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.
87
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 with excellent trigger terms, clear completeness (both what and when), and outstanding distinctiveness through explicit anti-trigger boundaries. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., scaffolding, manifest generation, CLI commands) rather than summarizing as 'complete lifecycle from requirements through deployment'.
Suggestions
Add 2-3 specific concrete actions to replace the vague 'complete lifecycle' phrase, e.g., 'Scaffolds new Foundry apps, generates manifests, manages app configuration, and handles deployment via the Foundry CLI.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('Falcon Foundry app lifecycle') and mentions some actions ('requirements through deployment'), but doesn't list multiple specific concrete actions like creating manifests, scaffolding projects, running builds, etc. The phrase 'complete lifecycle' is somewhat vague. | 2 / 3 |
Completeness | Clearly answers both 'what' (orchestrates complete Falcon Foundry app lifecycle from requirements through deployment) and 'when' (explicit TRIGGER and DO NOT TRIGGER clauses with specific examples). The anti-trigger guidance for sub-skills and other skills adds further clarity. | 3 / 3 |
Trigger Term Quality | Excellent trigger terms: 'create a Foundry app', 'build a Foundry app', 'plan a Foundry app', 'foundry apps CLI command', 'Foundry app architecture'. These are natural phrases users would actually say, with good variation coverage. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit DO NOT TRIGGER boundaries that delineate this skill from sub-skills (UI, function, workflow, collection) and from other skills (brainstorming, writing-plans). The Falcon Foundry domain is a clear niche with minimal conflict risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%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 orchestration skill with excellent actionability and workflow clarity. The step-by-step flow from requirements parsing through deployment is well-sequenced with validation checkpoints and clear error recovery guidance. The main weakness is moderate verbosity — the system injection block and repeated warnings about --no-prompt and not delegating to superpowers could be condensed without losing clarity.
Suggestions
Consolidate the --no-prompt guidance into a single prominent note rather than repeating it in the system injection block, Step 4, and Step 5.
Tighten the system injection block — the 'MUST NOT hand off to superpowers' instruction is already in the skill description and could be a single line rather than a multi-line explanation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and code blocks, but includes some redundant warnings (the --no-prompt guidance is repeated multiple times, the 'MUST NOT hand off' instruction appears in both the system injection block and the description). The system injection block at the top is quite verbose with meta-instructions that could be tightened. | 2 / 3 |
Actionability | Highly actionable with specific, executable CLI commands for every step, concrete bash examples, a clear mapping table from user requests to capabilities, and precise flags (--no-prompt, --no-git). The multi-cloud deployment section includes exact yq commands and the testing workflow has copy-paste ready sequences. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit dependency ordering (Collections → Functions → Workflows → UI), clear validation checkpoints ('Validate early', 'fail fast if specs or schemas are bad', 'If validation fails, STOP'), feedback loops for error recovery, and explicit warnings about what NOT to do (don't deploy twice, don't fall back to mkdir). The deploy-poll-release sequence includes explicit polling instructions. | 3 / 3 |
Progressive Disclosure | Well-structured with a clear overview and decision tree at the top, detailed but focused main workflow, and a Reading Guide table at the bottom pointing to one-level-deep references (headless-operation.md, superpowers-integration.md, etc.). Capability-specific work is explicitly delegated to sub-skills. The use-cases directory is referenced with clear instructions on how to discover patterns. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- CrowdStrike/foundry-skills
- Commit
e7fa026
- 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.