Use when the user asks to plan a feature, fix, migration, refactor, or technical project before coding. Read the repository's planning rules and current code first, split work into verifiable steps with dependencies and ownership, and preserve uncertainty instead of fabricating implementation details.
Use when the user asks to triage, investigate, mitigate, or document a production incident, outage, reliability regression, or security event. Establish scope and safety first, use current evidence, preserve forensic data, distinguish mitigation from root-cause work, and require explicit authorization for…
Use when the user asks to create, improve, review, or repair integration tests across modules, services, storage, queues, filesystems, or framework adapters. Exercise a real integration boundary with controlled dependencies, lifecycle cleanup, and evidence that the components work together.
Use when the user asks to organize notes, documents, references, or project knowledge into a searchable and maintainable structure. Inspect existing taxonomy and provenance first, preserve source meaning, mark uncertainty, and validate links and coverage after any authorized change.
Use when creating, validating, previewing, exporting, or installing an Lfcode plugin. Restricts model-authored plugins to reviewed tool or integration workspaces and requires explicit user confirmation before installation.
Use when the user asks to investigate incidents, errors, latency, crashes, missing events, or anomalous logs and metrics. Correlate real logs, metrics, traces, and runtime state within the authorized scope, redact sensitive data, and separate diagnosis from any restart or remediation.
Use when the user reports slow startup, latency, high CPU, memory growth, rendering jank, or throughput regression. Establish a reproducible baseline with available profiling tools, identify evidence-backed bottlenecks, and separate diagnosis from any authorized optimization.
Use when the user asks to design, implement, review, or repair property-based, generative, fuzz, invariant, metamorphic, or randomized tests. Express durable behavior over a broad input space, use valid generators and shrinking, and preserve a reproducible failing case.
Use when the user asks to prepare, update, audit, or submit a pull request. Inspect repository contribution rules, branch state, diff, tests, and the target base first; create a focused reviewable change description and do not commit, push, or open a hosted pull request without explicit authorization.
Use when the user requests a behavior-preserving code refactor, cleanup, extraction, consolidation, or architectural simplification. Map all references and contracts before editing, keep the change scoped, and prove behavior with focused tests and type checks.
Use when the user asks to clarify, elicit, assess, or document product or technical requirements, acceptance criteria, user flows, constraints, or risks before implementation. Inspect current behavior and existing evidence first, distinguish facts from assumptions, and obtain decisions for material scope choices.
Use when the user asks to research a topic, compare sources, summarize evidence, or produce a sourced brief. Gather information with the tools and scope actually authorized, distinguish fact from inference, retain source locations and dates, and state what could not be verified.
A setup guide for repairing or installing the local runtimes managed by Lfcode, including Python, C++, Java, FFmpeg, and a voice recorder. A runtime is the software environment needed to run a program or tool.
Use when the user asks for a security review, threat assessment, vulnerability audit, or hardening recommendation for code, configuration, APIs, or runtime behavior. Inspect actual trust boundaries and evidence, keep diagnosis separate from remediation, and do not perform unauthorized exploitation or changes.
Use when the user asks to create, revise, restructure, or quality-check a presentation or slide deck. Inspect the source deck, template, assets, audience, and available rendering tools first, then validate slide structure and rendered layout before claiming completion.
Use when the user asks to inspect, clean, analyze, transform, calculate, or produce CSV or spreadsheet workbooks. Inspect sheets, schemas, formulas, and available spreadsheet tools first, preserve source data, and validate results with independent totals and rendered or structural checks.
Use when a test fails, flakes, hangs, or gives an unexpected result. Reproduce the failure with the narrowest package-local command, distinguish test defects from product defects and environment issues, and only implement a fix when the user authorizes changes.
Use when the user asks to design, create, simplify, repair, or review test fixtures, factories, builders, seeded datasets, temporary files, or test environment setup. Produce minimal, explicit, isolated data that makes tests readable, deterministic, and safe to clean up.
Use when the user asks to design test coverage, assess test risk, create an acceptance test plan, or improve confidence before a change ships. Inspect real behavior, existing tests, contracts, and failure modes, then select the smallest test layers that cover the meaningful risk.
Use when the user asks to implement or revise a web, desktop, or mobile interface from a requirement, design, or screenshot. Inspect the existing UI architecture and real runtime first, reuse established components and tokens, and verify the rendered DOM, responsive states, and browser errors.
Use when the user asks to create, improve, review, or repair unit tests for a function, module, component, or isolated behavior. Derive observable contracts from real code, keep tests deterministic and focused, and use the repository's existing test runner and helpers.
Use when the user asks to detect, review, prevent, or update visual regressions in a web, desktop, or mobile interface. Capture comparable rendered states, control viewport and data variance, inspect image differences, and distinguish intended design changes from rendering defects.
Use when the user asks to import or translate an Lfcode Tavern or SillyTavern character card or worldbook, including PNG image cards, or manage the Tavern plugin lifecycle.
★not rated 2 26d agoA43 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: