Coding & Dev Tools

parvez3019 Bundle

Place code in the right layer and keep dependencies pointing inward, inside a single service. Covers ports and adapters (hexagonal) layering, the dependency rule, SOLID applied at class and service level, anti-corruption layers, framework isolation, and choosing a design pattern only when a named force demands it. Use when writing or reviewing any implementation code, deciding where a class belongs, wiring a dependency, adding a framework annotation to domain code, or when the user says 'architecture', 'layering', 'SOLID', 'coupling', 'hexagonal', 'design pattern', or 'where should this go'. This skill governs structure inside one service — not where services divide (see service-boundaries), not aggregate rules (see domain-modelling), not adapter craft (see infrastructure-adapters).

parvez3019 Bundle

Make a service behave predictably when its dependencies are slow, failing, or duplicating work. Covers timeouts and deadline propagation, retry with exponential backoff, jitter and retry budgets, circuit breakers, bulkheads, rate limiting and load shedding, fallbacks and graceful degradation, idempotent consumers, the transactional outbox and inbox, saga compensation, and health probes. Use when writing or reviewing any call that leaves the process, when handling a message, or when the user says 'resilience', 'circuit breaker', 'retry', 'timeout', 'cascading failure', 'outbox', 'saga', or 'graceful degradation'. This skill governs runtime failure behaviour — not layering (see clean-architecture), not test design (see test-strategy).

parvez3019 Bundle

Surface genuine architectural trade-offs as structured options with consequences instead of silently picking one. Governs how every other skill in this library reports its Ambiguity Signals — synchronous vs asynchronous, strong vs eventual consistency, orchestration vs choreography, split vs keep together. Use when a decision has two defensible answers, when the user says 'what do you think', 'which approach', 'trade-offs', or 'options', or when another skill routes an ambiguity here. This skill governs how a decision is presented and recorded — not what the right answer is (that belongs to the domain skill that raised it).

parvez3019 Bundle

Write the adapter layer that connects a service to everything outside it. Covers designing ports at the right granularity and owning them inward, wrapping third-party SDKs so their types never reach the domain, mapping and anti-corruption at the edge, where resilience and observability belong, adapters for HTTP clients, brokers, caches, blob storage and the clock, and how to test an adapter without testing the vendor. Use when writing or reviewing a client, a consumer, a publisher, a repository implementation, a mapper, or any wrapper around an external system, or when the user says 'adapter', 'port', 'client', 'SDK', 'wrapper', 'anti-corruption layer', or 'infrastructure'. This skill governs the outer layer's craft — the layering rules themselves belong to clean-architecture, persistence specifics to data-access.

ysyecust Skill

日本語翻訳：このファイルは logistics-exception-management 用の日本語翻訳が必要です

abelrguezr Bundle

Steganography Analysis

kritika810 Skill

Guide building apps, scripts, CI pipelines, or automations on top of the Cursor SDK (TypeScript @cursor/sdk or Python cursor-sdk/cursor_sdk). Use when integrating, installing, or writing code against the Cursor SDK.

kritika810 Skill

Save, back up, or share the current project as a hosted (non-public) copy, auto-handling git setup even for users unfamiliar with git. Use when asked to save/back up/publish/share a project online.

kritika810 Skill

Run all user text after a /shell invocation as a literal shell command. Use only when explicitly invoked with /shell.

kritika810 Skill

Install, sign in, update, or repair the 'origin' CLI for Cursor-hosted git repos. Use when git push/pull fails to authenticate against origin.cursor.com.

kritika810 Skill

Keep a pull request merge-ready by triaging comments, resolving clear conflicts, and fixing CI in a loop until green.

kritika810 Skill

Create a hosted repo for the current project and push it when it has no git remote yet. Use when asked to create/push a repo or set up a remote.

kritika810 Skill

Split current work/changes/branch into a few small reviewable PRs while preserving user work. Use when asked to split work, a branch, or a PR.

kritika810 Skill

Create custom subagents for specialized AI tasks (code reviewers, debuggers, domain-specific assistants) with custom prompts and isolated contexts. Use when creating a new type of subagent.

kritika810 Skill

View and modify Cursor CLI configuration in ~/.cursor/cli-config.json (permissions, approval mode, vim mode, display, sandbox, models). Use when asked to change CLI settings.

kritika810 Skill

Modify Cursor/VS Code user settings in settings.json (themes, font, tab size, format-on-save, auto-save, keybindings). Use when asked to change editor settings or preferences.

operatorstack Bundle

Probe the environment, branch on findings, ask the user only when something needs their hands.

operatorstack Bundle

Investigate a failure with bounded hypotheses, cheap-first probes, and an evidence-bound conclusion.

operatorstack Bundle

Release Yield through its protected GitHub workflows and verify every public registry.

operatorstack Bundle

Convert an existing prose SKILL.md into a Yield program in the language of your choice, verified by executing the result.

operatorstack Bundle

Test, review, approve, publish, and verify a package in a fixed order.

operatorstack Skill

Release Yield through its protected GitHub workflows and verify every public registry.

operatorstack Bundle

Read the failed job, apply one supported repair, and rerun the failing check.

operatorstack Skill

Publish a small package safely.

outfitter-dev Bundle

This skill should be used when encountering bugs, errors, failing tests, or unexpected behavior. Provides systematic debugging with evidence-based root cause investigation using a four-stage framework.

outfitter-dev Bundle

This skill should be used when choosing CLI tools, a tool seems slow, or when best tool, which tool, or tool alternatives are mentioned.

outfitter-dev Bundle

Reference for Outfitter Dev Kit conventions including Result types, Handler contract, Error taxonomy, and transport-agnostic patterns. Use when learning the stack, looking up patterns, understanding @outfitter/* packages, or when "Result", "Handler", "error taxonomy", or "OutfitterError" are mentioned.

outfitter-dev Bundle

This skill should be used when reviewing code before commit, conducting quality gates, or when review, fresh eyes, pre-commit review, or quality gate are mentioned.

outfitter-dev Bundle

This skill should be used when requirements are unclear, brainstorming ideas, or when pathfind, brainstorm, figure out, clarify requirements, or work through are mentioned.

outfitter-dev Bundle

This skill should be used when profiling code, optimizing bottlenecks, benchmarking, or when performance, profiling, optimization, or --perf are mentioned.

outfitter-dev Bundle

This skill should be used when configuring Codex CLI, setting up profiles, or when config.toml, sandbox mode, Codex config, or approval policy are mentioned.

outfitter-dev Bundle

This skill should be used when creating plugins, publishing to marketplaces, or when plugin.json, marketplace, create plugin, or distribute plugin are mentioned.

outfitter-dev Bundle

This skill should be used when making design decisions, evaluating trade-offs, assessing code quality, or when engineering judgment or code quality are mentioned.

outfitter-dev Bundle

This skill should be used when diagnosing failures, investigating incidents, finding root causes, or when root cause, diagnosis, investigate, or --rca are mentioned.

outfitter-dev Bundle

This skill should be used when analyzing conversation patterns, identifying frustration or success signals, or when analyze conversation, what went wrong, or patterns are mentioned.

outfitter-dev Bundle

Manage context window, survive compaction, persist state. Use when planning long tasks, coordinating agents, approaching context limits, or when context, compaction, tasks, or persist state are mentioned.