development-workflow

Orchestrates the complete Falcon Foundry app lifecycle from requirements through deployment. TRIGGER when user asks to "create a Foundry app", "build a Foundry app", "plan a Foundry app", runs any `foundry apps` CLI command, or discusses Foundry app architecture. DO NOT TRIGGER when user is working on a specific capability (UI, function, workflow, collection) within an existing app — use the appropriate sub-skill instead. This skill OWNS the entire Foundry development flow. Do not delegate Foundry app creation to superpowers:brainstorming or superpowers:writing-plans — those skills do not know about the Foundry CLI.

Quality

81%

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

81%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 orchestration skill with a clear sequenced workflow, strong validation checkpoints, and a good reference split. Its main weaknesses are redundant ALL-CAPS restatements of the same CLI gotchas across sections and two body-referenced paths (use-cases/, adapt_spec_for_foundry.py) that do not exist in the bundle.

Suggestions

Consolidate the repeated --no-prompt, cd-back-to-app-root, and no-mkdir-fallback rules into one canonical location (e.g. a 'CLI conventions' subsection) and reference it from Steps 4–7 and Manifest Coordination instead of restating them in ALL-CAPS each time.

Resolve the missing bundle references: either add the use-cases/ directory and adapt_spec_for_foundry.py to the bundle, or remove/soften the references to them in the Decision Tree, Step 1b, and the hallucination table.

Surface scripts/detect_fusion_redirect.py in the Reading Guide or where the fusion-redirect routing is discussed, since it ships in the bundle but is not pointed to from the body.

Dimension	Reasoning	Score
Conciseness	Content is command-dense and assumes Claude's competence (no concept bloat), but the SYSTEM INJECTION header and multiple ALL-CAPS rules restate the same gotchas (--no-prompt, cd-back-to-app-root, no-mkdir fallback) that recur across Steps 4–7 and Manifest Coordination, so it could be tightened; not a 4 because the redundancy is more than minor.	3 / 5
Actionability	Provides copy-paste-ready CLI commands with exact flags and dependency-ordered scaffolding covering the common cases (create, validate, deploy, release, multi-cloud), matching the fully-executable anchor.	5 / 5
Workflow Clarity	App Creation Flow is sequenced Steps 1–7 with explicit validation checkpoints ("VALIDATE EARLY — fail fast", stop and fix on validation failure) and feedback loops (deploy once, poll list-deployments, fix-and-retry), satisfying the anchor with validation and error-recovery loops.	5 / 5
Progressive Disclosure	A Reading Guide table maps tasks to five real, one-level-deep reference files that exist in references/, with clear navigation; however the body also references use-cases/*.md and adapt_spec_for_foundry.py, which are absent from the bundle, so references are mostly clear with a real organization gap rather than a clean 5.	4 / 5
	Total	17 / 20 Passed

Description

82%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 high-quality, third-person description that clearly states what the skill does and gives concrete positive and negative trigger guidance with strong distinctiveness. The only weakness is that the 'what' is a single broad lifecycle summary rather than an enumerated list of specific actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a broad concrete action ("Orchestrates the complete Falcon Foundry app lifecycle from requirements through deployment") but enumerates the lifecycle as a single summary rather than listing several specific concrete actions; not the level below (domain named with minimal/generic actions) nor above (lists several specific actions).	3 / 5
Completeness	Explicitly answers both what ("Orchestrates the complete Falcon Foundry app lifecycle from requirements through deployment") and when (concrete TRIGGER phrases plus DO NOT TRIGGER boundaries), matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ("create a Foundry app", "build a Foundry app", "plan a Foundry app"), the `foundry apps` CLI command, and "Foundry app architecture", but a few natural variations (e.g. deploy/scaffold) are absent, placing it above midpoint but short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Falcon Foundry app lifecycle) with distinct triggers, explicit DO NOT TRIGGER scope, and explicit non-delegation to superpowers:brainstorming/writing-plans, giving minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: CrowdStrike/foundry-skills
Path: skills/development-workflow/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.