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

23%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.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 shell—it promises a 'comprehensive reference' with configuration templates, prompting strategies, debugging techniques, and best practices, but delivers none of these in the body. The content is just a purpose statement and three links to sub-skills with no standalone value. Without the bundle files to verify the sub-skills exist and contain quality content, this skill provides virtually no actionable guidance on its own.

Suggestions

Add actual configuration template content or a concrete CLAUDE.md example directly in the skill body so it provides standalone value even without sub-skills.

Include at least one executable example of a prompting strategy or thinking keyword usage pattern inline, rather than deferring everything to sub-files.

Add a quick-start workflow with concrete steps (e.g., 1. Create CLAUDE.md with this template, 2. Use these thinking keywords, 3. Debug with these techniques) so the skill is actionable on its own.

Either provide the bundle files for the referenced sub-skills or inline the critical content so the skill isn't an empty table of contents.

Dimension	Reasoning	Score
Conciseness	The content is short but includes some unnecessary filler like the 'Purpose' section which restates what the skill is. However, it's not overly verbose—it's more that the content is thin rather than padded.	2 / 3
Actionability	There is no concrete guidance, no executable code, no specific commands, no examples, and no configuration templates despite promising them. The entire body is essentially a table of contents with no actionable content of its own.	1 / 3
Workflow Clarity	There is no workflow described. The skill mentions 'create a CLAUDE.md file' but provides no steps, no content guidance, no validation, and no sequencing. The Configuration section has a heading with a single sentence and no actual configuration content.	1 / 3
Progressive Disclosure	The skill attempts progressive disclosure by linking to three sub-skill files, which is a reasonable structure. However, no bundle files were provided to verify these references exist, the overview itself contains almost no useful content, and the section headers promise content (like configuration templates) that isn't delivered at any level.	2 / 3
	Total	6 / 12 Passed

Description

25%

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 vague table of contents for a guide rather than a precise skill description. It lacks explicit trigger conditions ('Use when...'), concrete actions, and clear domain boundaries. The term 'Agent Code' is ambiguous and the listed topics are too broad to reliably distinguish this skill from others.

Suggestions

Add an explicit 'Use when...' clause specifying the exact scenarios that should trigger this skill, e.g., 'Use when the user asks about configuring, prompting, or debugging Claude's agentic coding mode.'

Replace vague category labels with concrete actions, e.g., 'Provides YAML configuration templates for agent sessions, lists effective "Thinking" trigger keywords like "think step by step," and offers debugging workflows for agent errors.'

Clarify what 'Agent Code' refers to (e.g., Claude's agentic coding feature, a specific tool) to reduce ambiguity and conflict risk with other coding or prompting skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Agent Code') and lists some actions like 'configuration templates, prompting strategies, debugging techniques,' but these are category labels rather than concrete, specific actions. It reads more like a table of contents than actionable capabilities.	2 / 3
Completeness	Describes what it contains at a high level but has no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is entirely missing, which per the rubric should cap completeness at 2, and the 'what' is also quite vague, bringing this to a 1.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'prompting strategies,' 'debugging techniques,' 'Thinking keywords,' and 'configuration templates,' but 'Agent Code' is ambiguous and the description lacks natural user-facing trigger terms a user would actually say when needing this skill.	2 / 3
Distinctiveness Conflict Risk	The description is very generic — 'best practices for interacting with the agent' and 'prompting strategies' could overlap with numerous other skills related to AI usage, coding assistance, or prompt engineering. 'Agent Code' is not a well-defined niche.	1 / 3
	Total	6 / 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: 061c4c6

Reviewed: about 12 hours 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.