timholy/claude_config/freshen-runic
Claude Code and agent skill by timholy/claude_config
- community
Checking that the SKILL.md file is still in the repository.
Format a Julia package with runic, commit as a standalone PR, update .git-blame-ignore-revs, and install the runic post-edit hook
Install
npx vskill@latest install timholy/claude_config/freshen-runicSKILL.md
Format the Julia package in the current directory using runic, following these steps in order:
1. Verify tests pass
Run the test suite:
If there are failures, do not continue. Tell the user that this cannot continue until tests pass.
2. Verify a "clean slate"
Check that all of the following are true:
- the default branch is currently checked out
- there are no unmerged changes in tracked files
- the repository either lacks
.claude/settings.jsonor that file lacks the string "runic -i"
If any item on the list is false, do not continue. Report reason for stopping to the user.
3. Format source files
Run runic -i on all applicable directories:
src/(always)ext/(if it exists)test/(if it exists)
Also ensure that any tests are wrapped in an appropriately-named @testset.
4. Commit and open a PR
Check out a branch, stage all formatting changes, and commit with a message like "Apply runic formatting". This commit must contain only formatting changes — no functional changes. Open a pull request.
Pause here and wait for the user to confirm the PR has been merged before continuing.
5. Update .git-blame-ignore-revs
After the PR merges, add the merge commit SHA to .git-blame-ignore-revs (create the file if needed):
Then configure the repo to use it:
6. Install the runic post-edit hook
Create or extend .claude/settings.json in the project root to contain the following content (merge with any existing content rather than overwriting):
Stage .claude/settings.json. Prepare a proposed commit message and ask the user whether it should be committed.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/freshen-runic/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/timholy/claude_config/freshen-runic)