Browse Skills

Codebase Hygiene finds semantic duplicates and shallow modules that spread complexity across a codebase. It is read-only and advisory, used before routing any real changes through BUILD with full gates.

Debugging uses a feedback-loop-first approach to reproduce bugs before forming hypotheses. It covers root-cause tracing, blast-radius checks, and a four-phase investigation process for agent-driven debugging.

Verification enforces proof-first validation for agent work. Use it to independently confirm a task actually achieved its goal, with evidence, exit codes, and scenario-level checks.

Heavy Verify Loop runs a user-level verify, fix, and review cycle against the real Peri TUI using tmux, logs, and E2E helpers. Use it when a feature must be exercised like a real user until fresh end-to-end evidence shows no blocking problems.

Project Maturity Scanner scans a repository across tests, code quality, CI/CD, docs, security, and activity to produce a structured maturity report. Use it when evaluating a new codebase, reviewing release readiness, or doing a technical due diligence check.

API Testing covers Playwright patterns for API specs, including apiRequest usage, Zod response validation, multi-call test.step wrapping, and negative testing for request bodies and path parameters. Use it when adding or updating endpoint tests or comparing documented contracts with API behavior.

Data Strategy defines how to choose between Faker factories, static TypeScript datasets, and inline values for Playwright tests. Use it when creating test data, adding invalid-value sets, or deciding where a value should live.

Debugging helps you investigate Playwright test failures by reading error messages, classifying timeout and locator issues, and choosing the right tool to replay the problem. Use it when a test flakes, fails in CI, or needs local reproduction from traces and reports.

Enums defines TypeScript enum conventions for the Playwright scaffold, including naming, file placement, and when to add or extend enums. Use it for repeated app strings like routes, messages, roles, and storage paths.

Fixtures provides Playwright dependency-injection conventions for page objects, API request setup, and lifecycle helpers. Use it when adding or classifying fixtures, extending test options, or deciding whether code belongs in a fixture or a plain helper.

FrontierHarness Eval benchmarks a third-party coding-agent harness against FrontierHarness baselines using identical fresh restores, saved trajectories, and comparable cost accounting. Use it when evaluating, scoring, or comparing a harness such as FrontierHarness, DeepSWE, or Terminal-Bench setups.

FrontierHarness Eval benchmarks a third-party coding-agent harness against FrontierHarness baselines using identical runs, saved trajectories, and a comparison report. Use it when evaluating a harness, comparing results, or checking FrontierHarness, DeepSWE, or Terminal-Bench setups.