI errors, manifest validation failures, deploy failures, and development server issues. TRIGGER when user encounters CLI errors, `foundry ui run` not working, deploy failures, authentication issues, or any unexpected behavior during Foundry app development. Also trigger for headless/CI environment setup failures.
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies its domain (Falcon Foundry CLI troubleshooting), lists specific problem categories it handles, and provides explicit trigger conditions. The description is concise, uses third-person voice, and includes natural keywords that developers would use when encountering these issues.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions/domains: CLI errors, manifest validation failures, deploy failures, development server issues, headless/CI environment setup failures. These are concrete, actionable problem categories. | 3 / 3 |
Completeness | Clearly answers both 'what' (systematic troubleshooting for Falcon Foundry CLI errors, manifest validation, deploy failures, dev server issues) and 'when' (explicit TRIGGER clause listing specific scenarios like CLI errors, deploy failures, authentication issues, headless/CI setup failures). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'CLI errors', 'foundry ui run', 'deploy failures', 'authentication issues', 'CI environment setup failures', 'Foundry app development'. Good coverage of terms a developer encountering these issues would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Falcon Foundry CLI troubleshooting. The specific product name 'Falcon Foundry' and specific commands like 'foundry ui run' make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong troubleshooting skill with excellent actionability — concrete commands, decision trees, and a comprehensive symptom-to-fix table make it immediately useful. The workflow clarity is solid with good validation checkpoints and error recovery patterns. The main weaknesses are moderate verbosity in some sections (visual debugging, install failure narrative) and the monolithic structure that could benefit from splitting detailed subsections into referenced files.
Suggestions
Trim the Visual Debugging section — the bullet list of 'screenshots are effective for' largely restates issues already covered elsewhere; a single sentence pointing to screenshot-based diagnosis would suffice.
Consider extracting the Headless/CI section and the Common Issue Patterns table into separate referenced files to improve progressive disclosure and reduce the main file's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of decision trees and tables, but some sections are slightly verbose (e.g., the Visual Debugging section explains what screenshots are useful for at length, and the 'Debugging App Install Failures' section includes narrative that could be tightened). The pre-escalation checklist and some recovery strategies restate what's already covered. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout — bash commands with exact flags, environment variable names, config file formats with YAML examples, and specific CLI invocations. The headless environment section gives three distinct, copy-paste-ready solutions. The troubleshooting table maps symptoms directly to actions. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints (e.g., 'validate incrementally', 'fix and re-validate', the two-phase deployment explanation). The quick diagnosis decision tree provides clear branching logic. The app install debugging section has a clear 3-step isolation workflow with a concrete example of the feedback loop. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's a long monolithic file (~200 lines of substantive content) with no references to external files for detailed topics like headless setup or visual debugging. The one reference to 'e2e-testing/references/debugging-with-mcp.md' is good but the rest could benefit from splitting detailed sections into separate files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- CrowdStrike/foundry-skills
- Commit
631c815
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.