agent-toolkit-cli 1.12.0__tar.gz → 1.12.2__tar.gz

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: agent-toolkit-cli
-Version: 1.12.0
+Version: 1.12.2
 Summary: Composable AI agent toolkit — loops, skills, profiles, and MCP for Claude Code, Cursor, OpenCode, Windsurf, and more
 Project-URL: Homepage, https://github.com/ulises-jeremias/agent-toolkit
 Project-URL: Documentation, https://github.com/ulises-jeremias/agent-toolkit/tree/main/docs
@@ -31,7 +31,7 @@ License: MIT License
         SOFTWARE.
 License-File: LICENSE
 Keywords: agent-toolkit,agent-toolkit-cli,ai-agents,claude-code,cursor,github-copilot,loops,mcp,opencode,skills,windsurf
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -72,8 +72,8 @@ Description-Content-Type: text/markdown
 [![License: MIT](https://img.shields.io/badge/license-MIT-7c3aed?style=flat&labelColor=1f2937)](https://github.com/ulises-jeremias/agent-toolkit/blob/main/LICENSE)
 [![Validate](https://img.shields.io/github/actions/workflow/status/ulises-jeremias/agent-toolkit/validate.yml?branch=main&label=validate&style=flat&labelColor=1f2937)](https://github.com/ulises-jeremias/agent-toolkit/actions/workflows/validate.yml)
 
-![skills](https://img.shields.io/badge/skills-61-7c3aed?style=flat&labelColor=1f2937)
-![agents](https://img.shields.io/badge/agents-16-0891b2?style=flat&labelColor=1f2937)
+![skills](https://img.shields.io/badge/skills-77-7c3aed?style=flat&labelColor=1f2937)
+![agents](https://img.shields.io/badge/agents-17-0891b2?style=flat&labelColor=1f2937)
 ![loops](https://img.shields.io/badge/loops-10-ea580c?style=flat&labelColor=1f2937)
 
 [![Claude Code](https://img.shields.io/badge/Claude%20Code-plugin-7c3aed?style=flat&labelColor=1f2937&logo=anthropic&logoColor=white)](https://github.com/ulises-jeremias/agent-toolkit/tree/main/profiles/claude-code)
@@ -153,13 +153,13 @@ Full walkthrough: [docs/INSTALLATION.md](https://github.com/ulises-jeremias/agen
       <h3>🛠️ Skills</h3>
       <sub>Reusable capability units (<code>SKILL.md</code>) that teach an agent how to do a job — delivery, forge CLIs, design, data, ops.</sub>
       <br><br>
-      <sub>61 skills across 9 domains. Browse with <code>agent-toolkit inventory</code> or <code>agent-toolkit skills list</code>.</sub>
+      <sub>77 skills across domains. Browse with <code>agent-toolkit inventory</code> or <code>agent-toolkit skills list</code>.</sub>
     </td>
     <td width="50%" valign="top">
       <h3>🤖 Agents</h3>
       <sub>Personas that constrain <em>how</em> the AI works — review, plan, architect, fix CI — without rewriting prompts each time.</sub>
       <br><br>
-      <sub>16 personas, compiled into each target's native format via <code>install</code>.</sub>
+      <sub>17 personas, compiled into each target's native format via <code>install</code>.</sub>
     </td>
   </tr>
   <tr>

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/README.md

@@ -13,8 +13,8 @@
 [![License: MIT](https://img.shields.io/badge/license-MIT-7c3aed?style=flat&labelColor=1f2937)](https://github.com/ulises-jeremias/agent-toolkit/blob/main/LICENSE)
 [![Validate](https://img.shields.io/github/actions/workflow/status/ulises-jeremias/agent-toolkit/validate.yml?branch=main&label=validate&style=flat&labelColor=1f2937)](https://github.com/ulises-jeremias/agent-toolkit/actions/workflows/validate.yml)
 
-![skills](https://img.shields.io/badge/skills-61-7c3aed?style=flat&labelColor=1f2937)
-![agents](https://img.shields.io/badge/agents-16-0891b2?style=flat&labelColor=1f2937)
+![skills](https://img.shields.io/badge/skills-77-7c3aed?style=flat&labelColor=1f2937)
+![agents](https://img.shields.io/badge/agents-17-0891b2?style=flat&labelColor=1f2937)
 ![loops](https://img.shields.io/badge/loops-10-ea580c?style=flat&labelColor=1f2937)
 
