Skill rating

Inspect architectural variances with SMARTS; record only explicit user choices. Report-only requests make no changes.

Develop greenfield context from a resumable interview recorded as decomposition and knowledge records.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.

Verify authorized feature, fix, and refactor work with scoped obligations, regression-first fixes, behavioral checks, characterization baselines, coverage, and lint.

Audit CVE/vulnerability source coverage for a technology stack. Maps each component (container, library, base image, runtime) to authoritative CVE feeds, flags gaps, and produces audit-ready reports.

Research: structured investigation, fact-checking, explanation traces.

Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.

Harmonize a repository's skill portfolio across catalog and user-installed skills.

Audit two or more interdependent repositories for drift, duplication, and practices one repository uses well and another lacks. Verify every finding mechanically, decide with the user, then apply surg

Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, stale, duplicate, or tautological tests, stale comments, and other mistakes supported

Archive checked `.ai/TODO.md` tasks into `.ai/todos/YYYY-MM/DD.md`, leaving unchecked tasks.

Справочник API конфигурации 1С:ЗУП 3.1 (Зарплата и управление персоналом) по кадровому учету. Используй при разработке/доработке на ЗУП 3.1, когда нужны методы КадровыйУчет, КадровыйУчетРасширенный, З

Декомпиляция управляемой формы 1С (Form.xml) в JSON-черновик формата /form-compile. Используй когда нужно декомпилировать форму, преобразовать Form.xml в JSON, получить DSL из существующей формы для а

Создать объект метаданных 1С. Используй когда пользователь просит создать или добавить справочник, документ, регистр, перечисление, константу, общий модуль, обработку, отчет и др.

Компиляция табличного документа (MXL) из JSON-определения. Используй когда нужно создать макет печатной формы

Retired. Reporting feedback and sharing a session are documented by the CLI itself: run `deepline feedback send --help` and `deepline sessions send --help`. Kept only so installed CLIs that still list

Break a plan, spec, or PRD into independently-grabbable task files using tracer-bullet vertical slices.

Teach the user a new skill or concept, within this workspace.

Provides a pre-submission manuscript audit covering argument, numerical consistency, references and DOIs, writing, figures, CONSORT flow, pre-registration, and the replication archive. Use before pape

Генерирует release notes / CHANGELOG между двумя тегами или от последнего тега. Используй, когда просят release notes, changelog или список изменений релиза.

Пишет unit-тесты для указанного файла или функции в стиле существующих тестов проекта. Используй, когда просят добавить тесты, покрыть код тестами или проверить граничные случаи.

Безопасный рефакторинг маленькими шагами без изменения поведения. Используй, когда просят отрефакторить, упростить, разделить модуль, убрать дублирование или почистить код.

Review code changes, auto-fix safe issues, and report bugs

Structured plan review across 4 axes before writing any code (inspired by Garry Tan's workflow)

Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event

Restore context after /clear by summarizing recent work and project state

Analyze changes, detect scope issues, and create a well-structured PR

Create an instructions file (.instructions.md) for a project rule or convention.

Create a custom agent (.agent.md) for a specific job.

Create a reusable skill (SKILL.md) that packages a workflow.

Create a hook (.json) to enforce policy or automate agent lifecycle events.

codenotify

Help author a component specification for an agent.

Download Azure Pipelines CI logs for analysis

Review an Ansible PR following the project's standardized process from CLAUDE.md

Prepare, validate, and publish a Pake release. Not for version bumps without release intent.

First-run setup for ruvector@0.3.3 — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via `doctor`

Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime

Diagnose Ruflo health, then report system, MCP server, and active-agent status without changing the installation

Audit React Query usage for best practices — key factories, staleTime, mutations, and server state ownership

Analyze and fix useMemo/React.memo anti-patterns in your code

Analyze and fix unnecessary useState, derived state, and server-state-in-local-state anti-patterns

Validate an existing Sim integration (tools, block, registry, and resolved-secret/model-input boundaries) against the service's API docs and Sim execution conventions

Review UI code for alignment with the emcn design system — components, tokens, patterns, and conventions

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

Pursue a long-running goal in a single session by co-ordinating subagents.

Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

Ask which skill or flow fits your situation. A router over the skills in this repo.

Grill me about specs for the workflows I want to build, within this workspace.