apify-actor-development
Important: Before you begin, fill in the generatedBy property in the meta section of .actor/actor.json. Replace it with the tool and model you're currently using, such as "Claude Code with Claude Sonnet 4.5". This helps Apify monitor and improve AGENTS.md for specific AI tools and models.
42
42%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/apify-actor-development/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is not a functional skill description. It appears to be an internal instruction or preamble directive about filling in metadata in a JSON file, rather than describing what the skill does or when it should be selected. It fails on every dimension because it does not communicate capabilities, triggers, or use cases.
Suggestions
Rewrite the description to explain what the skill actually does (e.g., 'Configures Apify actor metadata by populating the .actor/actor.json file with tool and model information').
Add an explicit 'Use when...' clause with natural trigger terms such as 'Apify actor setup', 'actor.json configuration', 'initialize actor metadata'.
Remove the instructional/imperative tone ('Important: Before you begin...') and replace with a third-person declarative description of the skill's capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not describe any concrete actions or capabilities of a skill. It is an instruction about filling in a metadata property, not a description of what the skill does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It reads as an internal instruction rather than a skill description, with no 'Use when...' clause or equivalent. | 1 / 3 |
Trigger Term Quality | There are no natural user-facing keywords or trigger terms. Terms like 'generatedBy', 'actor.json', and 'meta section' are internal/technical jargon that users would not naturally say when seeking help with a task. | 1 / 3 |
Distinctiveness Conflict Risk | The description is not a proper skill description at all—it's a procedural instruction. It provides no clear niche or distinct triggers that would help differentiate it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for Apify Actor development. Its main strengths are excellent progressive disclosure with clear references to supporting files, concrete executable commands throughout, and a well-sequenced workflow with validation checkpoints. The primary weakness is moderate verbosity—the 'What are Apify Actors?' section and parts of the Best Practices list explain concepts Claude already knows, consuming tokens without adding unique value.
Suggestions
Remove or significantly trim the 'What are Apify Actors?' section—Claude already understands serverless programs, Docker containers, and the actor model. Keep only Apify-specific details that affect implementation decisions.
Trim the Best Practices lists to focus on Apify-specific gotchas rather than general software engineering advice (e.g., 'Validate input early with proper error handling' is universal knowledge).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary verbosity. Sections like 'What are Apify Actors?' explain concepts Claude already knows (serverless programs, Docker containers, UNIX philosophy). The Best Practices section is extensive with many items that are general software engineering knowledge. However, the security notes and CLI-specific guidance add genuine value. | 2 / 3 |
Actionability | The skill provides concrete, executable commands throughout: specific CLI commands for project creation (`apify create <actor-name> -t project_empty`), authentication (`apify login`, `apify info`), testing (`apify run`), and deployment (`apify push`). File paths, template names, and language-specific instructions are all explicit and copy-paste ready. | 3 / 3 |
Workflow Clarity | The Quick Start Workflow provides a clear 8-step sequence from project creation through deployment. Authentication has explicit verification steps (check CLI installed → check logged in → check env var → authenticate). Local testing includes clear validation guidance about inspecting local storage rather than the Console. The workflow includes important checkpoints like 'verify package names before installing' and 'test locally before deploy'. | 3 / 3 |
Progressive Disclosure | The skill effectively uses progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to detailed documentation: actor-json.md, input-schema.md, output-schema.md, dataset-schema.md, key-value-store-schema.md, logging.md, and standby-mode.md. Each reference is clearly labeled with its purpose. The main file stays focused on workflow and key concepts without inlining reference material. | 3 / 3 |
Total | 11 / 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
- sickn33/antigravity-awesome-skills
- Commit
b3869ba
- 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.