 [![Claude Code](https://img.shields.io/badge/Claude%20Code-plugin-7c3aed?style=flat&labelColor=1f2937&logo=anthropic&logoColor=white)](https://github.com/ulises-jeremias/agent-toolkit/tree/main/profiles/claude-code)
@@ -94,13 +94,13 @@ Full walkthrough: [docs/INSTALLATION.md](https://github.com/ulises-jeremias/agen
       <h3>🛠️ Skills</h3>
       <sub>Reusable capability units (<code>SKILL.md</code>) that teach an agent how to do a job — delivery, forge CLIs, design, data, ops.</sub>
       <br><br>
-      <sub>61 skills across 9 domains. Browse with <code>agent-toolkit inventory</code> or <code>agent-toolkit skills list</code>.</sub>
+      <sub>77 skills across domains. Browse with <code>agent-toolkit inventory</code> or <code>agent-toolkit skills list</code>.</sub>
     </td>
     <td width="50%" valign="top">
       <h3>🤖 Agents</h3>
       <sub>Personas that constrain <em>how</em> the AI works — review, plan, architect, fix CI — without rewriting prompts each time.</sub>
       <br><br>
-      <sub>16 personas, compiled into each target's native format via <code>install</code>.</sub>
+      <sub>17 personas, compiled into each target's native format via <code>install</code>.</sub>
     </td>
   </tr>
   <tr>

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/hatch_build.py

@@ -7,7 +7,7 @@ The GitHub Release linux ELF needs GLIBC_2.38, so the honest tags are
 ``manylinux_2_38_x86_64`` and ``manylinux_2_38_aarch64``. Do not claim
 manylinux_2_17 / 2_35.
 
-When CI packs Release assets on a Linux runner (``scripts/pack_pypi.py``),
+When CI packs Release assets on a Linux runner (``scripts/pack_pypi.vsh``),
 set ``AGENT_TOOLKIT_WHEEL_TAG`` so the tag matches the bundled binary rather
 than the builder OS.
 """

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/pyproject.toml

@@ -14,7 +14,7 @@ keywords = [
     "github-copilot", "skills", "loops", "mcp", "agent-toolkit", "agent-toolkit-cli",
 ]
 classifiers = [
-    "Development Status :: 4 - Beta",
+    "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
     "Intended Audience :: Developers",
     "License :: OSI Approved :: MIT License",

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/src/agent_toolkit/__init__.py

@@ -1,4 +1,4 @@
 """agent-toolkit: Composable AI agent capabilities for all major AI coding tools."""
 
-__version__ = "1.12.0"
+__version__ = "1.12.2"
 __author__ = "ulises-jeremias"

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/src/agent_toolkit/cli/plugin.py

@@ -32,12 +32,12 @@ if _sys_win.platform == "win32":
 
 
 # ---------------------------------------------------------------------------
-# gen-surfaces logic (inlined from scripts/gen-surfaces.py)
+# gen-surfaces logic (inlined from scripts/gen-surfaces.vsh)
 # ---------------------------------------------------------------------------
 
 
 def _build_surfaces(toolkit_dir: Path) -> dict[str, list[tuple[str, str]]]:
-    """Return the plugin→surfaces mapping, mirroring scripts/gen-surfaces.py."""
+    """Return the plugin→surfaces mapping, mirroring scripts/gen-surfaces.vsh."""
     agents_dir = toolkit_dir / "agents"
     skills_dir = toolkit_dir / "skills"
 

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/src/agent_toolkit/data/agents/agentic-security-reviewer/AGENT.md

@@ -19,7 +19,7 @@ You are agentic-security-reviewer at agent-toolkit. Identify agentic vulnerabili
 | App/code vuln (OWASP Web: SQLi, XSS, IDOR) | security-reviewer |
 | System design tradeoffs | architect |
 | Agentic / prompt / tool / MCP / supply-chain (OWASP LLM01-10 + AGNT01-06) | you + skills/agentic-security/owasp-agentic-review |
-| Full supply-chain surface | agentic-security/supply-chain-audit + scripts/audit-capability.py |
+| Full supply-chain surface | agentic-security/supply-chain-audit (static Grep/Read; checkout/CI may use scripts/audit-capability.vsh) |
 | MCP config/impl | agentic-security/mcp-audit |
 | Threat model (STRIDE + agentic) | agentic-security/threat-modeling |
 
@@ -41,7 +41,7 @@ AGNT04 Data Leakage via Tool Output — tool output PII forwarded to external MC
 ## Workflow
 
