agent-ix

Convert ISO spec requirements (StR, FR, NFR) into a TDD-based project plan with dependency analysis, parallel execution tracks, quality gates, and task decomposition. Selects or starts a plan and writes a frontmatter-typed plan bundle under plan/<Plan-id>-<slug>/ (Plan + Task + index + log).

Create or update spec artifacts from a design or change request. Orchestrates authoring each requested requirement type (StR/US/FR/NFR/IT) as a discrete file using quoin catalog templates and Quire validation.

Analyze requirement statements (FR/NFR/StR) for EARS requirement-grammar conformance and author a SpecReview of the findings.

Build and maintain the requirements Test Matrix ensuring 100% coverage.

Review requirements for quality, consistency, and completeness.

Verify a targeted plan is complete and validated — every task done, the Test Matrix backed by real tracking tags in tests, and code fully traced to spec (flagging underspecified code with no owning requirement). Optional semantic review checks that intent↔test↔code actually agree. Emits a quire-validated SpecReview artifact to reviews/YY-MM-DD-<slug>.md.

Convert validated requirements into an implementation plan.

Run a composite specification review.

Smallest possible workflow skill — two phases joined by one auto transition.

Multi-phase linear workflow — the agent narrates each phase to the user as it advances.

Build a directed graph of nodes; the core `acyclic` invariant gates the terminal advance.

One question, one phase, interview.complete gates the transition. Demonstrates FR-022, FR-023, FR-024 happy path.

Question bank exercising every supported answer type — text, list<text>, enum, bool, int — with minItems and required flags. Demonstrates FR-022, FR-023 validation paths.

Two-phase workflow with followUpIf re-surfacing a question downstream. Demonstrates FR-024-AC-8 advisory channel.

Integration of interviews and templates — interview answers drive frontmatter and body of a generated artifact. Demonstrates FR-017..025 end-to-end.

Custom invariant requires at least one greeting before advancing.

Define a normative Functional Requirement (FR) with complete specification.

Generate required integration test cases to cover integrations with all external services. These tests will be run in a real env with real services.

Define a normative Non-Functional Requirement (NFR) or quality constraint.

Write an authoritative Stakeholder Requirement (StR).

Write or format an ISO-compatible User Story (US) artifact.

Review requirements for quality, consistency, and completeness.

Convert ISO spec requirements (StR, FR, NFR) into a TDD-based project plan with dependency analysis, parallel execution tracks, quality gates, and task decomposition. Creates /plan/plan.md and /plan/tasks/.

Review an application-type spec for completeness against UI rendering requirements and golden-path structure.

Use when an agent needs to check whether an authored Markdown artifact is structurally valid with quire-cli. Covers quire validate (markdown-only), parse-based sanity checks, required-section checks, and how to report actionable validation failures without doing domain review.

Use when an agent needs to author or update a Markdown artifact for a quire module. Covers choosing an archetype, fetching its input contract with quire schema, authoring the Markdown directly, and validating the document with quire validate without domain-specific review guidance.

Use when an agent needs to inspect, outline, or fetch targeted sections from Markdown documents using the quire CLI. Applies to spec artifacts and other heading-structured Markdown where quire parse and quire lookup are faster and safer than ad hoc regex parsing.

Use when an agent needs to inspect relationships, ix links, dependency edges, or blast radius in Markdown artifacts with quire-cli. Covers quire extract, frontmatter relationship edges, body ix:// link harvest, and practical link-audit workflows.

Draft cli-evals scenarios, suite configs, assertions, fixtures, and metric classifiers.

Run, inspect, and debug cli-evals suites for live coding-agent CLI evaluations.