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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%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 highly actionable, well-sequenced skill with strong validation checkpoints and clean one-level-deep progressive disclosure to real bundle files. The main weakness is repetition across the injection banner and MUST/MUST NOT guardrails that inflates token cost without adding information.

Suggestions

Consolidate the repeated CRITICAL/MUST NOT guardrails (cwd requirement, --no-prompt, no-mkdir, no manual manifest edits) into one authoritative section and reference it instead of restating each multiple times.

Trim the ALL-CAPS SYSTEM INJECTION banner to the essential routing rule; the detail it previews is repeated verbatim later in the body.

Move the counter-rationalization framing out of the hot path and rely on the dedicated counter-rationalizations.md reference, keeping the body focused on instructions.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands and tables, but the SYSTEM INJECTION banner, repeated CRITICAL warnings, counter-rationalizations references, and restated guardrails ('MUST NOT edit manifest.yml', 'MUST NOT fall back to mkdir') reappear multiple times, adding padding a tighter version could trim. It is above the verbose score-2 anchor but carries enough repetition to sit below the lean score-4/5 anchors.	3 / 5
Actionability	Fully executable, copy-paste-ready CLI commands with flags (e.g. 'foundry apps create --name "app-name" --description "description" --no-prompt --no-git') plus concrete tables mapping user phrases to commands, matching the score-5 anchor of copy-paste-ready guidance covering common cases.	5 / 5
Workflow Clarity	A clearly sequenced 7-step App Creation Flow with an explicit early validation checkpoint ('VALIDATE EARLY — fail fast'), feedback loops ('If validation fails, STOP. Fix the spec/schema'), and recovery guidance for headless/connection failures, matching the score-5 anchor including feedback loops for destructive/batch operations.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with a Reading Guide table pointing one level deep to real reference files (headless-operation.md, superpowers-integration.md, performance-optimization.md, counter-rationalizations.md, advanced-patterns.md, all present in ./references/), plus a detect_fusion_redirect.py script, with content appropriately split and easy to navigate, matching the score-5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

91%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 strong, third-person description with explicit trigger and anti-trigger guidance plus concrete CLI actions, covering both what and when clearly. Minor room to broaden the enumerated action list and tighten in-family distinctiveness.

Suggestions

List a few more concrete lifecycle actions (scaffold, implement, validate, deploy, release) explicitly in the description to push specificity toward 5.

Add a one-line distinction from the sibling Foundry sub-skills (e.g. 'use sub-skills for individual capabilities') to reduce in-family overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Orchestrates the complete Falcon Foundry app lifecycle from requirements through deployment', 'runs any `foundry apps` CLI command'), with a minor gap in enumerating the full set of lifecycle actions. It is above the score-3 anchor (which lists only 1-2 actions) but not quite the comprehensive multi-action list of a 5.	4 / 5
Completeness	Explicitly answers both what ('Orchestrates the complete Falcon Foundry app lifecycle from requirements through deployment') and when ('TRIGGER when user asks to...'; 'DO NOT TRIGGER when...') with concrete trigger phrases and a negative trigger boundary, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases users would actually say ('create a Foundry app', 'build a Foundry app', 'plan a Foundry app') plus the technical signal 'foundry apps CLI command' and file extension-style tokens, matching the score-5 anchor that expects synonyms and concrete variants.	5 / 5
Distinctiveness Conflict Risk	A clear Foundry niche with explicit DO-NOT-TRIGGER boundary and an explicit guard against confusing it with superpowers:brainstorming/writing-plans, giving minimal conflict risk. It is mostly distinct with only minor overlap risk against sibling Foundry sub-skills, so it sits above 3 but the in-family overlap keeps it just below 5.	4 / 5
	Total	18 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: CrowdStrike/foundry-skills
Path: skills/development-workflow/SKILL.md
Commit: c01ff6b

Reviewed: about 20 hours 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.