stackhawk-api

Guides authoring and maintaining agent skills in this repository — enforcing Anthropic best practices, release-version rules, regenerating Cursor rules, and keeping the plugin structure consistent. Use when editing SKILL.md files, reference files, or plugin manifests; creating a new plugin; or reviewing a skill for compliance with authoring standards. Do NOT trigger for general coding tasks, security scanning, or platform API queries.

Use this skill when a user or agent needs to query the StackHawk platform for security reporting, findings analysis, or app management. Triggers include: "stackhawk api", "security posture", "findings report", "show me findings", "untriaged findings", "which apps", "scan history", "security dashboard", "triage", "what needs attention". Uses the hawk CLI (`hawk op` subcommand) for all platform queries. Do NOT use for running scans (use the hawkscan skill for "scan my app", "hawkscan", "stackhawk.yml", "DAST") or for fixing/remediating code or vulnerabilities — this skill only reads and reports platform data.

Use when the user wants to WIRE HawkScan into a CI/CD pipeline config file — triggers on "set up hawkscan in CI", "add stackhawk to my pipeline", "scan in CI", "configure github actions / gitlab / jenkins / circleci for hawkscan", "wire hawkscan into ci/cd", or any provider-named variant. Provider-agnostic: detects the CI system from repo files, edits the pipeline file in place to add a HawkScan job, prompts for HAWK_API_KEY storage in the CI's native secrets store (or an approved external manager), and wires commit-SHA + branch traceability. If no local stackhawk.yml exists yet, still trigger and route the local-config work to the hawkscan skill. Do NOT trigger for: documentation-only changes (e.g. editing a README about CI scanning); informational or research questions ("what CI providers does HawkScan support?"); or running / performing a scan — a local scan is the hawkscan skill, whereas this skill only edits CI pipeline config. Explicit trigger only; no autonomous code-change hook.

Runs the HawkScan DAST security loop — configure, scan, fix all reported vulnerabilities (not just your changes), rescan to verify. Performs code-first discovery to configure high-value scans, and quality-gates every scan against code-derived expectations before findings are parsed. Use when the user asks to run or perform a security/DAST scan, to test an app or API for vulnerabilities, or to verify a vulnerability is fixed; and AUTONOMOUSLY right after you complete a code change (feature, bugfix, refactor) — "done" means "done and secure," so run the loop without asking permission. Do NOT trigger for: informational questions about what HawkScan is, detects, or how it works (e.g. "what vulnerabilities does HawkScan find?"); editing stackhawk.yml or other config without running a scan; querying existing findings, security posture, untriaged counts, or scan history (use the stackhawk-api skill); documentation-only changes; installing or setting up the CLI; or when the user explicitly says to skip scanning.

Analyze a codebase and produce an optimal HawkScan setup — tech flags, scan-policy plugin selection, and stackhawk.yml corrections — then apply it as a non-destructive trial, run ONE trial scan, and promote or discard. Use when the user asks to "optimize my scan", "tune HawkScan", "make my scan faster", "reduce false positives", "pick the right plugins/policy for my app", or invokes /optimize. Also invoked automatically by the hawkscan skill on every fresh stackhawk.yml (Phase 0c) to set up the scan policy + tech flags (Setup mode), and re-runnable anytime via /optimize; the metrics Refine mode is surfaced when a scan is slow. Do NOT use for: a normal security scan or fixing vulnerabilities (use the hawkscan skill); querying existing findings or posture (use the api skill); or editing stackhawk.yml without optimizing/scanning. Requires an onboarded StackHawk app + env and a `hawk` build whose `hawk op` has the `policy` write commands.

Set up checked-in seed data so authenticated HawkScan can reach non-trivial paths. Drives the `hawk perch seed` preflight, designs the minimum seed manifest from the repo digest, then validates and finalizes it via `hawk perch seed validate` / `finalize` — emitting reviewed artifacts under data-seed/ (manifest.yaml, per-service SQL / HTTP / gRPC / Mongo / shell scripts, and a .data-seed-credentials.env handoff hawkscan consumes). Use when the user says "set up data for HawkScan", "my scan has no data to hit", "seed this repo for scanning", or as a first-time-setup step before invoking hawkscan on a fresh repo. NOT autonomous — the user explicitly asks.

Analyze a codebase and produce an optimal HawkScan setup — tech flags, scan-policy plugin selection, and stackhawk.yml corrections — then apply it as a non-destructive trial, run ONE trial scan, and promote or discard. Use when the user asks to "optimize my scan", "tune HawkScan", "make my scan faster", "reduce false positives", "pick the right plugins/policy for my app", or invokes /optimize. Also invoked automatically by the hawkscan skill on every fresh stackhawk.yml (Phase 0c) to set up the scan policy + tech flags (Setup mode), and re-runnable anytime via /optimize; the metrics Refine mode is surfaced when a scan is slow. Do NOT use for: a normal security scan or fixing vulnerabilities (use the hawkscan skill); querying existing findings or posture (use the api skill); or editing stackhawk.yml without optimizing/scanning. Requires an onboarded StackHawk app + env and a `hawk` build whose `hawk op` has the `policy` write commands.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. WHEN: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices.

Analyze Azure resource groups and generate detailed Mermaid architecture diagrams showing the relationships between individual resources. WHEN: create architecture diagram, visualize Azure resources, show resource relationships, generate Mermaid diagram, analyze resource group, diagram my resources, architecture visualization, resource topology, map Azure infrastructure.

Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.

Troubleshoot and resolve issues with Azure Messaging SDKs for Event Hubs and Service Bus. Covers connection failures, authentication errors, message processing issues, and SDK configuration problems. WHEN: event hub SDK error, service bus SDK issue, messaging connection failure, AMQP error, event processor host issue, message lock lost, message lock expired, lock renewal, lock renewal batch, send timeout, receiver disconnected, SDK troubleshooting, azure messaging SDK, event hub consumer, service bus queue issue, topic subscription error, enable logging event hub, service bus logging, eventhub python, servicebus java, eventhub javascript, servicebus dotnet, event hub checkpoint, event hub not receiving messages, service bus dead letter, batch processing lock, session lock expired, idle timeout, connection inactive, link detach, slow reconnect, session error, duplicate events, offset reset, receive batch.