ii-app

Use this skill when you need to initialize or restart local web and mobile app projects through the bundled Rust `ii-app` CLI instead of calling MCP tools.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./src/ii_agent/settings/skills/builtin/ii-app/SKILL.md

Quality

Content

72%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.

The content is highly actionable and well-structured with real, one-level-deep references, but it lists commands twice (costing conciseness) and omits validation/feedback checkpoints for its batch and setup operations, capping workflow clarity.

Suggestions

Collapse the duplicate command listing — keep either the intent-oriented bullets or the executable `Commands` block, not both — to recover token budget.

Add explicit validation checkpoints after setup/batch commands (e.g. confirm the web server is reachable after `web init`/`web restart`, verify the git checkpoint landed after `web checkpoint`, confirm `STRIPE_WEBHOOK_SECRET` was written after `stripe register-webhook`) with a fix-and-retry loop.

Add an error-recovery note for the build step (what to do when `scripts/build.sh` fails or `bin/ii-app` stays stale) so the workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no concept over-explanation, but each command appears twice — once in the opening bullet list and again in the `Commands` bash block — which is trimmable redundancy.	3 / 5
Actionability	The `Commands` block provides fully executable, copy-paste-ready invocations with all required flags, and the flags section enumerates concrete options (`--database-url`, `--host-url`, `--skip-install`, `--json`) covering the common cases.	5 / 5
Workflow Clarity	A clear numbered sequence is present with a staleness check, but setup/batch operations like `web init`, `web checkpoint`, and `stripe register-webhook` lack explicit post-action validation or error-recovery feedback loops, which the rubric caps at 3.	3 / 5
Progressive Disclosure	The body is a clean overview with two well-signaled, one-level-deep references (`references/template-ids.md`, `references/cli-contract.md`), both verified to exist, with bulk detail appropriately split out and commands kept inline as the core material.	5 / 5
	Total	16 / 20 Passed

Description

87%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.

The description is well-targeted: it states the domain, the concrete actions, the specific mechanism, and an explicit trigger clause while contrasting itself against the MCP alternative. Its only weakness is that it names just two command verbs rather than hinting at the fuller lifecycle it covers.

Dimension	Reasoning	Score
Specificity	Names the domain (local web and mobile app projects) and concrete actions (initialize, restart) via a specific mechanism (bundled Rust `ii-app` CLI instead of MCP tools), but the description surfaces only two of the command verbs rather than the full set (screenshot, status, checkpoint, stripe).	4 / 5
Completeness	Explicitly answers what it does (initialize/restart local web and mobile app projects through the bundled Rust CLI instead of MCP tools) and when to use it via the "Use this skill when you need to..." trigger clause.	5 / 5
Trigger Term Quality	"initialize or restart local web and mobile app projects" are natural trigger terms users would say, but common variations like "scaffold", "dev server", or "preview" are absent.	4 / 5
Distinctiveness Conflict Risk	"bundled Rust `ii-app` CLI instead of calling MCP tools" carves a precise, distinctive niche and explicitly disambiguates from the MCP-tool path, yielding minimal conflict risk.	5 / 5
	Total	18 / 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: Intelligent-Internet/ii-agent
Path: src/ii_agent/settings/skills/builtin/ii-app/SKILL.md
Commit: 28563d6

Reviewed: 5 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.