A multi-agent stock research and risk workflow that gathers financial, market, ownership, institutional-flow, news, and broader economic information for a ticker and date. It combines those findings into a research report only when required data can be verified.
Use when creating, revising, or validating agent skills, especially when source fidelity, context efficiency, supporting-file structure, or runtime compatibility must be preserved. Do not use for generic prompt writing.
Use the Web Search Plus MCP tools (websearch, webextract) for source-backed web research: current events, prices, release notes, docs and API references, arXiv papers, CVEs, local and shopping queries, and reading a specific page. Use when the user mentions "web search plus", "websearchplus", "wsp", asks which sources…
Live graph memory for agents — query and create entities, derive relationships by rule, explain why two things are associated, read the graph at a past commit, ask what a change would do, and answer as one role. Trigger on: memory, remember, recall, relationship, entity, association, why are X and Y related, as of…
Pass coding work between Claude Code and Codex, check the other agent's work, coordinate simultaneous implementation, or run a bounded two-agent design discussion. Use for delegation, pending handoffs, shared contracts and file ownership, or when the user wants both agents to debate an approach before coding.
Use when working on a SPIP site that uses the Escal squelette — installing or activating it, placing or configuring its noisettes (blocs latéraux, onglets « À la une »), reading or writing its escal/config settings, using its special pages (agenda, contact, recherche, annuaire, trombinoscope, forum de site, mots-clés…
Use when authoring, reviewing, or reorganizing content in the Health Economics Guide repository — writing a new chapter, running quality gates, updating the glossary/index, renumbering chapters, or otherwise editing the book's source files. For repo maintainers and contributors, not general readers of the finished…
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic…
Use when authoring or diagnosing DataLens JavaScript Editor table, Gravity, Advanced, Markdown, selector charts, or HTML inside an Editor chart. Not for standalone HTML Pages, native Wizard charts, or independent SDK scripts.
Consolidate project instructions and project memory into canonical AGENTS files. Use for 'consolidate-agents-md', 'consolidate-agent-md', or an explicitly requested end-of-work context cleanup.
QAs a PrestaShop pull request against an environment that is already running, in a real browser, on the command line or over HTTP, and writes an HTML report stating whether it is approved, with the recording as proof. Use when the user says "QA this PR", "test this pull request", "check that this fix works"…
Create high-quality architecture diagrams for any project with official SVG logos and clean editorial styling. Use when asked to visualize project architecture, generate a system architecture diagram, or create an arch diagram.
Generate hierarchical Markdown index files (docmap.md) for a project repository folder structure using progressive disclosure. Also called as Repository Navigation Index generation or docmap generation.
A contract-review workflow that checks agreements for risks, links important findings to relevant laws, and produces a written review. It covers common agreements such as sales, leases, loans, services, contracting, and intellectual property.
Design, write, test, deploy, and configure Art Blocks transfer hook contracts in Solidity. Use when an artist or developer wants a contract that runs on every mint and transfer of a project's tokens — recording provenance on chain, emitting richer events, or restricting when a token may move. Covers the ITransferHook…
Build, modify, run, and inspect Abaqus models and jobs using documentation matched to the installed release. Use for CAE scripting, INP generation, parameter studies, ODB extraction, Python-runtime mismatches, and failed Abaqus analyses. Separate script generation, solver completion, and engineering validation.
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, icons, micro-interactions, enter/exit animations, or any visual detail work. Supports quick and full review modes. Triggers…
Build explainer diagrams as HTML+SVG scenes in one consistent visual grammar (pixel-font title, mono subtitle, blue/orange cards and arrows, dashed containers, network circles, stat tiles, a one-line callout) and shoot each to a PNG with puppeteer. Use whenever a concept, story, trace, comparison, or set of numbers…
A generic senior-engineer operating playbook. MANDATORY for every coding task — plan before you type, test before you claim, debug from evidence, review your own diff.
Show live long-task progress as one Discord/Telegram card that is edited in place. Use when a task will take more than a couple of minutes or many items (research, enrichment, batch writes).
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: