Loading...
Loading...
Found 137 Skills
Fix confirmed bugs from user reports, runtime failures, failing tests, or verified `/find-bugs` findings. Reproduce the bug first, diagnose the real root cause, apply the smallest correct fix, verify against regressions, and report exactly what changed. Loads framework-specific references and category-specific playbooks as needed. Use when the user says "fix this bug", "fix the findings", "/bugfix", or asks to repair a confirmed defect.
Use when validating automation builds before launch or after significant changes.
Snapshot test email templates using Verify to catch regressions. Validates rendered HTML output matches approved baseline. Works with MJML templates and any email renderer.
Add test coverage to existing code with correct mock patterns. Use when adding tests to untested modules, writing regression tests for bugs, or user asks to test a specific file. Handles mockReset:true, vi.hoisted(), forwarding pattern, and test app builder utilities.
Evaluate Omni AI query generation accuracy by running test prompts through the Omni CLI, comparing generated query JSON against expected results, and scoring accuracy. Use this skill whenever someone wants to evaluate Omni AI, benchmark Blobby, run regression tests, compare AI output across branches or configurations, test prompt variations, measure AI quality, run A/B tests on model changes, assess impact of context changes, or any variant of "run evals", "test Blobby", "benchmark query generation", "compare AI results", "regression test", "how accurate is the AI", or "measure the impact of my changes".
Implements the minimal code change identified by the om-root-cause step, adds regression tests, and runs the configured validation gate. Claims the tracker issue at start (assignee + in-progress label + claim comment) so concurrent automation backs off. Does not commit, push, or open a PR — that is the om-open-pr step's job.
Debug and fix bugs, errors, or unexpected behavior
Implement the fix for a GitHub issue from its RCA artifact (created by piv-investigate-issue) — drift-check the plan, branch, implement, add regression tests, and validate. Use after the investigation artifact exists and you're ready to fix the issue.
Debugs a failing production call, reproduces the bug with Cekura evaluators, implements a fix, verifies it, runs regression tests, then raises a PR with evidence. Use when the user wants to fix a production call bug, investigate a failing prod call, reproduce and fix a production issue, run regression tests before a PR, or says things like "fix this prod call issue", "debug and fix call ID", "test my fix against prod scenarios", "reproduce this production bug", or "regression test before raising PR".
Hunt for real bugs in the vigiles CLI/codebase with a parallel expert fan-out, then FIX them directly — source-trace each defect to file:line, add a regression test, commit per theme. Use when asked to dogfood vigiles, find/fix bugs across the CLI the source-traced way, or fan out agents to audit the tool on itself.
Implement an agreed task incrementally and verify the result.
Determine and execute the smallest defensible EvalGate workflow for an AI change, response, artifact, or non-chat model event. Use for prompts, models, tools, agents, retrieval, skills, MCP, judges, datasets, routing, safety, cost, latency, release policy, external optimization imports, or governed improvement and confirmation cycles; skip it for work proven not to affect observable AI behavior.