testing-preview
Test the preview proxy feature end-to-end. Use when verifying preview URL changes, auth changes on the web proxy route, or networking-related fixes.
262 repo starsObserved in 1 repos
Testing & Quality
Testing & Quality skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
issue-to-regression-test
Use this skill when the user asks to fix a bug, references a GitHub issue number, or describes an issue and wants a fix. This skill will guide you through fetching the issue details, scaffolding a standard regression test, writing a failing test, fixing the issue, and verifying that all tests pass. Make sure to use this skill whenever a bug fix is requested.
261 repo starsObserved in 1 repos
Testing & Quality
verify-in-obsidian
Verify an Obsidian plugin change/fix actually works by driving the REAL Obsidian app in a dev vault via the `obsidian` CLI (eval / dev:console / dev:errors / dev:screenshot / command / plugin:reload) and asserting on persisted state — instead of trusting unit tests with mocks (jsdom can't load real Obsidian). Use when asked to verify/QA a fix, confirm a feature works end-to-end, check that something persists, reproduce a user-reported bug in the real app, or validate before merging — especially stateful UI (settings, modals, drag-reorder, lists). FIRST read the repo's AGENTS.md/CLAUDE.md for the vault name, plugin id, dev commands, and any QA matrix.
261 repo starsObserved in 1 repos
Testing & Quality
doistbot-loop
Run judgment-driven Doistbot local self-review loops against local git changes. Use when a user wants an agent to review and refine a branch before opening a pull request by running the Doistbot CLI, classifying findings for scope and relevance, fixing actionable issues, rerunning review, and stopping when remaining feedback is nits, out of scope, speculative, or no longer worth addressing.
260 repo starsObserved in 2 repos
Testing & Quality
investigating-anomalous-results
Use when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
260 repo starsObserved in 2 repos
Testing & Quality
azure-integration-tester
Run post-deployment integration tests for Azure resources. Verify Function Apps, Storage Accounts, Databases, App Services are healthy and accessible. Use after successful Azure deployment.
260 repo starsObserved in 1 repos
Testing & Quality
eval-creator
[Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them. Turns failures into test cases that prevent silent regression. This is the outer loop's regress-test step. Use when a learning is promoted and has a clear pass/fail condition, or on cadence to verify promoted rules still hold.
260 repo starsObserved in 1 repos
Testing & Quality
receiving-critical-review
Use when receiving critical feedback on an analysis or manuscript, before implementing suggestions, especially if feedback seems unclear or methodologically questionable - requires verification, not performative agreement or blind changes
260 repo starsObserved in 1 repos
Testing & Quality
requesting-red-team-review
Use after completing an analysis or before reporting a finding, to have a skeptical reviewer attack the conclusion before you believe it
260 repo starsObserved in 1 repos
Testing & Quality
self-healing
Active runtime recovery for coding agents: when something breaks mid-task, diagnose the root cause, write a fix, VERIFY by re-running the broken thing, then file a `HEAL-` entry to `.learnings/HEALS.md` with proof. Use whenever a command, test, build, or lint fails or exits non-zero; on missing tooling, dependency/lockfile mismatch, wrong runtime version, venv or permission errors, port conflicts, dirty git state, or a missing `.env`; when the agent needs a helper or one-off script that doesn't exist yet; when an external API, tool, or MCP errors or rate-limits; or when a test flakes. Search `HEALS.md` by `Pattern-Key` first — most heals are recurrences, so increment `Recurrence-Count` instead of duplicating. Verify is mandatory: mark `pending-verify` honestly if sandboxed, `abandoned` if the fix can't be made to work. Pairs with `self-improvement` (which promotes recurring heals to durable memory) but owns the verify-before-persist discipline self-improvement doesn't.
260 repo starsObserved in 1 repos
Testing & Quality