instruction-eval
claudeMeasure whether an LLM instruction changes model behavior.
11 skills
Cost-tiered development cycle over dev-cycle: an opus prescriber writes prescriptions that leave no decision, a sonnet suborchestrator runs the loop and both reviews, disposable haiku executors follow the prescription literally. No hooks.
Plugin dev-cycle-lite from marketplace my-claude-skills in ryzhakar/claude-skills. Commands read from the repo's manifest — 23 days ago.
lite-cycleRun the dev-cycle loop over one spec at the lowest cost tier — an opus prescriber writes a prescription per unit, disposable haiku executors follow it literally, and the suborchestrator running this skill reviews each unit itself and integrates. "run the lite cycle", "implement this cheaply", "imple
prescriptive-planningWrite a prescription — an implementation prescription, or a correction prescription after a failed review — that leaves the executor — the agent that will execute it — no decision, no option, no signature to invent, and no unverifiable step. "write a prescription", "prescribe the implementation", "w
executorExecute one prescription — a plan fixing every file, signature, test, and command — literally, inside its own git worktree, and report. Use it in the lite cycle for every unit; discard it after its report. Examples: <example> Context: The lite cycle has a prescription on disk for a unit. user: "Exec
prescriberWrite a prescription — an implementation plan leaving the executor no decision, no option, and no signature — for one unit from a spec and its requirements, by the prescriptive-planning skill. Use it before each executor launch in the lite cycle, and again to rewrite a prescription around review fin
suborchestratorRun the lite cycle — plan, prescribe, execute, review, integrate — over one spec as a sonnet agent beneath the main orchestrator, launching prescribers and executors and reviewing each unit itself. Use it when the owner marks a development run lite. Examples: <example> Context: A spec file exists an
Measure whether an LLM instruction changes model behavior.
11 skills
Domain-free skills governing how an agent conducts itself while working, independent of orchestration, memory, or any specific engineering domain.
6 skills · hooks
Development cycle orchestration: specify, plan, implement, review, integrate. A spec-capturer that interviews the owner, worktree-isolated implementers, spec and code-quality reviewers, and a review chain enforced by hooks.
1 skill · 4 agents · hooks
Software engineering discipline skills, agent-agnostic: outermost-test-first signature-first TDD, systematic debugging, bug triage, architecture improvement, and receiving code review. Used ad hoc or by dev-cycle.
5 skills
Playwright test lifecycle orchestrator. One skill drives the full loop: plan from live browser exploration, generate accessible .spec.ts files, execute with failure classification, and self-heal broken locators via deterministic ten-tier recovery with confidence-based PR routing.
1 skill · 4 agents
Agent delegation framework and multi-agent research orchestration. Decompose work across model tiers, manage parallel swarms, and govern quality.
2 skills
Visual workflow automation with templates, orchestration, and lifecycle management
5 skills · 8 commands · 3 agents
Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.
1 skill · 7 commands
This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.
37 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.
85 skills · 20 commands · 19 agents · 1 MCP server · hooks
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...
21 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.