メニュー
Use when: tracking work, adding todos, filing bugs, managing tasks/issues, checking what to work on, planning epics, deferring work, pre-PR checks, or any mention of bd/beads. Covers the full bd CLI.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when deciding how to manage, audit, sync, enable, disable, or troubleshoot skills and agents with the skillshare CLI across Claude Code, Codex, Gemini, OpenCode, Kiro, Goose, Pi, Antigravity, or project-local .skillshare setups. Especially use for questions about global vs project mode, disabled-by-default policies, .skillignore/.agentignore, target drift, broken symlinks, duplicate skills, sync dry-runs, or whether to use skillshare versus a runtime-native tool such as Codex skill-manager.
Use when creating git commits or reviewing commit messages. Ensures messages follow the Conventional Commits specification v1.0.0, which enables automated changelogs and semantic versioning. Invoked when the user wants to commit changes, craft a commit message, or validate an existing one.
Use when user references previous work phases, tasks, or discussions from prior sessions not present in current conversation context.
Use when designing or reviewing Python classes, deciding where logic belongs, or recognizing antipatterns like helper classes, utility bags, and god objects.
Use when crafting prompts that require factual accuracy, working with long documents, generating claims that need verification, or when outputs must be auditable and grounded in source material
Use when transitioning between work sessions and wanting to pick up where the previous session left off.
| name | beads |
| description | Use when: tracking work, adding todos, filing bugs, managing tasks/issues, checking what to work on, planning epics, deferring work, pre-PR checks, or any mention of bd/beads. Covers the full bd CLI. |
bd) — Skill ReferenceWhat it is: Git-native issue tracker (Dolt SQL DB at .beads/dolt/). Config committed to git; Dolt data is gitignored. Issue IDs: <prefix>-<slug> (e.g. ko2-tools-abc).
bd is the default task tracker. Any work item that should persist — bugs, features, follow-ups, test gaps — goes into bd, unless the project uses GitHub issues as its primary tracker (in which case bd handles personal/session/cross-project items only). TaskCreate/TaskUpdate is only for managing steps within a single task execution (ephemeral, not persisted).
Always use --json flag when parsing output programmatically.
bd prime # Load workflow context — run at start of every session
bd ready # Unblocked work (open + no active blockers)
bd ready is blocker-aware. bd list --ready is NOT equivalent.
bd q "Fix the thing" # Returns just the ID — fastest creation
bd todo add "Small task" # Lightweight task (type=task, P2)
bd create "Title" -d "details" -t bug -p 0 -l critical
bd q is for scripting/speed. bd todo add for lightweight tasks. bd create for full control.
Types: task bug feature epic chore decision
Priority: 0=critical 1=high 2=medium(default) 3=low 4=backlog — numeric only, never "high"/"low"
bd list # Open issues
bd list --all # Including closed
bd list -p 1 # By priority
bd list -l <label> # By label
bd list --status in_progress
bd show <id> # Full detail
bd blocked # All blocked issues
bd search <query> # Text search
bd stale # Forgotten issues needing attention
bd query "priority<2 AND status=open" # Compound filters
bd stats # Counts overview
bd update <id> --claim # Atomic: assignee + in_progress (fails if taken)
bd update <id> --status in_progress
bd update <id> --title "..." --priority 1
bd update <id> --append-notes "context"
bd update <id> --add-label foo --remove-label bar
bd comments add <id> "Progress note" # Add context without changing fields
NEVER use bd edit — opens $EDITOR, blocks agents.
bd close <id> # Mark done
bd close <id1> <id2> <id3> # Batch close (preferred)
bd close <id> --reason "text"
bd reopen <id>
bd defer <id> # Park for later (hidden from bd ready, visible in bd list)
bd undefer <id>
bd duplicate <id> --of <canonical-id> # Mark as dupe
bd supersede <old-id> --by <new-id> # Replace outdated issue
bd todo done <id> # Shorthand for closing task-type issues
bd dep add <issue> <depends-on> # issue depends on depends-on
bd dep <blocker> --blocks <blocked> # Equivalent, reverse syntax
bd dep tree <id> # Visualize dependency chain
bd dep list <id>
Direction: bd dep add A B → A depends on B → B must close before A unblocks.
bd create "Epic title" -t epic
bd create "Subtask" -t task --parent <epic-id>
bd epic status <epic-id> # Completion progress
bd children <epic-id> # List subtasks
bd remember "insight" # Store cross-session knowledge
bd memories # List all
bd memories <keyword> # Search
bd recall <key> # Retrieve
bd forget <key> # Delete
bd preflight # Pre-PR checklist
bd stale # Find forgotten issues
bd context # Show active repo/backend
| Wrong | Right |
|---|---|
bd list --ready | bd ready (blocker-aware) |
bd edit <id> | bd update <id> --field value |
priority "high" | priority 1 or P1 |
bd dep add A B thinking A blocks B | A depends on B (B blocks A) |
Looking in .dolt/ | DB is at .beads/dolt/ |
| MEMORY.md for cross-session insights | bd remember "..." |
| TodoWrite for persistent work | bd create / bd q / bd todo add |
bd close <id1> <id2> ... # Close all completed issues
bd preflight # Check for loose ends