agent-code-guide

Master guide for using Agent Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

Quality

27%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.agent/skills/agent-code-guide/SKILL.md

Quality

Content

22%

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

This skill is essentially a hollow index page that delegates all substance to sub-skill files without providing any actionable content, examples, or workflows in the main body. It claims to cover configuration templates, prompting strategies, debugging techniques, and best practices but delivers none of these directly. The progressive disclosure structure is reasonable in concept but the main file needs to stand on its own with at least quick-start content.

Suggestions

Add a concrete CLAUDE.md configuration template or example directly in the skill body so users get immediate actionable value without needing to navigate to sub-skills.

Include at least 2-3 key best practices or quick-reference tips inline (e.g., specific thinking keywords, common debugging commands) before pointing to detailed sub-skills.

Define a clear workflow for getting started: e.g., 1. Create CLAUDE.md with template, 2. Configure thinking keywords, 3. Use debugging patterns—with concrete examples at each step.

Remove the vague Purpose section and replace it with a brief, actionable quick-start section that demonstrates immediate value.

Dimension	Reasoning	Score
Conciseness	The content is short but includes some unnecessary filler like 'To provide a comprehensive reference for configuring and using Agent Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced usage patterns.' which is descriptive rather than instructive. However, it's not excessively verbose.	2 / 3
Actionability	The skill provides no concrete code, commands, configuration examples, or executable guidance. It merely states 'create a CLAUDE.md file' without showing what should go in it, and delegates everything to sub-skills without providing any actionable content itself.	1 / 3
Workflow Clarity	There is no workflow, sequence, or process described. The skill is essentially a table of contents with no steps, no validation checkpoints, and no guidance on how to use the referenced sub-skills together or in what order.	1 / 3
Progressive Disclosure	The skill does reference sub-skills with clear one-level-deep links, which is good structure. However, the SKILL.md itself contains almost no substantive content—it's essentially an empty shell that delegates everything, and no bundle files were provided to verify the references exist or contain useful content.	2 / 3
	Total	6 / 12 Passed

Description

32%

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 reads like a topic outline rather than a functional skill description. It lacks explicit trigger guidance ('Use when...'), uses vague categorical terms instead of concrete actions, and could easily overlap with other coding or agent-related skills. The 'Master guide' framing adds no discriminative value.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about configuring Claude Code agent mode, writing effective prompts for agentic workflows, or debugging agent behavior.'

Replace vague categories with concrete actions, e.g., 'Provides YAML configuration templates for agent mode, lists trigger keywords for extended thinking, and offers step-by-step debugging workflows for agent errors.'

Remove filler phrases like 'Master guide' and 'effectively' that add no discriminative value for skill selection.

Dimension	Reasoning	Score
Specificity	Names the domain ('Agent Code') and lists some actions like 'configuration templates, prompting strategies, debugging techniques,' but these are categories rather than concrete specific actions. It reads more like a table of contents than actionable capabilities.	2 / 3
Completeness	Describes what it covers (configuration, prompting, debugging, best practices) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'Agent Code', 'prompting strategies', 'Thinking keywords', 'debugging techniques', and 'best practices', but these are somewhat generic. Missing natural user phrases like 'how to use agent mode', 'Claude agent tips', 'agentic coding', etc.	2 / 3
Distinctiveness Conflict Risk	'Agent Code' is somewhat specific, but terms like 'best practices', 'debugging techniques', and 'prompting strategies' are broad enough to overlap with many other coding or AI-related skills. The scope is unclear enough to risk false triggers.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: Dokhacgiakhoa/antigravity-ide
Commit: c4a059b

Reviewed: 17 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.