local-test

Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/local-test/SKILL.md

Quality

Content

65%

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 concrete, executable Docker and Chrome MCP commands and a clear step sequence, but it is held back by repeated command/env blocks and the absence of inline validation feedback loops and any external reference structure.

Suggestions

De-duplicate the build command and the shared ONBOARD_COMPLETED/CLI_ENABLED env block by stating them once and showing only the differing variable per LLM backend.

Add an inline feedback loop in the Chrome MCP workflow (e.g. 'If the Connected indicator is absent, check docker logs and re-run read_page') instead of relying solely on the separate Troubleshooting section.

Consider moving the full per-backend run examples and troubleshooting catalogue into a referenced file (e.g. REFERENCE.md) so SKILL.md stays a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with executable commands, but the build command is repeated three times and the full required-env block is duplicated across five near-identical LLM backend examples, which could be tightened by stating shared flags once.	2 / 3
Actionability	It provides fully executable, copy-paste-ready docker build/run commands and exact MCP tool invocations (e.g. tabs_context_mcp, resize_window with concrete width/height), matching the anchor for fully executable guidance.	3 / 3
Workflow Clarity	The seven-step Chrome MCP workflow is clearly sequenced and includes a verify step ('Check for Connected indicator'), but it lacks inline validation/feedback loops tying a failed check to a fix-and-retry path; recovery guidance lives separately in Troubleshooting rather than as explicit checkpoints.	2 / 3
Progressive Disclosure	No bundle files exist and the content is a single ~200-line SKILL.md with everything inline; while sections are well organized, content that could be split out (the five LLM backend configs, the troubleshooting catalogue) is kept inline rather than referenced one level deep.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and action-oriented with a clear, distinctive niche, but it omits an explicit 'when to use' trigger clause and only partially covers natural trigger phrasings, capping completeness and trigger-term quality at 2.

Suggestions

Append an explicit 'Use when ...' clause naming natural user phrasings (e.g. 'Use when you want to test IronClaw changes locally, spin up a test container, or test the web gateway in Docker').

Add common natural trigger terms to the description itself (e.g. 'test my changes', 'local testing', 'test container'), not just to the activation keywords block.

Dimension	Reasoning	Score
Specificity	The phrase 'Build, run, and test IronClaw locally using Docker containers and Chrome MCP browser automation' lists multiple concrete actions (build, run, test) tied to specific tools (Docker, Chrome MCP), matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does but provides no explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	It mentions relevant terms like 'test', 'Docker', and 'locally', but lacks coverage of the natural phrasings a user would actually say (e.g. 'test my changes', 'spin up a test container'); trigger guidance lives only in the separate activation block, not the description.	2 / 3
Distinctiveness Conflict Risk	The product-specific scope ('IronClaw locally' with Docker + Chrome MCP) carves a clear niche with distinct triggers that are unlikely to conflict with other generic skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nearai/ironclaw
Path: skills/local-test/SKILL.md
Commit: b60038b

Reviewed: 2 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.