 1. Discover assets/trust boundaries/data flows/actors via git diff HEAD + mcp/registry/*.yaml
-2. Run scripts/audit-capability.py --json + load_registry + scan for injection phrases + check upstream.lock digests
+2. Grep/Read for shell/network/mcp/hooks surface + scan for injection phrases + check upstream.lock digests (checkout/CI only: `v run scripts/audit-capability.vsh --json`)
 3. Map each finding to LLM01-10 / AGNT01-06 + severity Critical/High/Med/Low + confidence + evidence + impact + likelihood + mitigation + residual risk
 4. Emit findings evidence-cited, no hallucination — delegate to owasp-agentic-review skill for template
 

agent_toolkit_cli-1.12.2/src/agent_toolkit/data/catalogs/agent-catalog.yaml

@@ -0,0 +1,55 @@
+version: 1
+generated: true
+count: 17
+agents:
+  - id: agentic-security-reviewer
+    name: agentic-security-reviewer
+    description: 'Agentic security review specialist — prompt injection, tool poisoning, excessive agency, credential exposure, supply-chain, MCP/plugin security. Use after agentic capability changes or before adopti'
+  - id: architect
+    name: architect
+    description: 'Software architecture and system design specialist. Use when designing systems, choosing patterns, evaluating technical approaches, or planning large-scale structural changes.'
+  - id: assistant
+    name: assistant
+    description: 'agent-toolkit Dev Companion — follows internal conventions and best practices. Use for any work in agent-toolkit or client repositories to ensure compliance with agent-toolkit standards.'
+  - id: build-error-resolver
+    name: build-error-resolver
+    description: 'Build and TypeScript error resolution specialist. Use proactively when encountering compilation errors, type errors, lint failures, or CI pipeline failures.'
+  - id: client-workflow-bootstrap
+    name: client-workflow-bootstrap
+    description: agent-toolkit client workflow bootstrap specialist. Use when onboarding a new client project or updating an existing delivery workflow skill pair. Conducts a structured interview and generates <client
+  - id: code-reviewer
+    name: code-reviewer
+    description: 'Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying any significant code.'
+  - id: database-reviewer
+    name: database-reviewer
+    description: 'PostgreSQL and database specialist. Use for schema design, query optimization, migration review, index analysis, and ORM usage questions.'
+  - id: docs-lookup
+    name: docs-lookup
+    description: 'Documentation and API reference specialist. Use when searching for framework docs, library APIs, configuration options, or usage examples.'
+  - id: e2e-runner
+    name: e2e-runner
+    description: 'End-to-end testing specialist using Playwright. Use when writing, debugging, or running E2E tests, or when setting up Playwright test infrastructure.'
+  - id: performance-optimizer
+    name: performance-optimizer
+    description: 'Performance analysis and optimization specialist. Use when code is slow, has memory leaks, fails performance benchmarks, or needs profiling.'
+  - id: planner
+    name: planner
+    description: 'Expert planning specialist for complex features and refactoring. Use before starting any significant implementation to break down work, identify risks, and create an actionable plan.'
+  - id: refactor-cleaner
+    name: refactor-cleaner
+    description: 'Dead code cleanup and refactoring specialist. Use when removing dead code, simplifying complex functions, reducing duplication, or improving code structure without changing behavior.'
+  - id: reference-lookup
+    name: reference-lookup
+    description: 'Lookup agent-toolkit reference examples and patterns from public examples. Use when looking for official agent-toolkit examples, starter templates, or established patterns in the agent-toolkit ecosyst'
+  - id: security-reviewer
+    name: security-reviewer
+    description: 'Security vulnerability detection specialist. Use proactively after implementing authentication, data handling, API endpoints, or any user-facing functionality.'
+  - id: tdd-guide
+    name: tdd-guide
+    description: Test-Driven Development specialist. Enforces write-tests-first methodology. Use when implementing new features to ensure proper test coverage from the start.
+  - id: tech-assistant
+    name: tech-assistant
+    description: 'Technical operations assistant — ops specialist'
+  - id: typescript-reviewer
+    name: typescript-reviewer
+    description: 'TypeScript and JavaScript code review specialist. Use for type safety improvements, modern TS/JS patterns, and resolving type complexity issues.'

