Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/16-hsantanna88-clo-author/dot-claude/skills/tools

Utility commands — commit, compile, validate-bib, journal, context-status, deploy, learn. Replaces individual utility skills.

Tools

Utility subcommands for project maintenance and infrastructure.

Input: $ARGUMENTS — subcommand followed by any arguments.


Subcommands

/tools commit [message] — Git Commit

Stage changes, create commit, optionally create PR and merge.

  • Run git status to identify changes
  • Stage relevant files (never stage .env or credentials)
  • Create commit with descriptive message
  • If quality score available and >= 80, note in commit

/tools compile [file] — LaTeX Compilation

3-pass XeLaTeX + bibtex compilation.

For papers:

cd Paper && TEXINPUTS=../Preambles:$TEXINPUTS xelatex -interaction=nonstopmode [file]
BIBINPUTS=..:$BIBINPUTS bibtex [file_base]
TEXINPUTS=../Preambles:$TEXINPUTS xelatex -interaction=nonstopmode [file]
TEXINPUTS=../Preambles:$TEXINPUTS xelatex -interaction=nonstopmode [file]

For talks:

cd Talks && TEXINPUTS=../Preambles:$TEXINPUTS xelatex -interaction=nonstopmode [file]

/tools validate-bib — Bibliography Validation

Cross-reference all \cite{} keys in paper and talk files against Bibliography_base.bib. Report: missing entries, unused entries, duplicate keys.

/tools journal — Research Journal

Regenerate the research journal timeline from quality reports and git history. Shows chronological record of agent actions, phase transitions, scores, decisions.

/tools context — Context Status

Show current context status and session health. Check context usage, whether auto-compact is approaching, what state will be preserved.

/tools deploy — Deploy Guide Site

Render Quarto guide site and publish to GitHub Pages.

cd guide && quarto publish gh-pages --no-browser

/tools learn — Extract Learnings

Extract reusable knowledge from the current session. Auto-memory handles corrections automatically; this is for multi-step workflows worth turning into a full skill.

/tools upgrade — Upgrade Clo-Author Infrastructure

Upgrade an existing project to the latest clo-author architecture.

What it does:

  1. Clone the latest clo-author release into a temp directory
  2. Save the user's filled-in domain-profile.md and any custom journal profiles
  3. Delete the old .claude/ directory
  4. Copy the new .claude/ in
  5. Restore the user's domain-profile.md and custom journal profiles
  6. Optionally copy new templates/
  7. Report what changed

Workflow:

Step 1: DOWNLOAD
  - Clone latest clo-author into /tmp/clo-author-upgrade
  - Or: gh release download --repo hugosantanna/clo-author

Step 2: PRESERVE USER CUSTOMIZATIONS
  - Save .claude/references/domain-profile.md if filled in (not just placeholders)
  - Save any custom journal profiles the user added to journal-profiles.md
  - Save .claude/settings.json (user's permissions and hooks)
  - Save .claude/settings.local.json if it exists

Step 3: REPLACE
  - Delete old .claude/ entirely
  - Copy new .claude/ from the downloaded release
  - Restore saved customizations from Step 2

Step 4: DO NOT TOUCH
  - paper/, scripts/, data/, explorations/, quality_reports/
  - CLAUDE.md, Bibliography_base.bib, README.md, .gitignore
  - Any other user content

Step 5: REPORT
  - List what was updated (new agents, skills, rules)
  - List what was preserved (domain profile, settings, custom profiles)
  - Clean up temp directory

No git merge. No upstream remote. No conflicts. Just delete and replace .claude/.


Principles

  • Each subcommand is lightweight. No multi-agent orchestration needed.
  • Compile always uses 3-pass. Ensures references and citations resolve.
  • validate-bib catches drift. Run before commits to catch broken citations.
  • Upgrade preserves content. Infrastructure changes, your paper doesn't.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall