AI Agent & Automation Workflows

Writes and maintains ADRs (MADR, Nygard, Y-Statement) and runs decision checkpoints before/during work—trigger matrix, option briefs, proposed ADRs. Use when creating or updating ADRs, facing a design fork, trade-off, boundary change, or when the user asks for key design decisions before implementing.

Bootstraps and maintains a vectorless, layered documentation store for concepts, architecture, and decisions—without duplicating how code works. Use when organizing repo docs, writing ADRs, north-star charters, agent playbooks, or mcpflutter-style doc lattices.

Creates and maintains DESIGNFAQ (why) and DXFAQ (how) documentation in FAQ-driven development style. Use when writing docs, rules, prompts, updating FAQs after code changes, or bootstrapping faqusage rules and Cursor commands.

Develops agent-first engineering culture via harness design—CLI and MCP with shared contracts, mechanical gates, and in-repo docs. Use when building agentic tooling, harness loops, Codex/Cursor workflows, or applying OpenAI harness engineering with Skill Steward meta-skills.

Design, implement, and integrate generalized validation harnesses across a producer-consumer boundary after a local harness contract exists. Use when refactoring custom validation CLIs/MCPs for large polyrepos, extending Steward across sibling repos, or deploying a local tool to a consumer project for dogfooding and testing; use mcp-harness-repo-maintainer first for initial steward.yaml adoption and cold-start proof.

Maintains MCP-and-harness repositories where CLI and MCP are thin agent-facing interfaces and core libraries hold domain logic—mcpflutter, IntentCall (intentcall), flutterharness, skillsteward. Use when refactoring adapters, enforcing CLI/MCP/core parity, contract gates, or sibling repo layout.

Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process. Dynamically spawns specialized subagents with different critical lenses to cross-reference findings and detect flaws, overlap, retention issues, or drift. Use when designing architectures, analyzing complex code, verifying multi-step plans, classifying evidence artifacts, or looking for duplicated intent in a repo.

Plan and document handoffs between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagent delegation, baton passes, or guild-style agent coordination.

Maintains docs/NORTHSTAR.md, wires AGENTS.md as a short agent map, and applies plan hygiene (any format—Superpowers, session plans, etc.) by extracting durable knowledge into ADR, FAQ, code, or harness then removing stale plan files. Use when updating charter, repo navigation, closing work, or docs.page structure. Does not define a new plan template.

Designs public or private AI skill and plugin marketplaces for Cursor, Claude Code, Codex, and npx skills—manifest layout, install matrix, and Guild vs product boundaries. Use when setting up a marketplace, distributing skills/plugins to a team, private registry, .cursor-plugin, .claude-plugin, or skills.sh publishing.

Simulates a skill directory that is well-formed but absent from skills.sh.json, to exercise registry drift detection in the validator.

Chooses ecosystem-native release and changelog tooling (Changesets, Melos, release-plz) plus binary distribution (GitHub Release tarballs, install.sh) when the product is an executable. Use for release CI, install.sh, versioning, CHANGELOGs, shipping MCP/CLI without clone, or meta repos that only ship skills via npx skills—not domain app tutorials.

Establish or audit a structural quality contract for any agent-operated engineering repository: app, library, CLI/tool, plugin, harness, or meta repo. Use when a repo needs charter clarity, docs/decision ownership, type-native validation gates, evidence paths, safe action policy, cold-start legibility, maturity proof, repair-loop routing, consumer/producer owner-boundary routing, or a repo ecology pass to decide what should be compressed, merged, removed, updated, created, retired, or moved to checks.

Master orchestration for repository governance, North Star impact, sub-Star boundaries, and repair-first or evidence-first drift checks. Guides an agent through the complete lifecycle of making architectural decisions, documenting them, writing FAQs, and cleaning up stale plans while adhering strictly to repo ethics and brand tone. Use whenever you need to make a structural change, write an ADR, update the doc lattice, or govern repository architecture.

Scaffold and formally review a new Agent Skill in this marketplace repo. Covers valid SKILL.md generation, directory layout, registry entries, and spec auditing. Use when adding a skill, validating frontmatter, or checking marketplace readiness before a PR.

Improves Agent Skills via validate → rule-based eval cases → plugin-eval → prompt evals → bounded edits with held-out gates. Use when tuning skill quality, routing, or adopting Chrome/Microsoft eval tiers—not for bulk validate-only or SkillOpt automation.

Requires durable citations when authoring or researching Agent Skills—maintain references/sources.md per skill, link external research, and record provenance in PRs. Use when creating skills, updating SKILL.md, doing web research for skills, or auditing missing sources.

Audit SKILL.md and skill directories for Agent Skills spec, Cursor extensions, and npx skills compatibility. Use when reviewing a skill, validating frontmatter, or checking marketplace readiness.

Maintain stewardship protocol continuity and tool/personality boundaries. Use when a repo agent needs steward-mode threshold checks, self-model update decisions, delegation hygiene, boundary violation review, or handoff-safe continuity context without overclaiming steward personality.

This skill is used to test the line count warning in the validator.

Critically analyze whether a product, repo, skill, plugin, harness, or architecture vision still fits the real application, user intent, implementation, evidence, and likely future direction. Use when asked to assess vision vs application, predict future fit, critique roadmap direction, analyze strategic intent, or decide whether to keep, refine, pivot, or kill a plan.