{agent_toolkit_cli-1.12.0 → agent_toolkit_cli-1.12.2}/src/agent_toolkit/data/catalogs/loop-catalog.yaml

@@ -6,12 +6,12 @@ loops:
     name: changelog-drafter
     tier: L1
     cadence: 1d
-    description: Draft release notes from merged PRs (L1, report-only)
+    description: 'Draft release notes from merged PRs (L1, report-only)'
   - id: ci-sweeper
     name: ci-sweeper
     tier: L2
     cadence: 15m
-    description: Detect CI failures and propose fixes via draft PRs (L2, cautious)
+    description: 'Detect CI failures and propose fixes via draft PRs (L2, cautious)'
   - id: daily-triage
     name: daily-triage
     tier: L1
@@ -26,7 +26,7 @@ loops:
     name: issue-triage
     tier: L1
     cadence: 4h
-    description: Propose labels and routing for new issues (L1, propose-only)
+    description: 'Propose labels and routing for new issues (L1, propose-only)'
   - id: oss-daily-briefing
     name: oss-daily-briefing
     tier: L1
@@ -36,20 +36,19 @@ loops:
     name: oss-pr-monitor
     tier: L3
     cadence: 1d
-    description: Monitor open PRs across OSS ecosystem repos and take action (L3,
-      daily)
+    description: 'Monitor open PRs across OSS ecosystem repos and take action (L3, daily)'
   - id: oss-triage
     name: oss-triage
     tier: L1
     cadence: 1d
-    description: Triage issues across OSS ecosystem repos (L1, daily)
+    description: 'Triage issues across OSS ecosystem repos (L1, daily)'
   - id: post-merge-cleanup
     name: post-merge-cleanup
     tier: L2
     cadence: 6h
-    description: Off-peak housekeeping after merges (L2, low impact)
+    description: 'Off-peak housekeeping after merges (L2, low impact)'
   - id: pr-babysitter
     name: pr-babysitter
     tier: L2
     cadence: 15m
-    description: Monitor open PRs and post review comments (L2, PR-gated)
+    description: 'Monitor open PRs and post review comments (L2, PR-gated)'

