CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands and clean progressive disclosure to real reference files. Its main weaknesses are duplicated command listings and a workflow that omits explicit validation checkpoints for destructive operations.

Suggestions

Merge the prose command summary and the Commands code block into a single listing to remove redundancy and improve token efficiency.

Add explicit validation/verification steps to the Workflow (e.g., confirm the cache file was written, check that the tmux server started, verify the checkpoint commit succeeded) with a fix-and-retry loop for failures.

Note the known failure/cleanup behavior (e.g., init removes partial state on failure) inline so Claude can recover without reading the full CLI contract.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (no concept explanations), but the command set is listed twice — once as prose summaries and again as full invocations in the Commands block — which could be tightened into one combined listing.

2 / 3

Actionability

The Commands block gives fully executable, copy-paste-ready invocations with all flags and placeholders (e.g. '"<skill-root>/bin/ii-app" web init <template_id> --project-name <name> --workspace <dir>'), and the Useful flags section documents concrete flag behaviors.

3 / 3

Workflow Clarity

The four-step Workflow is sequenced, but it lacks explicit validation/verification checkpoints and feedback loops, and several operations (web init failing on existing dirs, checkpoint git commits, stripe webhook secret writes) are destructive or batch-like — capping this at 2 per the rubric.

2 / 3

Progressive Disclosure

Content is well sectioned and points to two real, one-level-deep reference files (references/template-ids.md and references/cli-contract.md, both present) with clear 'For X, read Y' signaling, keeping detailed material out of the overview.

3 / 3

Total

10

/

12

Passed

Description

65%

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 has an explicit 'Use this skill when' trigger and a clear, distinctive niche, but it uses second-person voice and its trigger keywords are somewhat narrow. Specificity is further capped by the rubric's third-person-voice penalty.

Suggestions

Rewrite in third person (e.g., 'Initializes and restarts local web and mobile app projects...') to avoid the second-person penalty and recover specificity.

Broaden trigger terms to include natural phrasings users would say, such as 'scaffold', 'dev server', 'preview', or 'Expo'.

Mention a couple more concrete capabilities (e.g., screenshots, status snapshots, git checkpoints) to lift specificity toward the top anchor.

DimensionReasoningScore

Specificity

Base specificity was 2 (names the domain and a couple of concrete actions — 'initialize or restart local web and mobile app projects' via the 'bundled Rust `ii-app` CLI' — but omits several capabilities like screenshot, status, checkpoint, and stripe webhook), reduced by 1 per the rubric guideline because the description uses second person ('you need to') instead of third person.

1 / 3

Completeness

It explicitly answers what ('initialize or restart local web and mobile app projects through the bundled Rust `ii-app` CLI instead of calling MCP tools') and when ('Use this skill when you need to...'), satisfying the explicit-trigger requirement for the top anchor.

3 / 3

Trigger Term Quality

Relevant keywords are present ('initialize or restart', 'web and mobile app projects') but common user variations like 'scaffold', 'dev server', 'preview', or 'Expo' are missing, matching the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The niche is clear — local app lifecycle through a specific bundled Rust CLI 'instead of calling MCP tools' — making it unlikely to trigger for unrelated skills.

3 / 3

Total

9

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Intelligent-Internet/ii-agent
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.