Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 18631–18660 of 21647 skills

quant-validationavelikiy/great_ctoThe methods a financial-ML result has to survive before it is evidence — purged cross-validation with an embargo, triple-barrier labelling, sample uniqueness under overlapping labels, fractional differentiation, meta-labelling, and multiple-testing correction. Written because the invariants were required of quant-researcher and nothing in the project explained how to satisfy them: a rule without a method produces either an invention or a block. Applied whenever a backtest, a feature or a label is being designed or judged.Stars: 117Updated Claude CodeCodexUnverifiedInstall
perf-analyzercomposio-community/awesome-claude-pluginsUse when synthesizing perf findings into evidence-backed recommendations and decisions.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
perf-baseline-managercomposio-community/awesome-claude-pluginsUse when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
perf-benchmarkercomposio-community/awesome-claude-pluginsUse when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
perf-code-pathscomposio-community/awesome-claude-pluginsUse when mapping code paths, entrypoints, and likely hot files before profiling.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
perf-investigation-loggercomposio-community/awesome-claude-pluginsUse when appending structured perf investigation notes and evidence.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
perf-profilercomposio-community/awesome-claude-pluginsUse when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
perf-theory-gatherercomposio-community/awesome-claude-pluginsUse when generating performance hypotheses backed by git history and code evidence.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
perf-theory-testercomposio-community/awesome-claude-pluginsUse when running controlled perf experiments to validate hypotheses.Stars: 2kUpdated Claude CodeCodexUnverifiedInstall
agent-checkclaude-world/director-mode-liteValidate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.Stars: 80Updated Claude CodeCodexUnverifiedInstall
agent-templateclaude-world/director-mode-liteGenerate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.Stars: 80Updated Claude CodeCodexUnverifiedInstall
agentsclaude-world/director-mode-liteList all available agents (core, expert, self-evolving). Use when the user asks what agents are available or runs /agents.Stars: 80Updated Claude CodeCodexUnverifiedInstall
auto-loopclaude-world/director-mode-liteTDD-based autonomous development loop with checkpoint recovery and observability changelogStars: 80Updated Claude CodeCodexUnverifiedInstall
check-environmentclaude-world/director-mode-liteVerify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.Stars: 80Updated Claude CodeCodexUnverifiedInstall
code-reviewerclaude-world/director-mode-liteCode review knowledge base: quality, security (OWASP Top 10), error-handling, performance, and test-coverage checklists with severity-ranked output format. Use when reviewing code changes, PRs, or before commits. Loaded automatically by the code-reviewer agent.Stars: 80Updated Claude CodeCodexUnverifiedInstall
debuggerclaude-world/director-mode-liteSystematic debugging method: 5-step root-cause analysis (capture, isolate, hypothesize, investigate, fix & verify) plus common bug-pattern reference. Use when errors, exceptions, test failures, or unexpected behavior appear. Loaded automatically by the debugger agent.Stars: 80Updated Claude CodeCodexUnverifiedInstall
evolving-loopclaude-world/director-mode-liteSelf-Evolving Development Loop - Dynamic skill generation with learning and evolutionStars: 80Updated Claude CodeCodexUnverifiedInstall
evolving-statusclaude-world/director-mode-liteView Self-Evolving Loop session status, history, and memory metricsStars: 80Updated Claude CodeCodexUnverifiedInstall
focus-problemclaude-world/director-mode-liteDeeply scope a problem before coding: parallel Explore agents map related files, similar implementations, and test patterns, producing a problem definition, boundaries, and minimal implementation plan. Use when planning a feature, investigating a bug, or entering an unfamiliar codebase area.Stars: 80Updated Claude CodeCodexUnverifiedInstall
getting-startedclaude-world/director-mode-liteGuided five-minute onboarding for Director Mode Lite across Claude Code, Codex CLI, and Grok Build. Use after installation or when choosing a first workflow.Stars: 80Updated Claude CodeCodexUnverifiedInstall
handoff-geminiclaude-world/director-mode-liteDelegate long-context analysis, research, and large-document summarization to Google Gemini CLI (1M-token context) via non-interactive `gemini -p`, preserving Claude context. Use when the user says 'use gemini'/'hand off to gemini' or a task needs 100K+ tokens of context.Stars: 80Updated Claude CodeCodexUnverifiedInstall
hook-templateclaude-world/director-mode-liteGenerate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.Stars: 80Updated Claude CodeCodexUnverifiedInstall
hooks-checkclaude-world/director-mode-liteValidate hooks configuration and scripts. Use after adding or editing hooks in settings.json, before committing hook changes, or when a hook fails to fire.Stars: 80Updated Claude CodeCodexUnverifiedInstall
mcp-checkclaude-world/director-mode-liteValidate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check.Stars: 80Updated Claude CodeCodexUnverifiedInstall
project-health-checkclaude-world/director-mode-liteAudit project health across 7 dimensions (documentation, test coverage, security, code quality, dependencies, database, build/deploy) producing a scored report with prioritized fixes. Use for periodic checkups, before releases, or when the user runs /project-health-check.Stars: 80Updated Claude CodeCodexUnverifiedInstall
project-initclaude-world/director-mode-liteSet up concise, guidance-first Claude/Codex/Grok project context after inspecting the repository. Use on first setup, after cloning, or when the user runs /project-init.Stars: 80Updated Claude CodeCodexUnverifiedInstall
skill-checkclaude-world/director-mode-liteValidate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.Stars: 80Updated Claude CodeCodexUnverifiedInstall
skill-templateclaude-world/director-mode-liteGenerate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.Stars: 80Updated Claude CodeCodexUnverifiedInstall
skillsclaude-world/director-mode-liteList all available skills grouped by category. Use when the user asks what skills are available or runs /skills.Stars: 80Updated Claude CodeCodexUnverifiedInstall
smart-commitclaude-world/director-mode-liteCreate clean Conventional Commits: inspect the diff, group related changes, run quality checks, and write type(scope) messages. Use when committing work, or when the user runs /smart-commit or asks to commit changes.Stars: 80Updated Claude CodeCodexUnverifiedInstall