Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From coach
Approves a pending learning candidate by ID and applies the proposal to AGENTS.md or CLAUDE.md.
How this command is triggered — by the user, by Claude, or both
Slash command
/coach:approveThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Coach Approve Approve a pending learning candidate and apply it to CLAUDE.md. ## Arguments - `<id>` - The candidate ID to approve (e.g., "a1b2c3d4") ## Steps 1. Read `~/.claude-coach/candidates.json` and find the candidate by ID 2. Determine target location based on candidate scope: - Project scope → `<repo>/AGENTS.md` - Global scope → `~/.claude/CLAUDE.md` 3. Apply the proposal using the apply script: 4. Update the candidate status to "approved" in candidates.json 5. Confirm to user: - What rule was added - Where it was added (project/global) - The trigger and...
Approve a pending learning candidate and apply it to CLAUDE.md.
<id> - The candidate ID to approve (e.g., "a1b2c3d4")Read ~/.claude-coach/candidates.json and find the candidate by ID
Determine target location based on candidate scope:
<repo>/AGENTS.md~/.claude/CLAUDE.mdApply the proposal using the apply script:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/apply.py <id>
Update the candidate status to "approved" in candidates.json
Confirm to user:
If the candidate ID is not found, list available pending candidates.
npx claudepluginhub netresearch/claude-code-marketplace --plugin coach/reconcileFilters eligible learnings from learnings.jsonl, renders proposed .claude/rules/<slug>.md entries, and presents them for approval before writing. Supports --dry-run for preview only.
/setupRuns autocontext plugin first-run setup wizard via batched questions, configuring identity, test quality rules, lesson loading, persistence, and staleness. Saves to ~/.claude/autocontext.json.
/promotePromotes a Tasuku learning by ID to permanent project documentation like CLAUDE.md, auto-detecting target file or via --to FILE. Supports --keep to retain original.
/applyQueries Supabase for pending improvements, displays for interactive review with confidence scores, and applies approved changes to plugin files with backups. Supports --auto, --preview, --id.
/learnDisplays Claude Code best practices guide on sessions, context, memory, modes, CLI shortcuts, worktrees, and prompting. Also supports specific topics and saving session lessons to persistent memory.
/meta-agentManages the full CRUD lifecycle of Claude Code artifacts — commands, skills, rules, agents — with 9-phase workflow, quality gates, and multiple modes (create, enhance, audit, delete, rollback, list, onboard).