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.
70
87%
Does it follow best practices?
Impact
—
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 and delegation boundaries. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., scaffolding, manifest creation, CLI commands executed) rather than summarizing as 'complete lifecycle from requirements through deployment'.
Suggestions
Expand the capability description with specific concrete actions, e.g., 'Scaffolds project structure, generates app manifests, configures CLI settings, and deploys Foundry apps' instead of the abstract 'complete lifecycle from requirements through deployment'.
| 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 clause with multiple scenarios, plus DO NOT TRIGGER exclusions and delegation guidance). The explicit trigger guidance is thorough. | 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. The anti-triggers (DO NOT TRIGGER) also help with precision. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche ('Falcon Foundry app lifecycle'). The description explicitly addresses conflict risk by specifying DO NOT TRIGGER conditions for sub-skills and warning against delegation to brainstorming/writing-plans skills. This is excellent boundary-setting. | 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 with concrete CLI commands, validation checkpoints, and error recovery guidance is well-crafted. Progressive disclosure is effective with clear delegation to sub-skills and reference files. The main weakness is moderate verbosity: the system injection block is repetitive, some warnings appear multiple times, and peripheral sections (improving skills, testing existing apps) could be moved to reference files to tighten the core flow.
Suggestions
Consolidate the --no-prompt and 'run from app root' warnings into a single 'CLI Rules' section instead of repeating them in the system injection block, Step 4, and Step 5.
Move 'Testing an Existing App Locally' and 'Improving These Skills' sections to reference files to reduce the main skill's token footprint and keep focus on the primary creation flow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content earns its place — CLI flags, gotchas, and dependency ordering are genuinely non-obvious. However, the system injection block at the top is excessively verbose and repetitive (e.g., the --no-prompt warning appears three times across the document, the 'MUST NOT hand off' instruction is stated in both the frontmatter description and the body). Some sections like 'Improving These Skills' and the testing workflow add bulk that could be separate references. | 2 / 3 |
Actionability | Excellent actionability throughout — every step includes exact CLI commands with correct flags, concrete examples of capability mapping (user says → CLI command table), specific bash commands for multi-cloud ID stripping with yq, and clear build/deploy sequences. Commands are copy-paste ready with real flag combinations. | 3 / 3 |
Workflow Clarity | The 7-step App Creation Flow is clearly sequenced with explicit dependency ordering (Collections → Functions → Workflows → UI). Validation checkpoints are well-placed ('VALIDATE EARLY — fail fast if specs or schemas are bad', 'If validation fails, STOP'). Error recovery is addressed (fix and retry, don't fall back to mkdir). The deploy-once-then-poll pattern with list-deployments is a clear feedback loop. | 3 / 3 |
Progressive Disclosure | The Reading Guide table at the bottom provides clear one-level-deep references to headless-operation.md, superpowers-integration.md, performance-optimization.md, counter-rationalizations.md, and advanced-patterns.md. The Decision Tree delegates capability-specific work to named sub-skills. Use-cases are referenced via glob pattern with a README catalog. Structure is well-organized with clear section hierarchy. | 3 / 3 |
Total | 11 / 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 | |
631c815
Table of Contents
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.