CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

40

Quality

40%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/apify-actor-development/SKILL.md

The canonical home for this skill is apify-actor-development in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

The body is a well-structured, highly actionable guide that keeps detailed schema docs in seven real reference files and leads with a sequenced, validated workflow. Its main weakness is mild conceptual padding in the intro and best-practice sections that assumes too little of Claude.

DimensionReasoningScore

Conciseness

The body is mostly efficient with actionable commands and tight do/don't lists, but the "What are Apify Actors?" section explains a concept (serverless programs, UNIX philosophy) Claude already knows and could be trimmed; a few best-practice bullets could be tightened.

3 / 5

Actionability

Guidance is largely executable — concrete `apify create`/`run`/`push` commands, named templates, specific concurrency ranges (HTTP 10-50, Browser 1-5), and crawler recommendations — with only minor high-level gaps such as "Implement logic - Write the actor code in src/main.py".

4 / 5

Workflow Clarity

The 8-step Quick Start is clearly sequenced with validation checkpoints (verify CLI with `apify --help`, check login with `apify info`, test locally with `apify run` before `apify push`), plus a dedicated Local Testing section; minor gaps remain around explicit error-recovery feedback loops for the deploy step.

4 / 5

Progressive Disclosure

The body is a clear overview with well-signaled, one-level-deep markdown links to all seven existing reference files (actor-json, input-schema, output-schema, dataset-schema, key-value-store, logging, standby-mode), keeping detailed schemas out of SKILL.md while making navigation easy.

5 / 5

Total

16

/

20

Passed

Description

8%Weight 40%Scale 1-5

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 frontmatter description is mis-purposed: it reads as a setup reminder about populating a metadata field rather than describing what the skill does or when to trigger it. It fails the core what/when test and lacks natural trigger terms, which caps completeness and trigger quality at the floor.

Suggestions

Rewrite the description to state the skill's capability in third person, e.g. 'Develops, tests, and deploys Apify Actors — serverless containerized programs for web scraping and automation.'

Add an explicit 'Use when...' trigger clause naming natural phrases users say, e.g. 'Use when the user asks to build, test, or deploy an Apify Actor, scrape with Crawlee, or work with .actor/ configuration.'

Move the generatedBy fill-in instruction into the body (e.g. Prerequisites section) so the description is reserved for capability and trigger guidance.

DimensionReasoningScore

Specificity

The description names one concrete action ("fill in the generatedBy property in the meta section of .actor/actor.json") but this is a setup chore, not the skill's actual capability (Apify actor development); as a capability statement it is minimal and does not name the skill's domain.

2 / 5

Completeness

It answers neither "what does this skill do" nor "when should Claude use it" — the text is entirely a pre-flight instruction for filling in a metadata field, so both what and when are effectively missing.

1 / 5

Trigger Term Quality

Phrases like "generatedBy property", "meta section", and "Claude Code with Claude Sonnet 4.5" are setup jargon; none are natural keywords a user would say when they need to build an Apify actor, and there is no "Use when..." trigger language.

1 / 5

Distinctiveness Conflict Risk

The description does not distinguish this skill from others via its real purpose; the only distinguishing signal is the Apify-specific file path, leaving high overlap risk because nothing in the text identifies the actor-development niche.

2 / 5

Total

6

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.