agent_toolkit_cli-1.12.2/src/agent_toolkit/data/catalogs/skill-catalog.yaml

@@ -0,0 +1,389 @@
+version: 1
+generated: true
+count: 77
+skills:
+  - id: accessibility/review
+    name: review
+    domain: accessibility
+    description: 'WCAG 2.2 AA curated accessibility review — distinguishes automatically detectable, browser-assisted, and manual/human-judgment findings with evidence citations and SC mapping. Composes with design-a'
+    stability: stable
+  - id: agentic-security/mcp-audit
+    name: mcp-audit
+    domain: agentic-security
+    description: 'MCP config + implementation security audit — config secrets/auth, unpinned versions, remote vs local, OAuth, env exposure; implementation command injection, SSRF, unsafe args, tool poisoning. Static'
+    stability: stable
+  - id: agentic-security/owasp-agentic-review
+    name: owasp-agentic-review
+    domain: agentic-security
+    description: 'OWASP-mapped agentic security review — prompt injection, tool poisoning, identity, excessive agency, credential exposure, supply-chain, insecure output handling, overreliance, data leakage, insecure'
+    stability: stable
+  - id: agentic-security/supply-chain-audit
+    name: supply-chain-audit
+    domain: agentic-security
+    description: 'Inspect agent supply chain — skills/plugins/MCP/npm/py packages, hooks, scripts, remote prompts, provenance, version pins, hashes, licenses, network and dangerous permissions — before adopting.'
+    stability: stable
+  - id: agentic-security/threat-modeling
+    name: threat-modeling
+    domain: agentic-security
+    description: 'STRIDE + agentic threat modeling — architecture discovery → assets/trust boundaries/data flows/actors → STRIDE + agentic threats → risk-ranked mitigations → incremental review → security a'
+    stability: stable
+  - id: architecture/c4-model
+    name: c4-model
+    domain: architecture
+    description: 'WHAT — C4 model methodology (Context, Container, Component, Code) guidance — what to draw at each level, when, and how to render C4-inspired diagrams via Mermaid (PlantUML/Structurizr optional adv'
+    stability: stable
+  - id: cloud/aws-well-architected-review
+    name: aws-well-architected-review
+    domain: cloud
+    description: 'WHAT — AWS Well-Architected Framework review (6 pillars) — operational excellence, security, reliability, performance, cost, sustainability + WAR process. Checklist for workload evaluation on AWS;'
+    stability: stable
+  - id: cloud/cloud-design-patterns
+    name: cloud-design-patterns
+    domain: cloud
+    description: 'WHAT — Vendor-neutral distributed cloud patterns (Retry, Bulkhead, Circuit Breaker, CQRS, Event Sourcing, etc.) abstracted from AWS/Azure/GCP sources — when to apply, tradeoffs, mapping to AWS/GCP'
+    stability: stable
+  - id: core/assistant
+    name: assistant
+    domain: core
+    description: 'Assistant — on any repo, scan README→docs→AGENTS→CONTRIBUTING→PR templates→task runners→devcontainer→CI→configs before code; cite sources; prefer AGENTS.md for agent behavior; portab'
+    stability: stable
+  - id: core/dev-companion
+    name: dev-companion
+    domain: core
+    description: '''WHAT — Dev Companion (general): layered companion for client delivery; modes, gates, delegation to assistant and workflow-generic-project; no CLI matrices.'''
+    stability: stable
+  - id: core/onboarding
+    name: onboarding
+    domain: core
+    description: 'Getting started guide for new users. Walks through setup validation, the skill/agent hierarchy, and the three most useful commands per role (developer, PM, tech lead). Use when someone is new to the w'
+    stability: stable
+  - id: core/output-handshake
+    name: output-handshake
+    domain: core
+    description: '''WHAT — Default gate for any deliverable: confirm where the final artifact will be stored and that a human will review, before writing PRDs, TRDs, ADRs, or PR bodies. Repository paths, wikis, and ti'
+    stability: stable
+  - id: core/pr-fallback
+    name: pr-fallback
+    domain: core
+    description: 'WHAT — When the repo has no GitHub PR template, structure the pull-request body using the default in references/pr-body-default.md. Pair with output-handshake and github-cli-workflow. Does not open '
+    stability: stable
+  - id: core/project
+    name: project
+    domain: core
+    description: 'Clone, index, and orchestrate multi-repo work via agent-toolkit project — symlinks, quick access, and swarm workspaces.'
+    stability: stable
+  - id: core/workspace
+    name: workspace
+    domain: core
+    description: 'Scaffold and manage the stateless AI workspace — context, packs, repos, and knowledge for multi-repo orchestration.'
+    stability: stable
+  - id: core/workspace-knowledge-sync
+    name: workspace-knowledge-sync
+    domain: core
+    description: 'Syncs knowledge to the agentic-harness knowledge base. Use when the assistant discovers new patterns, learns user preferences, or identifies information worth preserving for future sessions. Integrate'
+    stability: stable
+  - id: data/dbt-validation
+    name: dbt-validation
+    domain: data
+    description: 'HOW — Run dbt checks as documented in the target repo (parse, compile, test, selective run). Does not configure Snowflake accounts or change cloud security.'
+    stability: stable
+  - id: data/snowflake-validation
+    name: snowflake-validation
+    domain: data
+    description: '''HOW — Read-only Snowflake validation patterns: use repo-documented CLI (snowflake/sql) or SQL checks. Never claim success without working credentials and evidence.'''
