n-n-code

Workflow for context packets, context audits, compaction, handoffs, session memory, and deciding what AI-agent context to load, retrieve, trim, summarize, refresh, or omit. Use for context rot, context flooding, stale or missing context, task switching, and long-running agent sessions. Do not use when prompt wording, repo file discovery for a story card, or AGENTS.md authoring is the main artifact

Python implementation and review skill. Use when writing, modifying, refactoring, or reviewing Python code, especially production Python that needs clear contracts, type safety, testability, and maintainable module boundaries. Portable across Python repos and tooling stacks.

Build a portable change-contract system for any repository. Use when creating or porting a repository workflow based on tracked feature records, lifecycle directories, a policy file, a checker, a lifecycle transition helper, and aligned docs/tests.

Use when generating, debugging, reviewing, or hardening Playwright E2E specs in an existing working harness across Node, Python, .NET, or Java — including flake triage, locator refinement with UI Mode or `codegen`, `playwright-cli` exploration, visual or responsive coverage, page-object, fixture, auth-reuse usage, or mock-boundary decisions. Not for first-time install, config repair, browser insta

Testing mindset skill for context-driven test strategy, exploratory testing, validation design, acceptance criteria, oracles, weak-test detection, edge cases, heuristics, checklists, and evidence review for code, products, plans, or claims. Use when the user asks what to test, how to test, whether evidence is enough, or to bring a tester mindset. Do not use for merely running an existing test comm

Go terminal UI implementation and review skill. Use when writing, modifying, refactoring, testing, or reviewing interactive Go TUIs built with Charmbracelet Bubble Tea, Bubbles, Lip Gloss, embedded Huh forms, Charm stack v2, tea.Model, tea.Cmd, key bindings, focus state, terminal layouts, or terminal screen state machines. Portable across Go TUI repos.

Portable workflow for repos that require tracked change contracts, verifier evidence, and smallest-proof validation. Use when a repo has a contract policy file or enforced feature-plan checker.

Overlay for config contracts, defaults, path helpers, and deterministic test coverage. Use alongside the repo's principle skill when the main task is config behavior or test coverage.

Overlay for app-owned versus vendored dependency boundaries. Portable across repos that vendor third-party code. Use when work touches vendored dependencies or their integration seam.

C++ implementation and review skill. Use when writing, modifying, refactoring, or reviewing C++ code, especially modern C++17/20/23 code that needs strong ownership, type safety, and testable design. Portable across C++ repos and build systems.

Companion overlay for multi-round collaborative drafting of large specs, proposals, decision docs, and similar documents. Use when the workflow needs structured context gathering, explicit outline approval, section-by-section iteration, and reader-testing rather than a direct documentation pass.

Combine 2 or more agent skills into one new merged skill without duplicated guidance or lost capability. Use when the user asks to merge, fuse, consolidate, deduplicate, or unify multiple local skills, `skills.sh` skills, or a mix of both into a single portable, precision-dense skill package. Do not use for ordinary multi-skill composition unless the goal is to create a new fused skill.

Prompt engineering workflow for designing, rewriting, debugging, evaluating, and optimizing LLM prompts, system prompts, developer prompts, few-shot examples, structured-output instructions, tool-use prompts, and prompt eval cases. Use when prompt behavior, reliability, safety, cost, latency, or model fit is the main task. Do not use for generic prose editing, model selection alone, or ordinary do

Create or revise reusable agent skills from a problem statement, workflow, or existing skill folder. Use when the user asks to build a skill, design an agent skill for a repo, improve a skill's triggering or structure, validate a skill with representative prompts, audit a skill for token efficiency, or turn a repeated workflow into a portable skill package.

Overlay for server-side networked code — HTTP handlers, gRPC services, message consumers. Use alongside the repo's implementation skill when implementing or reviewing backend logic.

Baseline overlay for substantial documentation authoring or restructuring: README, specs, ADRs, tutorials, how-to guides, reference docs, explanations, API docs, code comments, changelogs, and agent-facing docs. Use when the agent should classify doc type, ground claims in repo truth, and validate examples before finishing.

Companion overlay for the local `security` workflow skill when the task centers on authentication, sessions, identity recovery, or tenant-scoped access boundaries. Use with `security` for session handling, verification and reset flows, MFA, invitation logic, callback-origin trust, and organization or tenant boundary enforcement.

Overlay for graphical UI and web frontend code. Use alongside the repo's implementation skill when implementing or reviewing UI changes.

Bash implementation and review skill. Use when writing, modifying, refactoring, or reviewing Bash scripts, especially automation and repo tooling that need defensive error handling, safe quoting, predictable control flow, and maintainable shell boundaries. Portable across Bash-based repos and script stacks.

Go implementation and review skill. Use when writing, modifying, refactoring, testing, optimizing, or reviewing Go code, especially production Go that needs clear errors, context propagation, concurrency safety, interface discipline, package boundaries, REST or gRPC service boundaries, standard-library testing, pprof-backed performance work, logging, and tooling discipline. Portable across Go repo

Overlay for environment-sensitive diagnosis — service startup, install issues, platform integration, headless/container behavior, and runtime smoke checks. Portable across repos where build, install, or runtime behavior depends on the local platform.

