Create sync.yml for model skill synchronization#106
Create sync.yml for model skill synchronization#106chrismaz11 wants to merge 2 commits intomasterfrom
Conversation
Add a GitHub Actions workflow for cross model skill synchronization.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
There was a problem hiding this comment.
Pull request overview
Adds a GitHub Actions workflow intended to run a “Cross Model Skill Sync” action to validate/refresh model skill configurations across multiple adapters.
Changes:
- Introduces
.github/workflows/sync.ymlto runchrismaz11/Multi-Model-Skill-Sync - Configures target models for synchronization and optional reporting/fail-on-drift behavior
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
.github/workflows/sync.yml
Outdated
| - name: Cross Model Skill Sync | ||
| # You may pin to the exact commit or the version. | ||
| # uses: chrismaz11/Multi-Model-Skill-Sync@f4188af98f2d960acad17921b40a0ae0efeb3879 | ||
| uses: chrismaz11/Multi-Model-Skill-Sync@v1.0.0 | ||
| with: | ||
| # Repository root to manage. | ||
| repo-root: # optional, default is . | ||
| # Comma-separated model adapters to validate or refresh. | ||
| target-models: codex, claude, gemini | ||
| # Operation mode: validate or refresh. | ||
| mode: # optional, default is validate | ||
| # Fail the action when drift is detected. | ||
| fail-on-drift: # optional, default is true | ||
| # Path to write the JSON report to, relative to the repository root. | ||
| report-path: # optional, default is .ai/skills/reports/ai-skill-sync-report.json | ||
|
|
There was a problem hiding this comment.
This workflow file is not a valid GitHub Actions workflow as-is: it’s missing the required top-level keys (name, on, jobs) and the uses: step isn’t nested under jobs.<job_id>.steps. As written, GitHub will reject/ignore the workflow. Restructure the file into a complete workflow with at least one job and a step that uses this action.
| - name: Cross Model Skill Sync | |
| # You may pin to the exact commit or the version. | |
| # uses: chrismaz11/Multi-Model-Skill-Sync@f4188af98f2d960acad17921b40a0ae0efeb3879 | |
| uses: chrismaz11/Multi-Model-Skill-Sync@v1.0.0 | |
| with: | |
| # Repository root to manage. | |
| repo-root: # optional, default is . | |
| # Comma-separated model adapters to validate or refresh. | |
| target-models: codex, claude, gemini | |
| # Operation mode: validate or refresh. | |
| mode: # optional, default is validate | |
| # Fail the action when drift is detected. | |
| fail-on-drift: # optional, default is true | |
| # Path to write the JSON report to, relative to the repository root. | |
| report-path: # optional, default is .ai/skills/reports/ai-skill-sync-report.json | |
| name: Cross Model Skill Sync | |
| on: | |
| workflow_dispatch: | |
| jobs: | |
| sync: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Cross Model Skill Sync | |
| # You may pin to the exact commit or the version. | |
| # uses: chrismaz11/Multi-Model-Skill-Sync@f4188af98f2d960acad17921b40a0ae0efeb3879 | |
| uses: chrismaz11/Multi-Model-Skill-Sync@v1.0.0 | |
| with: | |
| # Repository root to manage. | |
| repo-root: # optional, default is . | |
| # Comma-separated model adapters to validate or refresh. | |
| target-models: codex, claude, gemini | |
| # Operation mode: validate or refresh. | |
| mode: # optional, default is validate | |
| # Fail the action when drift is detected. | |
| fail-on-drift: # optional, default is true | |
| # Path to write the JSON report to, relative to the repository root. | |
| report-path: # optional, default is .ai/skills/reports/ai-skill-sync-report.json |
.github/workflows/sync.yml
Outdated
| # Repository root to manage. | ||
| repo-root: # optional, default is . | ||
| # Comma-separated model adapters to validate or refresh. | ||
| target-models: codex, claude, gemini | ||
| # Operation mode: validate or refresh. | ||
| mode: # optional, default is validate | ||
| # Fail the action when drift is detected. | ||
| fail-on-drift: # optional, default is true | ||
| # Path to write the JSON report to, relative to the repository root. | ||
| report-path: # optional, default is .ai/skills/reports/ai-skill-sync-report.json |
There was a problem hiding this comment.