+    stability: stable
+  - id: delivery/adr
+    name: adr
+    domain: delivery
+    description: 'WHAT — Create and maintain Architecture Decision Records (ADRs) per the process. Covers when to write an ADR, required sections, review, and linking to epics/PRs. English for cross-team artifacts un'
+    stability: stable
+  - id: delivery/agreement
+    name: agreement
+    domain: delivery
+    description: 'WHAT - Capture explicit agreements, terms, parties involved, dates, validity, and linked work items using the Agreement Document structure.'
+    stability: stable
+  - id: delivery/bug
+    name: bug
+    domain: delivery
+    description: WHAT - Draft and review bugs using the Bug Template; classifies whether an issue should be escalated to incident based on production/user impact.
+    stability: stable
+  - id: delivery/decision-log
+    name: decision-log
+    domain: delivery
+    description: 'WHAT - Capture lightweight project, product, or operational decisions that do not require a full ADR; includes rationale, date, owner, and references.'
+    stability: stable
+  - id: delivery/development-workflow
+    name: development-workflow
+    domain: delivery
+    description: 'WHAT - Default development workflow, task lifecycle, DoR, DoD, validation, and evidence model when a project has no explicit override. Repository instructions still take precedence.'
+    stability: stable
+  - id: delivery/epic
+    name: epic
+    domain: delivery
+    description: 'WHAT - Draft and review epics using the Best Practices Epic Template; includes objectives, success criteria, related tasks, stakeholders, and effort metadata.'
+    stability: stable
+  - id: delivery/incident
+    name: incident
+    domain: delivery
+    description: 'WHAT - Draft and review incident reports and RCA notes using Incident Management guidance; includes detection, impact, timeline, RCA, resolution, and follow-ups.'
+    stability: stable
+  - id: delivery/management-unit-assessment
+    name: management-unit-assessment
+    domain: delivery
+    description: 'WHAT - Evidence-based management unit assessment for governance, delivery, collaboration, culture, and AI-native management readiness. Interactive and source-driven before any score is assigned.'
+    stability: stable
+  - id: delivery/meeting-minutes
+    name: meeting-minutes
+    domain: delivery
+    description: 'WHAT - Create structured meeting minutes from notes or transcripts using meeting templates, with redaction, action items, decisions, and traceability.'
+    stability: stable
+  - id: delivery/planning
+    name: planning
+    domain: delivery
+    description: 'WHAT - Planning, estimation, task breakdown, and iteration capacity fallback based on Best Practices. Use before finalizing backlog scope, story/task estimates, or iteration commitments.'
+    stability: stable
+  - id: delivery/prd
+    name: prd
+    domain: delivery
+    description: 'WHAT — Draft and review a Product Requirements Document (PRD) using the template. Business-level requirements, acceptance criteria, and traceability. Does not replace the product owner. English for '
+    stability: stable
+  - id: delivery/project-assessment
+    name: project-assessment
+    domain: delivery
+    description: '''WHAT - Interactive project assessment router: define assessment scope and units, collect evidence through project-assessment-evidence, then delegate to technical or management unit assessment skills.'
+    stability: stable
+  - id: delivery/project-assessment-evidence
+    name: project-assessment-evidence
+    domain: delivery
+    description: 'WHAT - Interactive evidence intake for project assessments. Ask the user where each evidence source lives, build an evidence map, track missing evidence, assumptions, freshness, and confidence before '
+    stability: stable
+  - id: delivery/spike
+    name: spike
+    domain: delivery
+    description: 'WHAT - Produce spike and research findings using the spike template; captures purpose, findings, implementation strategy, risks, tradeoffs, open questions, and references.'
+    stability: stable
+  - id: delivery/task
+    name: task
+    domain: delivery
+    description: 'WHAT - Draft and review technical tasks using the Best Practices Task Template; includes summary, technical notes, AC, estimate, owner, and due date.'
+    stability: stable
+  - id: delivery/technical-unit-assessment
+    name: technical-unit-assessment
+    domain: delivery
+    description: 'WHAT - Evidence-based technical unit assessment for repositories, platforms, frontend, backend, infrastructure, data, UI/UX, and AI-native structural readiness.'
+    stability: stable
+  - id: delivery/trd
+    name: trd
+    domain: delivery
+    description: 'WHAT — Draft and review a Technical Requirements Document (TRD) using the template, typically from an agreed PRD. Covers architecture, data contracts, technical decisions, risks, and test strategy. '
+    stability: stable
+  - id: delivery/user-story
+    name: user-story
+    domain: delivery
+    description: WHAT - Draft and review user stories using the task template plus the As a/I want/so that format from Best Practices examples.
+    stability: stable
+  - id: delivery/work-item
+    name: work-item
+    domain: delivery
+    description: 'WHAT - Router for creating and refining epics, user stories, tasks, bugs, and incidents using Best Practices work item hierarchy.'
+    stability: stable
+  - id: delivery/workflow-client-bootstrap
+    name: workflow-client-bootstrap
+    domain: delivery
