AI agents were hallucinating incorrect package names like "anthropic/mcpc"
when seeing just "mcpc" in prerequisites. Updated all 9 SKILL.md files to
include the explicit installation command: npm install -g @apify/mcpc
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add mcpc search-actors command as fallback for discovering Actors not in the
curated 55-Actor list. Users can now search the full Apify Store directly when
no suitable Actor is found. Bump skill 1.2.0 → 1.3.0, marketplace 1.4.0 → 1.5.0,
and plugin 1.4.0 → 1.5.0.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Consolidate all 8 existing Apify skills (55 Actors) into a single AI-driven
universal scraper supporting Instagram, Facebook, TikTok, YouTube, Google Maps,
Google Search, Google Trends, Booking.com, and TripAdvisor. Includes Actor
selection by platform and use case, multi-actor workflow examples, and
suggested follow-up actions.
Bump marketplace version 1.2.11 → 1.3.0, plugin version 1.2.9 → 1.3.0, and
new skill version 1.0.0 → 1.1.0 (minor bump for new feature).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace individual actor reference files and workflows documentation with a single examples.md file that demonstrates common use cases. This consolidation reduces redundancy while maintaining comprehensive guidance.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove the --fields basic option and essential fields functionality:
- Delete ESSENTIAL_FIELDS dict from run_actor.py
- Remove --fields argument and related filtering code
- Remove get_nested_value() and filter_fields() helper functions
- Remove "Essential Fields" sections from all 18 actor documentation files
- Simplify SKILL.md examples to show only full data exports
The feature was not being used and adds unnecessary complexity.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix mcpc command to include authentication header and --json flag
- Update fetch-actor-details command to pipe through jq for content extraction
- Update documentation with improved step descriptions and output format options
- Reorganize actor reference structure with gotchas documentation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Correct input parameters for sortBy and propertyType fields, add missing
parameters (startUrls, flexWindow, starsCountFilter, minMaxPrice), and
update currency/language enums with complete values from actual Actor schema.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new competitor intelligence skill for analyzing competitor strategies,
content, pricing, ads, and market positioning across Google Maps, Booking.com,
Facebook, Instagram, YouTube, and TikTok.
- 17 actor schemas copied from lead-generation and brand-reputation-monitoring
- 11 new actor schemas generated from Apify Store
- Complete SKILL.md with workflow documentation
- reference/scripts/run_actor.py with actor runner and data export
- reference/workflows.md with multi-step competitor analysis examples
Marketplace version: 1.1.1 → 1.2.0
Skill version: 1.0.0 → 1.1.0
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move skills directly to skills/ folder (from plugins/*/skills/)
- Add multi-tool support (Codex, Gemini CLI, Cursor) via agents/AGENTS.md
- Add generate_agents.py script with auto-generation and version bumping
- Add GitHub Actions workflow for CI validation
- Add Claude Code hook for auto-regeneration on commit
- Update README with new repo URL (github.com/apify/agent-skills)
- Add gemini-extension.json for Gemini CLI compatibility
BREAKING CHANGE: Repository structure changed from plugins/ to skills/
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Dusan Vystrcil