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. Also TRIGGER when user asks to "execute a function", "run my function", "debug this function", "get function logs", "check execution status", "write function tests", "test my function handler", or "add test cases for my function". DO NOT TRIGGER for generic "write integration tests" or "write tests" without function context — ask which capability they want to test first. DO NOT TRIGGER for calling Falcon platform APIs from functions — use functions-falcon-api instead. DO NOT TRIGGER for workflow YAML or UI components. DO NOT TRIGGER for Playwright/e2e/browser tests — use e2e-testing instead.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body with executable code, clear workflows including validation feedback loops, and excellent progressive disclosure via a real reference bundle. The main weakness is moderate verbosity from restating the credential/security guidance in multiple places.

Suggestions

Consolidate the 'never use raw HTTP / env-var credentials' guidance — it appears in the credential table, the API Integrations section, and Common Pitfalls; state it once authoritatively and cross-reference.

Trim the 'SYSTEM INJECTION' preamble; the load-time behavioral instructions could be shortened since the description already conveys when to act.

Move the lengthy requirements.txt rationale and runtime/glibc versioning detail into a reference file to reduce SKILL.md token load.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and tables, but includes some over-explanation Claude does not need (e.g., the 'SYSTEM INJECTION' preamble, repeated restating of the 'raw HTTP bypasses OAuth/rate limiting/audit' point across the credential table, API integrations section, and Common Pitfalls) that could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste ready code (Go and Python FDK patterns, auth wiring, APIIntegrations calls), concrete CLI scaffolding commands, and a manifest example covering common cases with specific field guidance.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with validation and feedback loops (the 'Fixing a Function Missing Schemas' section has explicit recreate-then-update-YAML steps with a warning about 409 conflicts), though the deployment workflow relies on deferring to references rather than inlining every checkpoint.	4 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled one-level-deep references (Reference Files table mapping tasks to references/python-patterns.md, go-patterns.md, testing-patterns.md, execution-and-testing.md, code-review-checklist.md), all of which exist as real bundle files, and content appropriately split with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, complete, and distinctive description that explicitly covers both capabilities and trigger conditions with concrete phrases and negative boundary guidance. It is somewhat verbose, but the content earns its length rather than padding with fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (build/create serverless functions, execute, debug, get logs, check execution status, write function tests) plus specific SDK patterns (FDK handlers, collection integration), giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what ('Build serverless Go or Python functions for Falcon Foundry apps') and when (multiple 'TRIGGER when' clauses with concrete trigger phrases, plus 'DO NOT TRIGGER for' negative guidance).	5 / 5
Trigger Term Quality	Includes natural phrases users actually say ('create a function', 'run my function', 'debug this function', 'get function logs', 'test my function handler') plus synonyms and the CLI command 'foundry functions create', covering common variations.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear Falcon Foundry functions niche with distinct triggers and explicit disambiguation ('DO NOT TRIGGER for calling Falcon platform APIs — use functions-falcon-api instead'; routing away workflow YAML, UI components, e2e-testing), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: CrowdStrike/foundry-skills
Path: skills/functions-development/SKILL.md
Commit: 1854e7d

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.