+    description: 'WHAT — Interactive interview to capture client delivery context and store it inside the user''s ~/.ai-workspace (or similar) as packs + knowledge (no client skills). Use when onboarding a new client '
+    stability: stable
+  - id: delivery/workflow-generic-project
+    name: workflow-generic-project
+    domain: delivery
+    description: '''WHAT — Generic client delivery: Jira or ClickUp, full repo context, human gates, English traceability on tickets, draft PR via delegated forge skills. Use workspace packs for client/account overlay'
+    stability: stable
+  - id: design/design-assessment
+    name: design-assessment
+    domain: design
+    description: 'WHAT - Evidence-based design-unit assessment orchestrated by project-assessment. Evaluates visual hierarchy, UX friction, interaction, a11y, responsiveness, design-system compliance, and distinctivene'
+    stability: stable
+  - id: design/design-improvement
+    name: design-improvement
+    domain: design
+    description: 'WHAT - Browser-grounded iterative design improvement. Consumes design-assessment findings, defines direction, prioritizes safe vs ambiguous changes, implements within existing design system, runs app,'
+    stability: stable
+  - id: design/figma
+    name: figma
+    domain: design
+    description: 'Use the Figma MCP server to fetch design context, screenshots, variables, and assets, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-co'
+    stability: stable
+  - id: design/figma-code-connect-components
+    name: figma-code-connect-components
+    domain: design
+    description: 'Connects Figma design components to code components using Code Connect mapping tools. Use when user says "code connect", "connect this component to code", "map this component", "link component to code'
+    stability: stable
+  - id: design/figma-create-design-system-rules
+    name: figma-create-design-system-rules
+    domain: design
+    description: 'Generates custom design system rules for the user''s codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelin'
+    stability: stable
+  - id: design/figma-create-new-file
+    name: figma-create-new-file
+    domain: design
+    description: 'Create a new blank Figma file. Use when the user wants to create a new Figma design or FigJam file, or when you need a new file before calling use_figma. Handles plan resolution via whoami if needed. '
+    stability: stable
+  - id: design/figma-implement-design
+    name: figma-implement-design
+    domain: design
+    description: 'Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions "implement design", "generate code", "imple'
+    stability: stable
+  - id: design/frontend-design
+    name: frontend-design
+    domain: design
+    description: 'Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don''t read as templated defau'
+    stability: stable
+  - id: design/frontend-design-review
+    name: frontend-design-review
+    domain: design
+    description: '> Review and create distinctive, production-grade frontend interfaces with high design quality and design system compliance. Evaluates using three pillars: frictionless insight-to-action, quality craf'
+    stability: stable
+  - id: design/web-design-guidelines
+    name: web-design-guidelines
+    domain: design
+    description: 'Review UI code for Web Interface Guidelines compliance — accessibility, focus, forms, animation, typography, performance, and anti-patterns. Use when asked to "review my UI", "check accessibility", '
+    stability: stable
+  - id: forge/gh-address-comments
+    name: gh-address-comments
+    domain: forge
+    description: 'Triage and address open GitHub PR review and conversation comments using the gh CLI. Use when the user wants to "address PR comments", "resolve review threads", or "respond to reviewers" on the curren'
+    stability: stable
+  - id: forge/gh-contribution-planner
+    name: gh-contribution-planner
+    domain: forge
+    description: 'Daily GitHub contribution planner — analyzes the gh-logged-in user''s non-archived repos (owned + forks) and recent contributions, produces a prioritized plan, halts for approval, then dispatches par'
+    stability: stable
+  - id: forge/gh-fix-ci
+    name: gh-fix-ci
+    domain: forge
+    description: 'Diagnose failing GitHub Actions checks on a PR via gh, summarize the failure context, propose a plan, and only implement after explicit user approval. External CI providers (Buildkite, CircleCI, etc.)'
+    stability: stable
+  - id: forge/github-cli-workflow
+    name: github-cli-workflow
+    domain: forge
+    description: '''HOW — GitHub CLI (gh): push branch, create draft PR with title/body from template or file; fallback untracked PR_DESCRIPTION_*.md. Use when origin is GitHub.'''
+    stability: stable
+  - id: forge/gitlab-cli-workflow
+    name: gitlab-cli-workflow
+    domain: forge
+    description: '''HOW — GitLab CLI (glab): push branch, create draft MR with title/body; fallback untracked markdown. Use when origin is GitLab.'''
+    stability: stable
+  - id: forge/workflow-client-bootstrap
+    name: workflow-client-bootstrap
+    domain: forge
+    description: DEPRECATED alias. Use workflow-client-bootstrap instead.
+    stability: stable
+  - id: forge/workflow-generic-project
+    name: workflow-generic-project
+    domain: forge
+    description: DEPRECATED alias. Use workflow-generic-project instead.
+    stability: stable
+  - id: forge/worktree
+    name: worktree
+    domain: forge
+    description: 'Manage Git worktrees per writer for Agent Toolkit swarms — isolated branches, handoff promotion, and cleanup.'
+    stability: stable
+  - id: integrations/clickup-cli
