claude-skills
Personal Claude Code skills, babysitter processes, agents, hooks, and commands.
Install on a new machine
git clone [email protected]:deedeeharris/claude-skills.git ~/claude-skills
cd ~/claude-skills && chmod +x install.sh && ./install.sh
Symlinks everything into the right locations. git pull to update — no re-install needed.
Claude cloud relay in Codex
The installer above links this skill into Claude Code along with the others. For Luna workers, use a Codex host that exposes Luna subagents and install the same folder in its user-level skill directory:
mkdir -p ~/.agents/skills
ln -s "$PWD/skills/claude-cloud-relay" ~/.agents/skills/claude-cloud-relay
Run this from the repository root. If that destination already exists, review the existing installation before replacing it. Start a new conversation and ask to use the skill. Claude Code itself does not expose OpenAI Luna workers; other hosts must disclose their model fallback.
See the relay setup guide for authentication, private configuration, and capability checks. The shareable skill contains no account details, saved credentials, session history, or personal preferences. Installing it does not activate a schedule or preserve login across fresh cloud environments.
Structure
| Folder | Symlinked to | What goes here |
|---|
skills/ | ~/.claude/skills/ | Claude Code skills (SKILL.md per folder) |
processes/ | ~/.a5c/processes/ | Babysitter process JS files |
agents/ | ~/.a5c/agents/ | Babysitter agent definitions |
hooks/ | ~/.claude/hooks/ | Claude Code hook scripts |
commands/ | ~/.claude/commands/ | Custom slash commands (.md files) |
Current contents
Skills
| Skill | Command | Description |
|---|
babysitter-multi-session | /babysitter-multi-session | Generate a run-sessions.sh script to chain multiple babysitter yolo sessions sequentially |
bh | /bh | Bug Hunter — scan, TDD-fix, conventions gate, code review, DoD gate, commit |
bh-forever | /bh-forever | Continuous bug hunting loop until convergence score ≥ 90 |
claude-cloud-relay | /claude-cloud-relay | Relay voice or typed instructions to existing Claude Code cloud sessions. Luna workers retrieve responses and verify message delivery; the main assistant gives short briefings. Selects the latest officially verified Luna model supported by the host. Includes PM scans, private checkpoints, and optional user-defined reply rules. Account-neutral; each user supplies their own login and preferences. Scheduled scans and PC Remote Control access require validation. |
codex-cli | /codex-cli | Codex CLI integration |
codex-review | /codex-review | Independent, out-of-family Codex review of an implementation diff, a PRD or a spec, with a PASS / FAIL / NEEDS_HUMAN verdict where blocking findings are independently validated by a second Codex call. Requires the OpenAI Codex CLI; used by gated-pipeline |
gated-pipeline | /gated-pipeline | Takes a feature from a raw task to a reviewed PR via in-session Claude Code Workflows: PRD → codex review → spec → codex review → test-first implementation → codex review + security pass → fix loop → full suite last → PR to the integration branch, with the human doing the merge. Works in any repo via a per-repo .claude/pipeline.yaml (template included). Requires the OpenAI Codex CLI and the codex-review skill (its scripts/run-review.js runner), which is not part of this repo. |
hebrew-rtl | /hebrew-rtl | Apply RTL Hebrew rules when generating any document with Hebrew text — fixes BiDi, punctuation, layout mirroring, comma placement. Use alongside pptx-generator, minimax-docx, minimax-xlsx, or minimax-pdf. |
gemini | /gemini |
Note: the prd-to-spec and task-to-prd skills are thin user-facing wrappers — they parse inputs, ask the user to pick /babysitter:call (interactive) or /babysitter:yolo (auto-approve), and dispatch to the matching process below.
Processes
| Process | Description |
|---|
bug-hunter.js | Babysitter process driving the full BH pipeline |
deep-plan-verification.js | Phase 0 plan verifier: 6-dimension parallel gap scan → dedup → prove gaps → self-answer → 3-judge review → consistency gate → quality score (target 95/100) |
prd-to-spec.js | Babysitter process that orchestrates the prd-to-spec skill: discovery (Verification Ledger) → SPEC generation → self-review (+ optional secondary reviewer) → user-approval breakpoint → execution prompt. Stack-agnostic. |
task-to-prd.js | Babysitter process that orchestrates the task-to-prd skill: source-load + Five Whys → interactive clarification → scope-lock breakpoint → PRD draft → 5 parallel verification checks (+ optional secondary review) → per-finding gate → final approval → optional tracker update + follow-up prompt. Stack-agnostic. |
Scripts
Standalone bash scripts and tools. See each folder for its own install instructions.
| Script | Description |
|---|
scripts/issue-loop.sh | Auto-fix GitHub issues in a loop using a 3-session babysitter pipeline: Session 1 writes a spec + runs /deep-verify-plan (≥95/100), Session 2 uses /writing-plans to produce a TDD task list, Session 3 implements with TDD + /verification-before-completion then commits and pushes. Quality gates validate each artifact. Rate limits are detected by multi-pattern regex, sleep until reset (parsed from Claude's output), and retry up to 5×. Rate-limit exhaustion skips the issue without marking it failed. Closes issues on success, labels needs-review on session failure. Stops when no open issues remain. Works on any git repo with gh + claude + jq + python3. |
scripts/deedeeharris-launch-cc-agents/ | Interactive menu to launch named Claude Code background agents. Menu-driven: pick by number or start all, detect already-running sessions, add/edit/remove agents. Works on Windows (Git Bash), macOS, Linux. Copy folder to ~/.claude/, run bash launch-agents.sh. |
Adding something new
New skill:
cp -r ~/.claude/skills/my-skill ~/claude-skills/skills/
cd ~/claude-skills && git add . && git commit -m "add skill: my-skill" && git push
New process:
cp ~/.a5c/processes/my-process.js ~/claude-skills/processes/
cd ~/claude-skills && git add . && git commit -m "add process: my-process" && git push
New agent / hook / command: same pattern — drop into the right folder, commit, push.
On any other machine: git pull and it's live instantly via symlinks.
