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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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

The body is well-organized and highly actionable with concrete commands and a clean progressive-disclosure structure backed by real reference files. Its main weaknesses are mild concept-explanation verbosity, some duplicated guidance across sections, and a workflow that lacks explicit validation feedback loops.

Suggestions

Remove or condense the "What are Apify Actors?" concept primer, since Claude already knows what serverless/containerized programs are, and deduplicate the generatedBy and apify-run reminders that recur across sections.

Add an explicit validate-then-fix feedback loop to the Quick Start Workflow, e.g. after `apify run`, list "if tests fail: inspect the storage/ output and logs, fix, then re-run" before proceeding to `apify push`.

Tighten the Best Practices list by merging the duplicated standby/logging entries so each rule appears once.

Dimension	Reasoning	Score
Conciseness	Most of the body is tight and actionable, but it explains concepts Claude already knows ("Actors are serverless programs inspired by the UNIX philosophy...") and repeats guidance in multiple places (the generatedBy note, the "use apify run not npm run start" rule, and the standby "only if true" note each appear 2-3 times).	2 / 3
Actionability	It provides copy-paste-ready commands throughout (`apify create <actor-name> -t project_empty`, `npm install`, `apify run`, `apify push`), concrete do/don't lists with specific deprecated options, and exact concurrency ranges (HTTP 10-50, Browser 1-5).	3 / 3
Workflow Clarity	The Quick Start Workflow gives a clear 8-step sequence including a local-test step before deploy, but it lacks explicit validation feedback loops (test -> diagnose -> fix -> retest) for the deploy/push operation, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	The body is an overview that cleanly offloads detail to one-level-deep, clearly signaled references (actor-json.md, logging.md, standby-mode.md, input/output/dataset/key-value-store schema docs), all of which exist as real files, making navigation easy.	3 / 3
	Total	10 / 12 Passed

Description

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 field is misused as a setup reminder about filling in `generatedBy` rather than describing the skill's purpose or triggers. It fails on every dimension because it communicates nothing about what the skill does or when to invoke it.

Suggestions

Rewrite the description to state the skill's purpose, e.g. "Create, modify, debug, and deploy Apify Actors...", and move the generatedBy reminder into the body's setup section instead of the frontmatter.

Add an explicit "Use when..." trigger clause listing natural phrasings like "Apify actor", "web scraping actor", "apify create", or "actor deployment".

Use third person and name concrete actions (bootstrap projects, wire input/output schemas, implement crawler logic, deploy with `apify push`) to improve specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names no capability of the skill; it only instructs the reader to "fill in the generatedBy property in the meta section of .actor/actor.json", which is a setup chore rather than a concrete skill action.	1 / 3
Completeness	It answers neither what the skill does nor when to use it; the entire text is a pre-flight instruction about populating a metadata field, so both the "what" and "when" are missing.	1 / 3
Trigger Term Quality	There are no natural trigger terms a user would say to invoke Apify actor development; the text mentions only "generatedBy property", "meta section", and "AGENTS.md", none of which map to a user's request phrasing.	1 / 3
Distinctiveness Conflict Risk	Because it conveys no skill purpose, it is indistinguishable from any other tooling skill and would not reliably trigger for Apify actor work; it reads as a generic config reminder.	1 / 3
	Total	4 / 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: sickn33/antigravity-awesome-skills
Commit: 2aaaf59

Reviewed: about 7 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.