+    name: clickup-cli
+    domain: integrations
+    description: 'ClickUp CLI for managing tasks, sprints, comments, statuses, and Docs. Use when the user needs to interact with ClickUp — creating/editing tasks, checking sprint status, adding comments, linking PRs'
+    stability: stable
+  - id: integrations/linear
+    name: linear
+    domain: integrations
+    description: 'Manage Linear issues, projects and cycles via the Linear MCP server. Use when the user wants to read, triage, create or update Linear tickets, plan a sprint, audit Linear documentation, or rebalance t'
+    stability: stable
+  - id: integrations/mcp
+    name: mcp
+    domain: integrations
+    description: 'Configure and manage MCP providers for Agent Toolkit — setup, list, doctor, and per-tool deployment.'
+    stability: stable
+  - id: integrations/slack-assistant
+    name: slack-assistant
+    domain: integrations
+    description: 'Interact with Slack workspaces for reading channels/messages, sending messages, adding reactions, and browsing canvases. Use when the user asks about Slack channels, messages, or notifications — NOT'
+    stability: stable
+  - id: integrations/slack-cli
+    name: slack-cli
+    domain: integrations
+    description: 'Interact with the official Slack CLI to create, run, deploy, and manage Slack apps, environments, manifests, and triggers. Use when the user asks about Slack app development workflows, not workspace c'
+    stability: stable
+  - id: loops/loop-runner
+    name: loop-runner
+    domain: loops
+    description: 'Execute and manage loop engineering primitives (init, run, status, audit) from an AI coding session via the agent-toolkit loop CLI.'
+    stability: stable
+  - id: ops/docs-generator
+    name: docs-generator
+    domain: ops
+    description: '''WHAT — Generate or update documentation from code: README.md from repo structure, CHANGELOG.md from git history, API reference from OpenAPI/GraphQL schemas, and AGENTS.md starters for new projects.'
+    stability: stable
+  - id: ops/llm-cost-advisor
+    name: llm-cost-advisor
+    domain: ops
+    description: 'WHAT — Recommend the most cost-effective LLM provider for a given task type. Shows estimated cost per run across available providers and integrates with devcompanion llm-status to show what is actua'
+    stability: stable
+  - id: ops/swarm
+    name: swarm
+    domain: ops
+    description: Launch an Agent Toolkit swarm from a natural language request using agent-toolkit swarm CLI with Herdr/tmux eager windows and file handoffs.
+    stability: stable
+  - id: ops/swarm-handoff
+    name: swarm-handoff
+    domain: ops
+    description: 'Create artifact/commit file handoffs for Agent Toolkit swarms with worktree-per-writer, branch, and promotion integration.'
+    stability: stable
+  - id: ops/swarm-observer
+    name: swarm-observer
+    domain: ops
+    description: 'Observe, diagnose, and recover Agent Toolkit swarm runs via status, handoffs, logs, and attach with worktree and shell awareness.'
+    stability: stable
+  - id: ops/triage
+    name: triage
+    domain: ops
+    description: 'Workstation health triage — validate tooling, directory layout, and run doctor with remediation suggestions.'
+    stability: stable
+  - id: quality/codeql
+    name: codeql
+    domain: quality
+    description: 'CodeQL operational workflow — discover/config, run/inspect, triage SARIF findings (rule/query ID, source→sink, evidence), remediate, re-validate. Distinguishes broad MegaLinter linting from semant'
+    stability: stable
+  - id: quality/megalinter
+    name: megalinter
+    domain: quality
+    description: 'MegaLinter coding-agent orchestration — discover config, run/check (CI watch or local Docker), classify findings, apply safe fixes, targeted re-check (bounded 3 iterations), report remaining. Consum'
+    stability: stable
+  - id: tooling/chrome-devtools
+    name: chrome-devtools
+    domain: tooling
+    description: 'Use Chrome DevTools MCP to control and inspect a live Chrome instance for network, console, performance, rendering, and Deep debugging. Pairs with playwright-cli (deterministic interaction/E2E) — co'
+    stability: stable
+  - id: tooling/herdr
+    name: herdr
+    domain: tooling
+    description: 'Manage Herdr workspaces, tabs, and panes for Agent Toolkit swarms with eager windows, shell-aware execution, and reuse.'
+    stability: stable
+  - id: tooling/inventory
+    name: inventory
+    domain: tooling
+    description: 'Discover installed skills, agents, loops, and platform capabilities via agent-toolkit inventory, matrix, and skills list.'
+    stability: stable
+  - id: tooling/jupyter-notebook
+    name: jupyter-notebook
+    domain: tooling
+    description: 'Create, scaffold, or refactor Jupyter notebooks (.ipynb) for experiments and tutorials. Prefer the bundled templates and the helper script (`new_notebook.py`, also exposed as `newnotebook`) to generat'
+    stability: stable
+  - id: tooling/mermaid
+    name: mermaid
+    domain: tooling
+    description: 'WHAT — Mermaid diagrams from text (flowchart, sequence, class, state, ER, gantt, gitGraph) — Markdown-native, Git-native, MIT. Primary renderer for architecture pack; renders via GitHub native or '
+    stability: stable
+  - id: tooling/playwright-cli
+    name: playwright-cli
+    domain: tooling
+    description: 'Drive a real browser from the terminal using the Playwright CLI (snapshot, click, fill, screenshots, traces). Use when the task is CLI-first browser automation (data extraction, UI debugging, form fil'
+    stability: stable