jimmc414/claude-code-plugin-marketplace - Page 2

tokenize-then-parse

For interpreters: separate lexing from parsing, token stream to AST, structured text processing in stages.

use-class-for-state

For complex state: encapsulate multiple interacting variables, stateful algorithms, backtracking search state.

use-comprehension-chain

For data transformation: list/dict/set comprehensions, chained filtering and mapping, creating lookup structures concisely.

use-counter-frequency

For counting and frequency: histograms, most common elements, vote tallying, neighbor counting, word frequencies, distribution analysis.

use-defaultdict-groups

For grouping and auto-initialization: adjacency lists, grouping by key, multi-maps, nested structures without KeyError handling.

use-generator-lazy

For memory efficiency: large sequences, infinite streams, early termination possible, pipeline processing without materializing all data.

use-lambda-inline

For inline callbacks: anonymous one-liner functions, key functions for sorting, trivial transformations as dict values.

use-namedtuple-record

For lightweight records: immutable data with named fields, hashable structures for sets/dicts, self-documenting tuple alternatives.

use-operator-module

For functional operations: named functions for operators, cleaner than lambdas for arithmetic, building interpreter environments.

use-sparse-set

For sparse data: infinite grids, large spaces with few active elements, membership testing, set operations on coordinates or states.

use-table-driven-rules

For rule-based systems: store rules as data, easier to add/modify than if-elif chains, simplification tables, configuration.

validate-before-process

For input validation: check format and constraints before processing, fail fast with clear errors, defensive parsing.

verify-solution-properties

For solution checking: independent verification that result is correct, separate from how it was computed.

verify-with-inline-tests

For test co-location: tests in same file as code, run with main, tests as documentation and examples.

write-docstring-first

For writing clean functions: start with docstring, iterate until code matches docstring exactly, achieve docstring-code isomorphism.

error-ux

Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.

documentation-testing

Provides heuristics for identifying incomplete or broken documentation. Use when validating README setup instructions, testing onboarding flows, or auditing documentation quality. Triggers: docs, readme, onboarding, setup validation, documentation audit.

plugin-publishing

Knowledge for extracting local Claude Code components and publishing to plugin marketplaces. Use when helping users package skills, agents, hooks into shareable plugins. Triggers: publish, marketplace, share skill, share agent, extract plugin, contribute,…

adversarial-analysis

Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.

adversarial-patterns

Library of realistic adversarial attack vectors and anti-patterns to avoid. Contains examples of valid attacks and subtle gaming patterns to reject.

local-llm

Manage local Ollama LLM models for development and testing. Use when: running local models, configuring Ollama, switching between fast/quality models, optimizing VRAM usage, troubleshooting model performance, creating Modelfiles, or integrating local LLMs…

parallel-orchestrator

Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue…

parallel-retrospective

Analyze completed parallel workflows for lessons learned. Use when: reviewing workflow execution quality, identifying process improvements, evaluating skill effectiveness, post-mortem analysis after parallel work, assessing planning accuracy. Triggers:…

parallel-worker

Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree,…

skill-name

{{SKILL_DESCRIPTION}}. Use when {{TRIGGER_CONDITIONS}}.