progen

Use when the user wants to create/generate/scaffold a new Spring Boot project (Maven or Gradle, REST API / Web App / Spring Boot + Angular full stack). Derives progen CLI inputs from the user's plain-English project description, asks for any missing mandatory info, ensures the progen binary is available, and runs it to generate the project. If the user asks for features progen doesn't support natively, generate the base project first, then add those features on top of the generated code.

Quality

91%

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

82%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 commands, an exact config schema, and a clear six-step workflow. Its main gaps are a missing explicit fix→retry loop around progen warnings and a config table that borders on reference material better suited to a bundled file.

Suggestions

Add an explicit validate→fix→retry loop in Step 5: after `progen -c .progen.json`, if WARNING: lines appear for replaced enum defaults, correct the offending fields in `.progen.json` and re-run before proceeding.

Before generating, check whether a directory named after `AppName` already exists and confirm with the user or pick a new name, since progen writes into that directory and could clobber an existing project.

Consider moving the full config schema table into a `references/config-schema.md` file and keeping a condensed summary in SKILL.md, which would trim the body and let progressive_disclosure reach its top anchor.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no 'what is Spring Boot' padding), and the config table earns its place since field names must be exact JSON marshaling; minor trims possible in the macOS Gatekeeper aside and asset-naming workaround. Not a 5 because those tangential asides add tokens that aren't core to the workflow.	4 / 5
Actionability	Fully executable, copy-paste ready guidance: `progen --version`, the curl/tar/chmod/mv install sequence, `progen init`, and a complete `.progen.json` followed by `progen -c .progen.json`, plus an exact field/type/default table covering the common cases.	5 / 5
Workflow Clarity	Six steps are clearly sequenced with checkpoints (version check in Step 1, 'check the command output for these WARNING:' in Step 5), but there is no explicit validate→fix→retry feedback loop after warnings, and no check that the target directory doesn't already exist before generating. Not 3 because validation is present; not 5 because the error-recovery loop is only implied.	4 / 5
Progressive Disclosure	No bundle files exist and the skill is self-contained with clear numbered sections and a top overview; the large config schema table is borderline reference material but is core operational data needed at generation time, so inline placement is defensible. Not 5 because the skill exceeds ~50 lines and the schema table could arguably live in a references file for a leaner SKILL.md.	4 / 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, well-triggered description that cleanly answers what the skill does and when to invoke it, with natural synonyms and a distinct niche. It uses the conventional third-person/trigger voice with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Derives progen CLI inputs', 'asks for any missing mandatory info', 'ensures the progen binary is available', 'runs it to generate the project', 'generate the base project first, then add those features on top' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (derives config, ensures binary, runs progen, layers unsupported features) and 'when' ('Use when the user wants to create/generate/scaffold a new Spring Boot project...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrasing with synonyms and variants: 'create/generate/scaffold a new Spring Boot project', 'Maven or Gradle', 'REST API / Web App / Spring Boot + Angular full stack' — the terms a user would actually say when they need this skill.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Spring Boot scaffolding via the progen CLI) with distinct triggers; minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: sivaprasadreddy/sivalabs-agent-skills
Path: skills/progen/SKILL.md
Commit: 031ea5c

Reviewed: 4 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.