beekeeper-lab
37 verified skills
ai-team-library/claude/skills/close-loop
# Skill: Close Loop ## Description Verifies task completion by checking produced artifacts against the original acceptance criteria, runs quality checks, and closes the feedback loop between requesting and producing personas. If all criteria pass, the task is marked complete and downstream consumers are notified. If criteria fail, the task is returned to the producer with specific, actionable failure reasons. This skill enforces the quality contract that keeps the autonomous team reliable. ##
development
ai-team-library/claude/skills/release-notes
# Skill: Release Notes ## Description Collects completed work items, merged changes, and resolved issues from a release cycle and produces structured release notes, a changelog entry, and a known issues list. The skill reads task completion records, PR summaries, and the generation manifest to build a comprehensive picture of what changed, then formats it for both technical and non-technical audiences. This supports the DevOps/Release Engineer and Technical Writer personas. ## Trigger - Invo
development
ai-team-library/claude/skills/run
# Skill: Run ## Description Pulls the latest code from `main` and launches the desktop application. Designed for the workflow where development happens on a remote server and the app is run locally from freshly pulled code. ## Trigger - Invoked by the `/run` slash command. ## Usage ``` /run # Pull main and run /run main # Pull main branch and run (explicit) ``` ## Process 1. **Save current branch** — Record which branch we're on. 2. **Auto-stash if dirty** — If `git
development
ai-team-library/claude/skills/trello-load
# Skill: Trello Load ## Description Connects to Trello via the MCP server, pulls all cards from the Sprint_Backlog list, and creates well-formed beans directly from each card's content. Beans are created with **Approved** status (ready for work). After each bean is created, the source card is moved to the In_Progress list on Trello. This runs fully non-interactively — no user prompts, no clarifying questions — suitable for cron jobs or automated pipelines like `/long-run`. ## Trigger - Invok
tools
ai-team-library/claude/skills/ip-licensing
# Skill: IP & Licensing Analysis ## Description Performs intellectual property and licensing analysis for software projects, covering open source license compatibility, software patents, trade secrets, copyright ownership, and contributor license agreements (CLAs). The skill evaluates a project's IP posture by examining dependencies, contributions, and licensing declarations, then produces a structured assessment with risks, recommendations, and actionable remediation steps. This is the Legal
development
ai-team-library/claude/skills/regulatory-assessment
# Skill: Regulatory Compliance Assessment ## Description Performs a structured regulatory compliance assessment for software products, mapping applicable regulations (GDPR, CCPA, HIPAA, SOX, ADA, and others) to the product's data practices, user base, and operational jurisdictions. The skill conducts jurisdiction analysis, identifies compliance gaps against each applicable regulation, and produces a prioritized remediation roadmap. This is the Legal Counsel persona's primary regulatory analysi
development
ai-team-library/claude/skills/merge-bean
# Skill: Merge Bean ## Description Safely merges a bean's feature branch into the `main` branch. Handles pulling latest changes, detecting merge conflicts, and reporting results. This is the Merge Captain's primary operation — the final stage of the bean execution wave. ## Trigger - Invoked by the `/merge-bean` slash command. - Called automatically by `/long-run` as the final stage after bean verification. - Should be executed by the Team Lead (acting as Merge Captain) or the integrator-merg
development
ai-team-library/claude/skills/legal-drafting
# Skill: Legal Drafting ## Description Drafts and reviews legal documents for software products and services: Terms of Service (ToS), Privacy Policies, End-User License Agreements (EULAs), Data Processing Agreements (DPAs), and cookie consent notices. The skill produces structured, plain-language documents that address regulatory requirements (GDPR, CCPA, CAN-SPAM, COPPA, ePrivacy Directive) while remaining understandable to non-lawyers. Each document type follows a specific process tailored t
development
ai-team-library/claude/skills/new-adr
# Skill: New ADR ## Description Creates a new Architecture Decision Record from a structured template. Guides the author through capturing the context, decision drivers, considered options with tradeoffs, the chosen option with rationale, and consequences. Links the ADR to related stories or work items and assigns it a sequential number. This skill enforces ADR discipline so that architectural decisions are documented consistently and discoverable by the whole team. ## Trigger - Invoked by t
development
ai-team-library/claude/skills/notes-to-stories
# Skill: Notes to Stories ## Description Transforms unstructured input -- meeting notes, brainstorming dumps, feature requests, Slack threads, or plain-language descriptions -- into structured user stories with acceptance criteria, open questions, and identified risks. This skill is the BA persona's primary tool for converting raw requirements into actionable backlog items that the rest of the team can work from. ## Trigger - Invoked by the `/notes-to-stories` slash command. - Called by the
tools
ai-team-library/claude/skills/review-beans
# Skill: Review Beans ## Description Generates a filtered Map of Content (MOC) file linking to beans matching a given status and/or category, then opens Obsidian pointed at the `ai/beans/` directory. The user can review and edit bean files directly — including changing status from `Unapproved` to `Approved`. Edits happen in-place on real files. ## Trigger - Invoked by the `/review-beans` slash command. - Can be invoked by any persona or by the user directly. ## Inputs | Input | Type | Requ
development
