ai-team-library/claude/skills/new-bean/SKILL.md
# Skill: New Bean ## Description Creates a new bean in the project's beans backlog. Assigns the next sequential ID, creates the bean directory with a `tasks/` subdirectory, populates `bean.md` from the project's bean template, and appends an entry to the backlog index. This is the standard way to add work items to the beans workflow. ## Trigger - Invoked by the `/new-bean` slash command. - Called by the Team Lead when new work is identified. - Can be invoked by any persona who identifies wor
npx skillsauth add beekeeper-lab/foundry ai-team-library/claude/skills/new-beanInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Creates a new bean in the project's beans backlog. Assigns the next sequential ID, creates the bean directory with a tasks/ subdirectory, populates bean.md from the project's bean template, and appends an entry to the backlog index. This is the standard way to add work items to the beans workflow.
/new-bean slash command.| Input | Type | Required | Description |
|-------|------|----------|-------------|
| title | Text | Yes | Short descriptive title for the bean |
| priority | Enum: Low, Medium, High | No | Defaults to Medium |
| problem_statement | Text | No | Description of the problem; can be filled in later |
Read the backlog index (fresh) -- Open ai/beans/_index.md right now, even if you read it recently. In a multi-agent environment, another agent may have added beans since your last read. Parse the Backlog table to find all existing bean IDs. Extract the highest BEAN-NNN number.
Compute next ID -- New ID = highest existing number + 1. Format as three-digit zero-padded: BEAN-006, BEAN-007, etc. Never pre-assign IDs — always derive the ID from the current state of _index.md at creation time.
Generate slug -- Convert the title to kebab-case:
Check for duplicates -- Verify no existing directory matches ai/beans/BEAN-{NNN}-{slug}/. If a collision exists, error with DuplicateSlug.
Create directory structure -- Create:
ai/beans/BEAN-{NNN}-{slug}/ai/beans/BEAN-{NNN}-{slug}/tasks/Populate bean.md -- Read ai/beans/_bean-template.md. Replace placeholders:
BEAN-NNN → the assigned ID[Title] → the provided titleUnapprovedMediumYYYY-MM-DD format(unassigned)ai/beans/BEAN-{NNN}-{slug}/bean.md.Update backlog index -- Append a new row to the Backlog table in ai/beans/_index.md:
| BEAN-{NNN} | {title} | {priority} | Unapproved | — |
Confirm -- Report: bean ID, directory path, and remind the user to fill in Problem Statement, Goal, Scope, and Acceptance Criteria if not provided.
| Output | Type | Description |
|--------|------|-------------|
| bean_directory | Directory | ai/beans/BEAN-{NNN}-{slug}/ with tasks/ subdirectory |
| bean_spec | Markdown file | ai/beans/BEAN-{NNN}-{slug}/bean.md populated from template |
| updated_index | Markdown file | ai/beans/_index.md with new row appended |
| confirmation | Text | Bean ID and directory path |
bean.md matches the template format with all metadata fields populated.tasks/ subdirectory exists and is empty (ready for Team Lead decomposition).| Error | Cause | Resolution |
|-------|-------|------------|
| NoTitleProvided | Title text is empty | Provide a descriptive title |
| IndexNotFound | ai/beans/_index.md does not exist | Create the beans directory structure first |
| TemplateNotFound | ai/beans/_bean-template.md does not exist | Create the bean template |
| DuplicateSlug | Directory already exists for this slug | Use a more specific title |
ai/beans/_bean-template.mdai/beans/_index.mddevelopment
# Skill: VDD (Verification-Driven Development) Gate ## Description Runs the programmatic VDD gate for a bean: parses the bean's `## Acceptance Criteria` section, dispatches each criterion's evidence type to the matching runner (test, lint, file, file-contains, or manual), aggregates the results into a pass/fail verdict, and writes a structured markdown report at `ai/outputs/tech-qa/vdd-<NNN>.md` (zero-padded NNN). This is the machine-checkable counterpart to the prose VDD policy in `ai/contex
tools
# Skill: Spawn Task ## Description Dispatches a single specialist persona to execute a single task with only that task's context. Auto-detects the runtime environment and chooses one of two execution paths: - **In tmux** (`$TMUX` set): spawn a worker in a git worktree using a child tmux window. Process-isolated, parallelizable, durable across the calling session's lifetime. Same pattern as `/spawn-bean` but at task granularity. - **Not in tmux**: invoke the `Agent` tool with `subagent_typ
development
# Skill: Orchestration Report ## Description Aggregates the per-bean **Orchestration Telemetry** blocks (BEAN-278) across recent Done beans and produces a markdown report that answers the architecture-aware-evaluation question: **is the orchestration paying for itself?** Distinct from `/telemetry-report` (which aggregates raw cost, duration, and tokens); this skill aggregates the orchestration-quality metrics layered on top — bounces, persona activations, contract violations, escape-hatch usag
development
# Skill: Health Check ## Description Runs all health checks defined in `ai/context/health-checks.md` and produces a table-format report. Can be called standalone or by other skills (e.g., `/long-run`). ## Trigger - Invoked by the `/health-check` slash command. - Called programmatically by `/long-run` at the start of each cycle. ## Inputs | Input | Type | Required | Description | |-------|------|----------|-------------| | health_checks | Markdown file | Yes | `ai/context/health-checks.md`