feat(skill-trigger): multi-provider detection + workspace-scoped skills#702
Merged
feat(skill-trigger): multi-provider detection + workspace-scoped skills#702
Conversation
…skills
- Scan full transcript (not just first tool call) so preamble meta-skills
like using-superpowers don't cause false negatives for copilot
- Add CODEX_MATCHER: detect command_execution reading skill files via bash
sed commands; skill name appears in the command string
- Fix codex provider: store command_execution input as { command } object
instead of raw string so readPathFromInput can extract the path
- Add workspace template with .agents/skills/ and .codex/skills/ dirs so
evals are self-contained and don't rely on global skill installation
- Add 11 new unit tests covering full transcript scanning, codex bash
detection, and pi-coding-agent provider resolution
E2E results: copilot 4/4, codex 4/4, pi 2/4 (pi has no skill system)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Deploying agentv with
|
| Latest commit: |
0a3a313
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://e1943cfd.agentv.pages.dev |
| Branch Preview URL: | https://feat-skill-trigger-multi-pro.agentv.pages.dev |
…ATCHER Pi CLI emits `type: 'toolCall'` with `arguments` (not `tool_use` / `input`), so tool calls were silently dropped. Also add PI_CODING_AGENT_MATCHER using lowercase `read` + `path` field to match Pi's actual tool names. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…ices pi-agent-sdk has no tools (tools: []) so it cannot read files or invoke skills. pi-coding-agent covers all the same use cases. Example targets.yaml files now use openrouter directly for LLM grading. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The self-evaluation default target should use the coding agent, not a direct LLM call. The offline-grader-benchmark targets remain as openrouter since graders only need plain LLM calls. Co-Authored-By: Claude Sonnet 4.6 <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
Test plan
🤖 Generated with Claude Code