feat: Skills Abstraction (Phase 2)#4
Merged
Conversation
Define 10 built-in skills (claude-code, codex, opencode, gemini-cli, cursor, pi, github, web-browse, file-system, shell) with category, runtime, and provider compatibility metadata. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Built-in skills are returned with source='built-in' alongside company custom skills, ensuring they're always available even without DB rows. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fetch each agent's skills and render them as small icon+name pills on the agent card. Skills are fetched in parallel on page load and every 15s refresh cycle. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Creates scripts/migrate-skills-from-adapter.ts that reads agents with adapter_type set and creates corresponding built-in skill records and agent_skills entries. Maps claude_local→claude-code, codex_local→codex, gemini_local→gemini-cli, opencode_local→opencode, cursor→cursor, pi_local→pi. Copies cwd/command from adapter_config into skill config. Fully idempotent — skips existing links. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Skills section now fetches available skills from GET /api/skills, displays them in a categorized 2-column grid with icons and descriptions, and filters by compatibleProviders when agent has a provider set. Checked skills show a cyan highlight. Built-in skills now appear alongside custom company skills. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds src/lib/resolve-adapter-from-skills.ts which checks an agent's enabled skills to determine the execution adapter (e.g. claude-code skill → claude_local adapter). Falls back to adapter_type if no CLI skills are installed. Updates both start and task routes to use skill-based resolution, keeping full backward compatibility with adapter_type. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
1 participant
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
Adds the skills layer to the provider+skills architecture. Agents now have installable skills (Claude Code, Codex, GitHub, etc.) that determine their capabilities.
Changes (6 commits)
Built-in Skills Registry
src/lib/skills/built-in.ts: 10 built-in execution skills with provider compatibilityAPI
GET /api/skillsnow merges built-in skills with company custom skillsAgent Config UI
Agent Cards
Execution Engine
Migration
scripts/migrate-skills-from-adapter.ts: maps existing adapter_type to skill entriesNot Changed