ac-verifier
Maps acceptance criteria to implementation evidence, tests, and scope creep. Use during review when a diff, PR, ticket, or story includes numbered ACs.
Draws one evidence-grounded architecture diagram as an editable draw.io file plus a rendered image, from an evidence bundle supplied by the caller. Use to produce or redraw a system context, container, deployment, data flow, sequence, or state diagram; spawn one per diagram for
$ npx -y skills add hoangnguyen0403/agent-skills-standard --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Draws one evidence-grounded architecture diagram as an editable draw.io file plus a rendered image, from an evidence bundle supplied by the caller. Use to produce or redraw a system context, container, deployment, data flow, sequence, or state diagram; spawn one per diagram for
name: solution-diagrammer description: Draws one evidence-grounded architecture diagram as an editable draw.io file plus a rendered image, from an evidence bundle supplied by the caller. Use to produce or redraw a system context, container, deployment, data flow, sequence, or state diagram; spawn one per diagram for a batch.
Produce exactly one diagram for one slug, per `common-architecture-diagramming`. Do not gather your own evidence, redesign the architecture, or draw a second view because the first looked thin.
node would be UNVERIFIED — never invent a box to make the picture look complete.
1. Restate the audience, the diagram type, and the one question this diagram answers. 2. Extract nodes and edges from the bundle per `references/source-extraction.md`, attaching a `path:line` to every node you can prove and leaving `evidence` absent for the rest. Carry `metric` and `constraint` onto each node from the bundle's `constraint -> component -> cost` lines and edge metrics from stated latency budgets; never invent a number. A node with no stated number gets no metric. 3. Write the spec per `references/diagram-spec.md`. 4. Run `scripts/validate_spec.py`; fix the spec, never the validator. 5. Run `scripts/render_drawio.py --strict`; a layout finding means change the spec (a `layer`, the node order, or a split), never the renderer. Then export: a draw.io MCP tool if the session has one, else `scripts/export_drawio.py`, else report the image as not exported. 6. Look at the exported image before reporting. Labels clear of boxes, no line crossing a third box, legend complete.
DIAGRAM: [.drawio path] + [image path | "image: not exported (no draw.io MCP or CLI)"] TYPE: [context|container|deployment|dataflow|sequence|state] · AUDIENCE: [exec|tech] NODES: [n] (UNVERIFIED: [ids or "none"]) EDGES: [n] METRICS: [n of m nodes carry a metric; edges with metric: k] QUESTION: [the one question this diagram answers] REVIEW: [one question for the named audience] BLOCKED: [reason, if any]
The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.
Repo: hoangnguyen0403/agent-skills-standard
Maps acceptance criteria to implementation evidence, tests, and scope creep. Use during review when a diff, PR, ticket, or story includes numbered ACs.
Audits PR diffs for architecture boundary violations, design simplicity, dependency drift, and established-pattern mismatches. Use during code review when…
Application Security Posture Management persona. Correlates findings from SAST, DAST, and SCA tools, deduplicates noise, maps vulnerabilities to specific code…
Explores codebase structure, affected files, blast radius, related tests, and local conventions for a focused topic. Use when review or planning needs…
Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal…
Generates one integration/E2E test from an approved test case spec using existing project patterns. Use for independent Zephyr TC, Playwright, Appium, Flutter,…