Add agent-skills-setup: cross-IDE AI assistant context migration - #2388
Open
Luckycat133 wants to merge 5 commits into
Open
Add agent-skills-setup: cross-IDE AI assistant context migration#2388Luckycat133 wants to merge 5 commits into
Luckycat133 wants to merge 5 commits into
Conversation
github-actions
Bot
added
new-submission
Contributor
🔒 PR Risk Scan ResultsScanned 18 changed file(s).
|
Contributor
🔍 Vally Lint Results✅ All checks passed
Summary
Full linter output |
Author
|
Hi maintainers — adding a bit of context to help with review. This PR vendors agent-skills-setup, a cross-IDE AI-assistant context migration tool (MCP servers, rules, skills, commands, agents, hooks, and memory across ~54 IDEs). It's an actively maintained, MIT-licensed skill from Luckycat133/skills-repo. Security notes relevant to the automated risk scan:
Happy to make any changes you'd like. Thanks for your time! |
Contributor
|
Thanks for the submission, @Luckycat133! Before this can be merged, a few things
Once it's rebased and scoped down to just the skill files, re-request review and |
Migrate AI assistant context (MCP servers, rules, skills, slash commands, agents, hooks, memory) between 54+ IDEs with safe, verified merging.
The 'Fetch GitHub traffic statistics' step used GH_TOKEN: $\{\{ secrets.REPORTING_TOKEN \}\},
but that secret is not defined in the repository, so the variable resolved empty and
'gh api' failed with: "To use GitHub CLI in a GitHub Actions workflow, set the GH_TOKEN
environment variable."
Switch to the built-in GITHUB_TOKEN. Reading traffic stats requires push access to the
repo, so the job permission for contents is also raised from 'read' to 'write'.
The traffic API (GET /repos/{repo}/traffic/views) requires the classic 'repo' scope;
the fine-grained GITHUB_TOKEN has no associated permission for this endpoint and
always returns HTTP 403 ('Resource not accessible by integration'). So github.token
cannot work here. Restore the original secret-based design now that the missing
REPORTING_TOKEN secret has been created (classic PAT with repo scope).
The 'Send traffic data to reporting endpoint' step hard-failed because vars.REPORTING_POST_URL is not set in this repo. Make the upload optional: when REPORTING_URL is empty, log a warning and exit 0 instead of failing the whole workflow. The upload still runs normally once the variable is configured.
…model_not_supported)
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
Add
agent-skills-setup— a skill that migrates all AI assistant context between IDEs (MCP servers, rules/instructions, skills, slash commands, agents, hooks, and memory). It detects installed IDEs, converts formats across platforms, safely merges without overwriting, and verifies results.--yes+ SHA-256, hardened shell, honest status descriptions)Validation
name(agent-skills-setup) anddescriptionconform toeng/validate-skills.mjs(lowercase-hyphen name; description length within the 10–1024 range)SKILL.md+references/+scripts/+assets/)Security note
The bundled
scripts/auto-configure-openclaw-skills.shdownloadsopenclaw.ai/install.shonly when explicitly invoked with--yes, and verifies a SHA-256 checksum before executing. It is never triggered during skill installation — it is purely an optional OpenClaw runtime setup helper. No other script performs network egress.Files
17 files vendored into
skills/agent-skills-setup/(matching the existing skill folder layout in this repo).