// Use the Claude Code CLI as a depth-analysis co-pilot for paper-from-zero. Primary role: claim tree compression, logical hole detection, evidence sufficiency audit, and review/empirical routing judgment. Also supports generic code collaboration as fallback.
| name | collaborating-with-claude |
| description | Use the Claude Code CLI as a depth-analysis co-pilot for paper-from-zero. Primary role: claim tree compression, logical hole detection, evidence sufficiency audit, and review/empirical routing judgment. Also supports generic code collaboration as fallback. |
| metadata | {"short-description":"Depth co-pilot (Claude) for paper-from-zero"} |
Use Claude Code CLI as a depth-analysis collaborator for paper-from-zero, or as a generic code collaborator in fallback mode.
This skill provides a lightweight bridge script (scripts/claude_bridge.py)
that returns structured JSON and supports multi-turn sessions via SESSION_ID.
Shared rules: This skill inherits all shared rules from
../../_shared/collaboration-base.md(core rules, candidates-only constraint, fallback code-collaboration mode, safety guardrails, and collaboration state capsule format). Only Claude-specific additions are listed below.
ref.bib entries or verified citations.--help first if you are unsure of parameters.--cd set to the repo root.
Use --add-dir when Claude needs access to additional directories.--SESSION_ID (resume). Session selectors are mutually
exclusive: choose one of --SESSION_ID, --continue, or --session-id.claude
and /login once if needed).--verbose; the bridge enables this automatically.Claude Code supports model aliases, so you can use --model sonnet / --model opus instead of hard-coding versioned model IDs.
--model, Claude Code uses its configured default (typically from ~/.claude/settings.json, optionally overridden by .claude/settings.json and .claude/settings.local.json).--model <full-name>.claim-stress-test and route-review-vs-empirical templates, prefer opus.evidence-sufficiency-audit, sonnet is sufficient.If your prompt contains Markdown backticks, use a heredoc; see references/shell-quoting.md.
PROMPT="$(cat <<'EOF'
Review src/auth.py around login() and propose fixes.
OUTPUT: Unified Diff Patch ONLY.
EOF
)"
python3 .codex/skills/collaborating-with-claude/scripts/claude_bridge.py --cd "." --model sonnet --PROMPT "$PROMPT" --output-format stream-json
Output: JSON with success, SESSION_ID, agent_messages, and optional error / all_messages.
# Start a session
PROMPT="$(cat <<'EOF'
Analyze the bug in foo(). Keep it short.
EOF
)"
python3 .codex/skills/collaborating-with-claude/scripts/claude_bridge.py --cd "." --PROMPT "$PROMPT" --output-format stream-json
# Continue the same session
PROMPT="$(cat <<'EOF'
Now propose a minimal fix as Unified Diff Patch ONLY.
EOF
)"
python3 .codex/skills/collaborating-with-claude/scripts/claude_bridge.py --cd "." --SESSION_ID "<SESSION_ID>" --PROMPT "$PROMPT" --output-format stream-json
Use assets/prompt-template.md as a starter when crafting --PROMPT.
Paper-mode templates (top of the file):
claim-stress-test — adversarial review of contribution-map (use --model opus)route-review-vs-empirical — routing recommendation with adversarial self-challenge (use --model opus)evidence-sufficiency-audit — per-claim evidence sufficiency assessment (use --model sonnet)Each template specifies its input sources, output artifact mappings, and constraints.
check-collaborators skillpython3 .codex/skills/collaborating-with-claude/scripts/claude_bridge.py --help--output-format stream-json and confirm JSON contains success: true and a SESSION_ID.../../_shared/collaboration-base.md (shared rules)assets/prompt-template.md (prompt patterns)references/shell-quoting.md (shell quoting/backticks)Writes ML/AI review and survey papers for arXiv using the IEEEtran LaTeX template with verified BibTeX citations. Triggers when the deliverable is a review paper, literature survey, or when an existing LaTeX project needs citation validation or repair.
Verify that Gemini CLI and Claude Code CLI are installed, authenticated, and API-reachable before starting collaboration workflows.
Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero. Primary role: candidate direction expansion, adjacent work scanning, keyword cluster generation, and alternative framing proposals. Also supports generic code collaboration as fallback.
Draft IEEE-style empirical ML/AI papers from a structured research contract. Builds experiment plans, section skeletons, placeholder-safe results, and a near-submission draft without fabricating evidence.
Post-process LaTeX project prose to improve readability through varied sentence and paragraph lengths. Removes filler phrases and unnecessary transitions while preserving all citations and semantic meaning.
Route a fixed research topic into a rigorous paper-generation workflow. Handles active literature search, innovation framing, contribution/evidence planning, and routes to either the review writer or empirical writer skill.