Several with: inputs are declared but left blank (repo-root:, mode:, fail-on-drift:, report-path:). In GitHub Actions, providing an empty value overrides the action’s default (it will pass an empty string/null), which can cause the action to misbehave. If you want defaults, omit these keys entirely; otherwise set explicit values (e.g., repo-root: ., mode: validate, etc.).
| # Repository root to manage. | |
| repo-root: # optional, default is . | |
| # Comma-separated model adapters to validate or refresh. | |
| target-models: codex, claude, gemini | |
| # Operation mode: validate or refresh. | |
| mode: # optional, default is validate | |
| # Fail the action when drift is detected. | |
| fail-on-drift: # optional, default is true | |
| # Path to write the JSON report to, relative to the repository root. | |
| report-path: # optional, default is .ai/skills/reports/ai-skill-sync-report.json | |
| # Comma-separated model adapters to validate or refresh. | |
| target-models: codex, claude, gemini |
.github/workflows/sync.yml
Outdated
| # Repository root to manage. | ||
| repo-root: # optional, default is . | ||
| # Comma-separated model adapters to validate or refresh. | ||
| target-models: codex, claude, gemini |
There was a problem hiding this comment.
target-models is provided as a single string containing commas and spaces (codex, claude, gemini). If the action parses this strictly, the spaces may become part of the model identifiers (e.g., " claude"). Prefer a no-space CSV (codex,claude,gemini) or the action’s documented list format (if supported).
| target-models: codex, claude, gemini | |
| target-models: codex,claude,gemini |
.github/workflows/sync.yml
Outdated
| # uses: chrismaz11/Multi-Model-Skill-Sync@f4188af98f2d960acad17921b40a0ae0efeb3879 | ||
| uses: chrismaz11/Multi-Model-Skill-Sync@v1.0.0 |
There was a problem hiding this comment.
The comment suggests pinning to a commit SHA, but the workflow uses a moving tag (@v1.0.0). For supply-chain security, prefer pinning to a full commit SHA (and optionally include the tag in a comment) so the workflow can’t change unexpectedly if the tag is moved.
| # uses: chrismaz11/Multi-Model-Skill-Sync@f4188af98f2d960acad17921b40a0ae0efeb3879 | |
| uses: chrismaz11/Multi-Model-Skill-Sync@v1.0.0 | |
| # v1.0.0 | |
| uses: chrismaz11/Multi-Model-Skill-Sync@f4188af98f2d960acad17921b40a0ae0efeb3879 |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: c8e6136c2d
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
.github/workflows/sync.yml
Outdated
| @@ -0,0 +1,16 @@ | |||
| - name: Cross Model Skill Sync | |||
There was a problem hiding this comment.
on and jobs
This file starts with a single step entry (- name: ...) instead of a workflow definition, so GitHub Actions cannot execute it as a workflow. In .github/workflows/, each workflow must define triggers and jobs at the top level; as committed, the intended sync automation will never run, which breaks the feature introduced by this commit.
Useful? React with 👍 / 👎.
|
@copilot apply changes based on the comments in this thread |
…puts Agent-Logs-Url: https://github.com/TrustSignal-dev/TrustSignal/sessions/167287b6-852f-43bc-8319-2f1726d9ce1d Co-authored-by: chrismaz11 <24700273+chrismaz11@users.noreply.github.com>
Applied all changes from the review thread in commit
|
Add a GitHub Actions workflow for cross model skill synchronization.
Summary
.github/workflows/sync.ymlwith a valid GitHub Actions workflow structure (name,on,jobstop-level keys) that runs thechrismaz11/Multi-Model-Skill-Syncactionf4188af98f2d960acad17921b40a0ae0efeb3879) instead of a moving tag for supply-chain securitytarget-modelsto a no-space CSV (codex,claude,gemini) to avoid unintended whitespace in model identifierswith:inputs (repo-root,mode,fail-on-drift,report-path) so the action uses its documented defaultsAI Disclosure (optional)
Review Checklist