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.
47
Quality
35%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent/skills/agent-code-guide/SKILL.mdQuality
Discovery
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 provides a reasonable overview of the skill's content areas but lacks explicit trigger guidance, which is critical for skill selection. The capabilities listed are more like topic categories than concrete actions, and the description would benefit from natural user language and a clear 'Use when...' clause.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user asks about agent configuration, prompting techniques, or debugging agent behavior'
Include natural user phrases such as 'how to prompt the agent', 'agent not working', 'agent tips', 'Claude agent help'
Replace category labels with specific actions like 'Configure agent settings, craft effective prompts using Thinking keywords, troubleshoot agent errors'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('Agent Code') and lists some actions ('configuration templates, prompting strategies, debugging techniques'), but these are categories rather than concrete specific actions like 'extract text' or 'fill forms'. | 2 / 3 |
Completeness | Describes what it covers (configuration, prompting, debugging) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Agent Code', 'prompting strategies', 'Thinking keywords', 'debugging', but missing common user variations like 'Claude agent', 'agentic coding', 'agent tips', or 'how to use agent'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Agent Code' is somewhat specific, but 'prompting strategies' and 'best practices' are generic enough to potentially overlap with other guidance or documentation skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a skeleton/table of contents rather than a functional skill. While it's concise, it provides zero actionable content - no configuration templates despite promising them, no prompting strategies, no debugging techniques. The entire value is deferred to sub-skills, making the main skill nearly useless on its own.
Suggestions
Add a concrete CLAUDE.md template example directly in this skill so users can immediately copy-paste a starting configuration
Include at least one actionable quick-start section with specific commands or code before deferring to sub-skills
Add a brief workflow showing how to set up and iterate with Agent Code (e.g., 1. Create CLAUDE.md, 2. Run agent, 3. Review output, 4. Refine prompts)
Provide at least one concrete example of a 'Thinking keyword' or debugging technique inline, with sub-skills offering deeper coverage
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely lean with no unnecessary explanations. Every line serves a purpose - it's essentially a navigation hub with minimal overhead. | 3 / 3 |
Actionability | The skill provides no concrete guidance, code, or executable instructions. It only describes what exists and points to other files without any actionable content in the main skill itself. | 1 / 3 |
Workflow Clarity | There is no workflow defined. The skill mentions 'create a CLAUDE.md file' but provides no steps, no template, no validation, and no process to follow. | 1 / 3 |
Progressive Disclosure | References to sub-skills are present and one-level deep, but the main skill is essentially empty - it's all disclosure with no substance. The overview section lacks any quick-start content before pointing elsewhere. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%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
3395991
- 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.