ai-team-library/claude/skills/compile-team/SKILL.md
# Skill: Compile Team ## Description Assembles a complete team configuration from AI Team Library components. Resolves persona, stack, and workflow references from a composition spec, checks for dependency conflicts, merges all resolved content into a unified CLAUDE.md constitution, and produces a generation manifest recording exactly what was compiled and from where. This is the core build step in the Foundry pipeline (Select --> Compose --> **Compile** --> Scaffold --> Seed --> Export). ##
npx skillsauth add beekeeper-lab/foundry ai-team-library/claude/skills/compile-teamInstall 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.
Assembles a complete team configuration from AI Team Library components. Resolves persona, stack, and workflow references from a composition spec, checks for dependency conflicts, merges all resolved content into a unified CLAUDE.md constitution, and produces a generation manifest recording exactly what was compiled and from where. This is the core build step in the Foundry pipeline (Select --> Compose --> Compile --> Scaffold --> Seed --> Export).
/compile-team slash command.foundry_app/services/compiler.py during pipeline execution.| Input | Type | Required | Description |
|------------------------|-----------------------------------|----------|--------------------------------------------------------------------|
| composition_spec | YAML file path | Yes | The composition defining personas, stacks, and workflows to include |
| library_path | Directory path | Yes | Root of the ai-team-library (contains personas/, stacks/, workflows/) |
| output_dir | Directory path | No | Where to write compiled output; defaults to ./build/ |
| validation_strictness | Enum: light, standard, strict | No | Validation level; defaults to standard |
persona.md, outputs.md, prompts.md, and any files under templates/ from the library.conventions.md and associated skill files from stacks/{stack}/.workflows/.generation-manifest.json.| Output | Type | Description | |----------------------|------------|--------------------------------------------------------------------| | compiled_claude_md | File | Unified CLAUDE.md team constitution ready for deployment | | generation_manifest | JSON file | Record of every source file, content hash, and compile metadata | | validation_report | Text | Warnings, info messages, or errors encountered during compilation |
| Error | Cause | Resolution |
|------------------------------|----------------------------------------------------|---------------------------------------------------------|
| InvalidCompositionSpec | YAML fails schema validation | Fix the composition YAML to match the CompositionSpec model |
| PersonaNotFound | Persona name in spec has no matching library folder | Check spelling; ensure the persona exists under personas/ |
| StackNotFound | Stack name in spec has no matching library folder | Check spelling; ensure the stack exists under stacks/ |
| MissingRequiredFile | A persona directory lacks persona.md or outputs.md | Add the missing file to the persona's library directory |
| DependencyConflict | Two stacks or personas declare incompatible rules | Remove one conflicting entry or resolve the conflict manually |
| OutputDirectoryNotWritable | The output_dir path is not writable | Check filesystem permissions or choose a different path |
foundry_app/core/models.py -- CompositionSpec and GenerationManifest data contractsfoundry_app/services/compiler.py -- reference implementation of the compile logicdevelopment
# 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`