skills: add aiXplain Agent Builder skill#907
Merged
Conversation
Adds a top-level skills/ folder modeled after anthropics/skills, containing the aiXplain Agent Builder skill — a portable skill for building, running, debugging, and deploying aiXplain agents from any skill-compatible AI coding agent (Claude Code, Cursor, etc.). - skills/README.md: overview of the skills collection - skills/aixplain-agent-builder/: SKILL.md, README, and reference playbooks Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replaces the generic "Zero-setup requirements" list with a narrative that walks through the ask -> plan -> approve -> deploy flow, links to the Studio visual builder and analytics dashboard, and calls out Python Sandbox as the automatic fallback when a capability isn't in the marketplace. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…liner, what-you-can-build table - Collapse "Who it's for" to a single sentence with bolded archetypes - Compact "Quick start" to 5 steps; move longer explanation into "How it works under the hood" - Merge "What the skill does for you" into the same section - Convert "What you can build" into a Mode / Say / Does table - Drop example that assumes scheduling (weekly email); use on-demand phrasing Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…ctices list - Add 8-item value prop list above "Who it's for" - Remove standalone "Best practices baked in" section (covered by item 6) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…es into "What you can build" - Remove bullets in "How it works" that duplicate the Why list; keep only unique details (plan contents, reuse, Studio links, key discovery order) - Merge "Sample queries to try" into the "What you can build" table as additional Build rows Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When a capability is not available as a marketplace tool/integration, the skill must announce in the plan that it will build a Python Sandbox function instead of stopping with "not found". Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
aix-ahmet
force-pushed
the
skills/add-agent-builder
branch
from
ac7c630 to
97a7ce9
Compare
aix-ahmet
approved these changes
Apr 9, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
skills/folder modeled onanthropics/skillsskills/README.mdlanding page with value props, quick start, "What you can build" list, and integration coverageTest plan
skills/README.mdrenders correctly on GitHubskills/aixplain-agent-builder/SKILL.mdloads in a skill-compatible agent🤖 Generated with Claude Code