561 skills · sorted by relevance
Check a Kiln branch or pull request through real browser interactions. Multiple agents test separate feature areas in isolated environments, then combine findings into a severity-ranked Markdown report with reproduction steps and expected versus actual behavior.
Review vulnerability findings before drafting a bug bounty report. Seven validation questions and submission checklists help assess scope, reproducibility, demonstrated impact, duplicate reports, and whether the claimed severity matches the available evidence.
Turn validated vulnerabilities into clear bug bounty reports for HackerOne, Bugcrowd, Intigriti, or Immunefi. Platform templates help organize demonstrated impact, reproducible steps, supporting evidence, severity reasoning, and concrete fixes in language reviewers can follow.
Triage a raw bug report into something a team can act on — clean repro steps, a defensible severity/priority, environment, likely area/owner, and duplicate check. Use when asked to triage this bug, set severity and priority, is this a P1, or clean up this bug report for the backlog. Produces the normalized repro, a severity and priority with the reasoning (impact × frequency × workaround), the environment/metadata, a suspected component and owner queue, and a duplicate/related-issue check — flagging when info is missing rather than guessing.
The English summary is being prepared. Showing the original description.
Production incident response. Use when handling incidents, classifying severity, reconstructing timelines, writing postmortems, generating comms templates, or building response playbooks with severity scoring and RCA frameworks.
The English summary is being prepared. Showing the original description.
Systematic QA testing for web applications, desktop apps, and workflows. Three tiers: QUICK (critical/high severity only — 5 min), STANDARD (+ medium severity — 15 min), EXHAUSTIVE (+ cosmetic — 30+ min). Tests user flows, finds bugs, reports with severity classification, and optionally auto-fixes with atomic commits. Produces before/after health scores and ship-readiness summary. Use when user says "test this", "QA", "find bugs", "does this work?", or "is it ready to ship?". Voice triggers: "quality check", "run QA", "test the app". For report-only (no fixes), use with --report-only flag.
The English summary is being prepared. Showing the original description.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Check internet disruptions using Cloudflare Radar data. Filter detected outages by country and time window, then review their location, cause, severity, and end time to understand regional failures or nationwide shutdowns.
Check current airport delays and cancellations worldwide, including delay types, severity, average delay minutes, and the share of flights affected. Use airport-level alerts to understand disruption before a trip or review conditions across a region.
Retrieve climate-related disaster records, including floods, cyclones, droughts, and heatwaves. Check affected countries, severity, status, and population figures, then consult climate anomalies and related news for broader context.
Run three static audits covering architecture alignment, threats, and MCP server policies, permissions, and dependencies. Store timestamped results, track changes across runs, and fail scheduled CI jobs when findings reach a chosen severity.
Audit a codebase with three vulnerability hunters and two engineers who build small demonstrations of suspected flaws. Verify attack paths, assess severity from demonstrated impact, and report evidence, targeted fixes, and checks to prevent recurrence.
Audit a codebase across nine areas, including architecture, tests, security, and documentation. Produces TECH_DEBT_AUDIT.md with source locations, severity ratings, estimated repair effort, and prioritized recommendations to help plan maintenance work.
Integrate harmful-content checks into Python applications using Azure AI Content Safety. Analyze text and images by category and severity, and manage custom text blocklists to help review user submissions or AI-generated content before display.
Build content moderation features in Java with Azure AI Content Safety. Analyze text and images for harmful content, retrieve severity scores by category, and manage custom blocklists, which are lists of terms to flag.
Design production alerts, route notifications by severity, and organize on-call schedules. Use configuration examples to define backup contacts, escalation steps when alerts go unanswered, and runbooks that guide responders through incident investigation.
Review a pull request or code diff for bugs by reading callers, expected behavior, and nearby error handling. Receive findings tied to specific lines, ranked by severity, plus a summary of merge risks and needed tests.
Turn defects found during Oracle-to-PostgreSQL migration into structured bug reports. Document expected and actual behavior, reproduction steps, severity, root causes, proposed changes, and validation on both databases so teams can act on the findings.
Review a diffusers contribution before opening a pull request. Check the full change against project rules, trace potentially unused code, and receive a severity-based report separating required fixes from points to discuss with reviewers.
Build automated responses to AWS GuardDuty security findings using EventBridge and Lambda. Configure severity filters, isolate EC2 instances, disable compromised access keys, preserve disk snapshots for investigation, and send notifications to security teams.
Set up and operate Amazon GuardDuty to detect threats in AWS. Configure protection features, centralize findings across accounts, investigate suspicious activity, and build automated responses with EventBridge and Lambda, including containment of potentially compromised resources.
Build dashboards that show how long vulnerabilities remain unresolved and compare remediation times with severity-based deadlines. Define response policies, automate escalation notices, and report compliance rates and other measures of remediation progress.
Design a security operations center escalation matrix that defines incident priorities, response deadlines, analyst responsibilities, and notification paths. Use business impact, asset importance, and data sensitivity to decide when incidents need senior or management attention.
Present results returned by a Codex helper while preserving findings, severity, file references, and uncertainty. This internal guidance also covers reporting edited files, failed runs, and setup requirements, with user confirmation before fixing review findings.