Use when adding, extending, or repairing a repo-owned Playwright E2E harness across Node `@playwright/test`, Playwright Pytest, or .NET/Java test frameworks — including browser installation, harness config, auth reuse plumbing, package placement, or CI smoke/sharding setup. Not for ordinary spec debugging once the harness already works; route that to `playwright-testing`.

Create or revise repository AGENTS.md files from repo inspection, existing docs, and a small number of high-impact clarifications. Use when the user asks to create an AGENTS.md, improve agent instructions for a repo, convert CLAUDE.md-style guidance into AGENTS.md, or write coding-agent instructions for a repository.

Canonical overlay for non-trivial server-side networked code that needs multi-layer architecture, data-access, reliability, trust-boundary, or deeper testing discipline. Use alongside the repo's implementation skill for backend services, APIs, middleware, queues, repositories, transactions, auth-sensitive flows, or backend refactors; use `backend-guidance` for thin routine handler work.

Security workflow skill for repo-grounded threat modeling, exploit-focused security review, and secure-by-default implementation guidance. Use when the user explicitly asks for security work, or when security properties are the primary concern in a high-risk change. Do not trigger for ordinary code review, routine endpoint work, or general backend implementation just because a repo contains APIs,

Canonical overlay for graphical UI and web frontend work that is redesign-heavy, frontend-polish-heavy, or UX-review-heavy. Use alongside the repo's implementation skill when visual direction, accessibility, interaction quality, responsive behavior, forms, navigation, or data presentation need stronger design discipline; use `ui-guidance` for routine UI changes.

Overlay for day-to-day feature work and bug fixes in repo-owned code. Provides a validation checklist for build, test, format, and analysis. Use alongside the repo's principle skill.

Qt implementation and review skill. Use when writing, modifying, refactoring, or reviewing Qt C++ QWidget desktop code, especially Widgets, `.ui` forms, Designer-generated UI, models, `QAbstractItemModel`, signals and slots, `eventFilter`, `QThread`, CMake-based Qt5/Qt6 builds, layout-heavy UI, and QObject lifetime or thread-affinity problems. Portable across Qt-based C++ application repos.

Template for authoring or revising the thin repo-local overlay generated by the development contract system. Use when writing overlay guidance that names a target repo's policy path, plan directory, checker command, lifecycle helper, or validation profiles; use `development-contract-process` for ordinary work in a repo that already has the system.

Recursive self-questioning heuristic for stress-testing a plan, diagnosis, design, review, or recommendation before acting. Use when the user asks to use recursive thinking, go deeper, interrogate assumptions, pressure-test an approach, ask why/how questions, or find what would change the conclusion. Avoid for simple factual lookups or low-ambiguity tasks.

Reflective sleep-and-dream heuristic for learning from recent experience. Use when the user asks to sleep on something, dream about it, reflect overnight, learn from yesterday, or extract lessons after a meaningful task, conversation, or debugging session. Avoid for first-pass analysis, simple factual lookups, direct execution, or tasks that do not benefit from reflection.

Use when writing, reviewing, or hardening Go tests that rely on stretchr/testify — `assert`, `require`, `mock`, and `suite` — including table-driven tests, subtests, parallel tests, mocks versus hand-written fakes, error-wrap assertions, and flaky test triage with `-race` and `-count`.

Model-aware implementation planning workflow for turning a clarified story card plus repo context into an actionable plan for a human or coding agent. Use after user-story-clarifier and story-repo-scout when a story needs ordered implementation steps; avoid for story drafting, repo scouting alone, or direct code implementation.

Structured thinking skill. Merges ideation, systems analysis, critical reasoning, and convergent planning. Use when a user needs to explore and narrow a vague idea, challenge assumptions, compare approaches, or converge on a practical next move in the same pass. Do not use when sustained divergence alone is the goal or when a candidate plan already exists and needs adversarial stress-testing.

Overlay for release-facing docs, install layout, workflows, licenses, and hygiene scripts. Portable across repos with a release/packaging pipeline. Use for publication-facing changes.

Coordinate the full story-to-plan preparation workflow across user-story-clarifier, story-repo-scout, and story-implementation-planner. Use when a rough ticket needs clarification, repo scouting, implementation planning, packet validation, partial-packet resumption, or downstream skill routing before coding; avoid direct implementation.

Repo scouting workflow for using a story card, ticket, or acceptance criteria to scour the current repository, find relevant files and file paths, and append compact implementation context. Use before coding when a story needs repo context; avoid for story drafting, broad architecture review, security review, or implementation.

Workflow for drafting, rewriting, splitting, and auditing story-level requirements, user stories, feature definitions, definitions of done, and acceptance criteria into unambiguous story cards for humans and coding agents. Use for rough tickets, broad epics, or unclear product behavior; avoid for full PRDs, glossary definitions, and code implementation.