Навыки: Тестирование

Observe Before Editing

Sync Claude conversations to Obsidian vault. Use when user asks to: sync conversations, export chat history, catalog ses...

Testing strategies for OCaml libraries. Use when discussing tests, alcotest, eio mocks, test structure, test-driven deve...

Use the OpenConstructionERP validation engine: rule packs (BOQ quality, DIN 276, NRM, GAEB, MasterFormat, DPGF) that che...

AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives....

Use when converting scanned PDFs, image-heavy books, technical textbooks, music books, OCR output, or rough Markdown int...

Change a live OCS chatbot's system prompt, tools or pipeline, then republish and smoke-test it. Use when someone asks to...

Use this skill whenever the prompt contains any `github.com` URL, even if the user only pastes a link and gives no GitHu...

Solve ordinary differential equations (initial and boundary value problems). Supports stiff/non-stiff systems, event det...

Orchestration doctrine for the Software Engineering workflow — optional business analysis and arc42-structured architect...

Drive a month-end accounting close on Odoo through odoo-mcp — AR/AP aging, open-item and draft-invoice review, reconcili...

Creates comprehensive test suites for Odoo 16.0 modules following Siafa project standards. This skill should be used whe...

Audit offer quality across 16 diagnostics (value, urgency, trust, positioning). Scores 0-100. Use for offer quality chec...

Create a offer letter with structured process, quality checks, and system integration

Draft a job offer — the written offer letter and a verbal-offer script. Use when asked to write an offer letter, a job o...

YC Office Hours — two modes. (gstack)

Execute a bounded D4RL-style offline recovery proxy with fixed-dataset training and normalized-score evidence.

独立双模型交叉审查（随时可用）

Be the expert on Open Knowledge Format (OKF) — portable project knowledge as a directory of markdown files with YAML fro...

Make, record, reconcile, or troubleshoot citrus peel and sugar extraction by weight. Use when declared peel and sugar ma...

Use when running local LLMs with Ollama — choosing models by measured speed and quality on CPU-only or old-GPU machines,...

Advanced om-auto-continue-pr for PRs started by om-auto-create-pr-loop — claims the PR, resumes from the first non-done...

Repo-local extension of om-auto-create-pr - per-phase test, copy and generated-file discipline, commit style and the dep...

Repo-local extension of om-auto-qa-pr - the viewports, themes, hydration wait and console policy that decide PASS/FAIL i...

QA a PR's UI change in a real browser through the configured browser-provider descriptor — first ensuring the PR has bee...

Run and create integration/E2E tests by exploring the live app with the configured browser provider, preserving reposito...

Repo-local extension of om-prepare-test-env - how this app boots for QA (local D1, throwaway .dev.vars, the seed, the 30...

Prepare a reusable, technology-agnostic environment for local tests and QA. Compiles discovery into cross-platform launc...

Run only the tests a change can affect — diffs the branch against its base, maps changed files to affected units via the...

Create an offline HTML explanation of a code diff, PR, or branch. Use when an interactive code-change walkthrough is req...

Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and...

Publish package to npm registry with pre-checks

Use when fixing review findings on a GitHub PR, resolving inline review threads, applying code review suggestions, or wh...

Use when fixing review findings on a GitLab MR, resolving inline discussion threads, applying code review suggestions, o...

Zero-knowledge onboarding audit. Pretends to be a new developer who has never seen this repo. Tries to get it running. D...

Run an AI-assisted PR review that validates issue linkage, local quality gates, manageable scope, and review comments.

Guide an interactive human PR review by summarizing changes and linked issues, checking reviewer understanding with a qu...

Review application logging for correct TRACE/DEBUG/INFO/WARN/ERROR/FATAL usage, mandatory level labels, and complete err...

Verify whether pull request review comments are addressed, then guide the PR author through code fixes or prefixed repli...

Create a one pager with structured process, quality checks, and system integration

Use this skill when creating new files that represent architectural decisions — data models, infrastructure configs, aut...

Ultra-fast feature implementation using Explore → Code → Test workflow. Use when implementing focused features, single t...

Validate material sample annotations and data structures against ontology constraints. Use when checking if CMSO annotat...

Onyx repository operating knowledge for backend, RAG/indexing, agents/Craft, web, mobile, CLI, deployment, and maintaine...

Use when the user says "open a PR", "/open-pr", "make the PR", "ship this", "draft a PR", "create the PR", or wants Clau...

Lints an OpenAPI file with the bundled Spectral wrapper. Use when the user edits an OpenAPI spec and wants it validated.

mistakes.md参照・最小差分・大出力はmemoryadd退避のバグ修正スキルです。

Create, test, evaluate, optimize, and package OpenCode skills with the opencode-skill-creator plugin. Use when users exp...