ai-team-library/claude/skills/review-pr
# Skill: Review PR ## Description Performs a structured code review following a repeatable checklist: readability, correctness, maintainability, consistency with project conventions, test coverage, and security red flags. The review produces a verdict (ship, ship with comments, or request changes) with specific, actionable feedback tied to file locations. This skill can require "green checks" (passing tests and lint) as a prerequisite before the human-judgment review begins. ## Trigger - Inv
development
ai-team-library/claude/skills/scaffold-project
# Skill: Scaffold Project ## Description Creates the standard project folder structure from a composition spec. Produces the repo skeleton that all other skills and personas operate within: CLAUDE.md, `.claude/` agent/skill/hook directories, `ai/` context and output directories, README, and per-persona output folders. This is the structural foundation step in the Foundry pipeline (Select --> Compose --> Compile --> **Scaffold** --> Seed --> Export). ## Trigger - Invoked by the `/scaffold-pro
development
ai-team-library/claude/skills/telemetry-report
# Skill: Telemetry Report ## Description Parses telemetry data from all bean.md files and produces an aggregate summary of project metrics: total time invested, average bean duration, breakdowns by category and owner, and identification of outliers. ## Trigger - Invoked by the `/telemetry-report` slash command. ## Inputs | Input | Type | Required | Description | |-------|------|----------|-------------| | category | String | No | Filter to a single category: `App`, `Process`, or `Infra`. C
development
ai-team-library/claude/skills/threat-model
# Skill: Threat Model ## Description Performs a STRIDE-based threat analysis over a system's architecture, producing a structured threat model with identified threats, risk ratings, mitigations, and a security test checklist. The skill reads architecture documentation and context to identify trust boundaries, data flows, and entry points, then systematically evaluates each for Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, and Elevation of Privilege risks. This is
development
ai-team-library/claude/skills/update-docs
# Skill: Update Docs ## Description Detects documentation drift and refreshes project documentation to match the current state of the codebase. Compares README, runbooks, ADR index, architecture overview, and onboarding guides against recent changes (code, configuration, dependencies, API surface) and produces a list of stale sections with proposed updates. This skill prevents the common failure mode where documentation is accurate at launch but decays silently as the code evolves. ## Trigger
development
ai-team-library/claude/skills/validate-config
# Skill: Validate Config ## Description Checks configuration and secrets hygiene across the project. Detects hardcoded secrets, validates environment variable usage, verifies config schemas, ensures secrets come from expected sources (env vars, secret managers, encrypted files), and flags configuration that would break across environments. This skill catches the class of bugs where code works on one machine but fails in staging or production because of config assumptions. ## Trigger - Invoke
development
ai-team-library/claude/skills/validate-repo
# Skill: Validate Repo ## Description Runs a comprehensive health check against a generated project or any repo that follows the Foundry structure. Verifies folder expectations, required files, template completeness, broken internal links, and stack-specific tooling (lint, test, build commands). Produces a pass/fail checklist with actionable remediation for every finding. This skill works on any project regardless of stack because it adapts its checks based on the composition spec. ## Trigger
tools
ai-team-library/claude/skills/bean-status
# Skill: Bean Status ## Description Reads the beans backlog and produces a formatted summary of all beans grouped by status. Optionally includes task-level detail for active beans. This is the Team Lead's dashboard command for understanding what work is new, in progress, or complete. ## Trigger - Invoked by the `/bean-status` slash command. - Called by the Team Lead during planning, standups, or retrospectives. - Can be invoked by any persona who wants to see the current backlog state. ## I
development
ai-team-library/claude/skills/contract-review
# Skill: Contract Review ## Description Performs a structured review of software contracts, SLAs, vendor agreements, and Master Service Agreements (MSAs). The skill systematically analyzes each clause for risk exposure, identifies unfavorable terms, evaluates liability caps and indemnification provisions, flags auto-renewal traps and termination restrictions, and produces a redline-ready report with recommended changes. This is the Legal Counsel persona's primary contract analysis tool. ## Tr
tools
ai-team-library/claude/skills/long-run
# Skill: Long Run ## Description Puts the Team Lead into autonomous backlog processing mode. The Team Lead reads the bean backlog, selects the best bean to work on, decomposes it into tasks, executes the assigned wave (Developer and Tech-QA are mandatory; other specialists are assigned only when the bean needs them), verifies acceptance criteria, commits the result, and loops to the next bean. Continues until no actionable beans remain or an unrecoverable error occurs. ## Trigger - Invoked b
development
ai-team-library/claude/skills/new-dev-decision
