functions-development
Build serverless Go or Python functions for Falcon Foundry apps. TRIGGER when user asks to "create a function", "write a serverless function", "build backend logic", runs `foundry functions create`, or needs help with FDK handler patterns, function testing, or collection integration from functions. DO NOT TRIGGER for calling Falcon platform APIs from functions — use functions-falcon-api instead. DO NOT TRIGGER for workflow YAML or UI components.
69
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 an excellent skill description that clearly defines its scope, provides rich trigger terms covering natural user phrases and CLI commands, and explicitly delineates boundaries with related skills via DO NOT TRIGGER clauses. It uses proper third-person voice throughout and is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: build serverless Go/Python functions, FDK handler patterns, function testing, collection integration. Also specifies the platform (Falcon Foundry) and languages (Go, Python). | 3 / 3 |
Completeness | Clearly answers both 'what' (build serverless Go/Python functions for Falcon Foundry apps) and 'when' (explicit TRIGGER clause with multiple scenarios). Also includes explicit DO NOT TRIGGER exclusions to prevent misuse, which goes beyond the minimum requirements. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'create a function', 'write a serverless function', 'build backend logic', 'foundry functions create', 'FDK handler patterns', 'function testing', 'collection integration'. Includes both user-facing phrases and CLI commands. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via DO NOT TRIGGER clauses that distinguish it from 'functions-falcon-api' (for API calls) and workflow YAML/UI components. The niche of serverless function authoring for Falcon Foundry is clearly carved out. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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, comprehensive skill that provides excellent actionable guidance for building Foundry serverless functions in both Go and Python. Its main strengths are the concrete, executable code examples, well-organized reference structure, and thorough coverage of pitfalls. Weaknesses include the unnecessary 'SYSTEM INJECTION' framing, some verbose explanatory sections, and the lack of an explicit step-by-step development workflow with validation checkpoints.
Suggestions
Remove the 'SYSTEM INJECTION' block — it wastes tokens on theatrical framing that doesn't add actionable value.
Add an explicit numbered workflow (scaffold → implement handler → test locally → validate → deploy) with validation checkpoints between steps.
Trim the 'Functions as a Last Resort' section to a brief bullet list without explanatory parentheticals — Claude already understands these concepts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary content: the 'SYSTEM INJECTION' block at the top is theatrical and redundant (Claude doesn't need to be told it's a specialist), the 'Functions as a Last Resort' section explains alternatives Claude likely knows, and some explanatory prose could be trimmed. However, the tables, code examples, and pitfalls list are dense and valuable. | 2 / 3 |
Actionability | Excellent actionability throughout — fully executable Go and Python handler examples, CLI scaffolding commands, manifest YAML, requirements.txt patterns, authentication code for both languages, and concrete error handling patterns. The code is copy-paste ready and covers the key scenarios. | 3 / 3 |
Workflow Clarity | While individual patterns are clear, there's no explicit end-to-end workflow for creating a function from scratch (scaffold → implement → test → deploy). The Common Pitfalls section serves as implicit validation guidance, but there are no explicit validation checkpoints or feedback loops for the multi-step process of building and deploying a function. | 2 / 3 |
Progressive Disclosure | Well-structured with a clear reference table pointing to python-patterns.md, go-patterns.md, and testing-patterns.md for detailed content. Use cases and reference implementations are cleanly separated. The main file provides enough to get started while clearly signaling where to find deeper content, all one level deep. | 3 / 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.