๐
Plugins
Loading...
Showing 30 of 27361 results
Calculate TAM, SAM, and SOM with explicit assumptions, methods, and caveats.
Deploy tiny web apps to a private HTTPS URL you open on your phone.
Run 300+ Tamarind Bio protein and molecular-science tools through the authenticated MCP server โ structure prediction, design, docking, and analysis.
from chatii/claude-code-finding-tanaoroshi
Edit and iterate on documents with any MCP-capable AI. Claude is the default and best-supported client today.
Tandoor Recipes tools over the Authentik-authenticated MCP gateway, plus a tandoor-agent that follows the curated food-vocabulary conventions and treats food merges as approval-gated.
uv-first enforcement: blocks system python/pip, teaches uv shebang scripts
TanStack Start guidance for scaffolding examples, routing patterns, full-stack app structure, and agent-friendly implementation workflows
Node-tap and Testcontainers integration expertise: container-based testing, test lifecycle, service orchestration, and best practices for Node.js
Search the Tapaya documentation and REST API from your AI editor over MCP.
Auto-injects PROBE-first behavior, file:line citation enforcement, dev-tooling-vs-runtime distinction, and friction-as-memory writing for Claude Code sessions in any Tapestry-consuming project. 4 hooks cover the session lifecycle (SessionStart auto-recall + architecture snapshot; UserPromptSubmit PROBE injection; PreToolUse write audit; Stop upskilling check + Path A observer). Registers the loom-memory MCP. Emits OTel telemetry per the coordination contract. Renamed from loom-discipline.
Canonical patterns library โ ONE home for the reusable agents, skills, and tools that ship with the platform. Available in every Claude Code session so the same pattern means the same thing wherever invoked. Includes drift-watcher, infrastructure-mapping, next-actions-planning, lessons-learned, agentic-skill-design, deep-research-pattern, documentation, seed-leftover-audit, template-inheritance-check, id-rename-blast-radius, and more. Renamed from liz-patterns.
Multi-source drug-target due-diligence โ turn a ranked gene list (e.g. scRNA-seq DE output) into a per-gene dossier across UniProt, OpenTargets, and PubMed, plus a local cross-lineage DE scan, then re-rank by a configurable composite score (cross-lineage convergence + druggability + disease genetics + tractability + novelty). Disease-agnostic: configurable focus disease and cell-context queries.
Loads a task description from `.claude-task.md` and surfaces it as findings for `/apply-fix` to consume. Read-only โ reports findings without editing files.
Structured task execution with multi-agent review: plan, analyze, approve, implement, QC, present
Non-technical, business-only feature planning mode for product partners who don't write code. Activates session-wide on persona-declaration phrases ('ะฏ ะฟัะตะดััะฐะฒะปัั ะฑะธะทะฝะตั'). Produces business-draft artifacts auto-detected by the companion task-planner skill.
Dispatches tool-heavy, high-output, and information-gathering work to a cheaper Haiku subagent that carries out explicit orders and returns a compact report, so the main high-reasoning agent spends its expensive tokens on judgment instead of on tool output. Session hooks never reach subagents, so a PreToolUse hook rewrites each Agent dispatch in flight to stamp the directive onto the spawned subagent's prompt. The same hook intercepts destructive and outward-facing commands from the runner โ it cannot judge whether destroying something is right โ and asks YOU to approve each one, since no model can accept that risk on your behalf; it denies instead when the permission mode means no prompt reaches a person. Toggle with /task-gopher.
ไปปๅกๅฎๆๆ็คบ้ณๆไปถใๅจ Claude Code ไปปๅกๆง่กๅฎๆๅๆญๆพๆ็คบ้ณๆ้็จๆทใ
Project analysis and planning agent โ decomposes complex tasks, creates implementation plans, identifies risks and dependencies
from Angriff36/task-orchestrator