# Skill: New Dev Decision ## Description Creates a lightweight developer decision record for implementation-level choices that don't rise to the level of a full ADR. Where ADRs capture architectural decisions (database choice, service boundaries, API strategy), dev decisions capture the smaller but still important choices made during implementation: library selection, algorithm approach, data structure choice, error handling strategy, or performance tradeoff. These decisions accumulate into a
development
ai-team-library/claude/skills/new-bean
# 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
development
ai-team-library/claude/skills/pick-bean
# Skill: Pick Bean ## Description Updates a bean's status from `Approved` to `In Progress`, assigning ownership to the Team Lead. This is the formal act of selecting a bean from the backlog for decomposition and execution. Only beans with `Approved` status can be picked — `Unapproved` beans must be reviewed and approved first. Updates both the bean's own file and the backlog index to keep them in sync. ## Trigger - Invoked by the `/pick-bean` slash command. - Called by the Team Lead during s
development
ai-team-library/claude/skills/risk-liability
# Skill: Risk Assessment & Liability Analysis ## Description Performs a structured legal risk assessment and liability analysis for a software project, evaluating legal exposure across six domains: contractual liability, indemnification obligations, limitation of liability provisions, insurance requirements, incident response legal obligations, and breach notification duties. The skill reads project context, contracts, and regulatory landscape to produce a comprehensive risk-liability report w
development
ai-team-library/claude/skills/seed-tasks
# Skill: Seed Tasks ## Description Decomposes project objectives into actionable, assignable tasks. Each generated task is scoped to a single work cycle, assigned to exactly one primary persona, given testable acceptance criteria, and linked to its dependencies. This skill bridges the gap between high-level goals and the concrete work items that personas execute. It runs during the Seed phase of the Foundry pipeline (Select --> Compose --> Compile --> Scaffold --> **Seed** --> Export). ## Tri
development
ai-team-library/claude/skills/backlog-consolidate
# Skill: Backlog Consolidation ## Description Detects and resolves duplicates, scope overlaps, contradictions, missing dependencies, and merge opportunities across recently created beans. Designed for post-refinement cleanup after running multiple `/backlog-refinement` sessions in parallel. The Team Lead analyzes all target beans, presents findings grouped by severity, and iterates with the user to apply agreed changes. ## Trigger - Invoked by the `/backlog-consolidate` slash command. - Shou
development
ai-team-library/claude/skills/backlog-refinement
# Skill: Backlog Refinement ## Description Turns raw ideas, feature descriptions, or broad vision text into one or more well-formed beans through an iterative dialogue. The Team Lead analyzes the input to identify distinct units of work, asks clarifying questions to understand scope and priority, then creates properly-formed beans using `/new-bean`. This is the primary intake mechanism for getting new work into the backlog. ## Trigger - Invoked by the `/backlog-refinement` slash command. - S
development
ai-team-library/claude/skills/build-traceability
# Skill: Build Traceability ## Description Maps user stories and their acceptance criteria to test cases, producing a traceability matrix that shows coverage relationships and identifies gaps. Every acceptance criterion should trace forward to at least one test case, and every test case should trace back to at least one requirement. This bidirectional mapping ensures nothing is tested without purpose and nothing is required without verification. ## Trigger - Invoked by the `/build-traceabili
development
ai-team-library/claude/skills/compile-team
# 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). ##
development
.claude/local/skills/health-check
# 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`
development
ai-team-library/claude/skills/new-work
# Skill: New Work ## Description Single entry point for initiating any unit of work: bug fix, feature, chore, spike, or refactor. Collects the work type, goal, constraints, urgency, and affected areas, then creates a Task Spec, optionally drafts a BA artifact (user story for features, bug report for bugs), and seeds initial tasks with the appropriate dependency wave. This skill replaces the need for separate bug/feature/chore commands by routing through one consistent funnel that adapts its ou
development
ai-team-library/claude/skills/handoff
# Skill: Handoff (Typed) ## Description Creates a **typed**, contract-aware handoff packet when one persona completes its phase and the next persona picks up. The packet is no longer a free-form dump — it is the typed intersection of what the **sender produces** and what the **receiver consumes**, with each artifact spelled out in the registry-required fields. The skill bridges `close-loop` (which verifies the sender's work) and the next persona's start (which now has a checkable schema instea
development
ai-team-library/claude/skills/vdd
# 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
development
ai-team-library/claude/skills/spawn-task
# 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
tools
ai-team-library/claude/skills/orchestration-report
# 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
ai-team-library/claude/skills/deploy
# Skill: Deploy ## Description Creates a release from the current `main` branch. Runs quality gates (tests, lint), reviews documentation, builds release notes from bean commits since the last tag, optionally tags the release, and cleans up merged feature branches. One approval, no extra prompts. With trunk-based development, feature branches merge directly to `main` via `/merge-bean`. The deploy skill validates the accumulated work on `main` and produces a tagged release. ## Trigger - Invok
development