AI & ML

axross Bundle

Writing, reviewing, refactoring, or running end-to-end tests, or verifying a change through the e2e suite — including a prompt naming only snapshots, test IDs, selectors or locators, polling and waiting, flaky tests, scenario coverage, a runner (Playwright, Cypress, Maestro, Detox, WebdriverIO, Vitest), or a failing e2e run. Tests that drive the whole system as a real user or client does. Covers layout and naming, the test-id then role then copy locator hierarchy, poll-not-sleep waiting, server lifecycle, no live network, and a scenario catalog.

axross Bundle

Deciding whether material belongs in a skill at all, or in the project's own documentation instead, before deciding its tier; adding, editing, renaming, moving, or removing an agent skill in a project that keeps skills in two tiers; a `git status` showing installed copies or `skills-lock.json` out of sync with their source; or a skill you loaded turning out to be wrong, outdated, or missing a rule — including mid-task, and including when its upstream is one you do not own. The skill-or-document question, the storage and install model, the drift check, and how to route a defect found in an installed skill.

axross Bundle

Updating a project's own documentation when a change alters what it says, and reading it before planning one — a behaviour, a domain term, or a decision that constrains future work; also placing or updating a project's conventions or operational procedures once they share one docs/ tree with that documentation. Triggers on "docs/", "spec", "domain model", "glossary", "ubiquitous language", "ADR", "supersede", "the docs are stale", "is this documented anywhere", "conventions/", "operations/". Not spec-driven development — a plan drives the change and this records what became true, so "spec-first" and "generate from the spec" route elsewhere. Covers the docs/ shape, its invariants, decision records, conventions and operations, and five single-purpose validators.

bolasblack Bundle

Search over a million GitHub repositories for real-world code examples using grep.app. Find literal code patterns, usage examples, and implementation patterns across popular open-source projects. Perfect for discovering how developers use specific APIs, libraries, or coding patterns.

bolasblack Bundle

Web content fetching and conversion to markdown for efficient LLM consumption. Provides 1 tool for fetching URLs and extracting content.

bolasblack Bundle

Rendered guardrail framework: keep a repo's hard rules in one-rule-per-file GRL sources behind a compact router, and render only the rules a task needs. Use when gathering guardrail context before implementing or reviewing code, when creating, editing, retiring, or reviewing GRL rule files or .agents/guardrails/index.md, when running the guardrails CLI (validate, render, review-metadata, next-id), or when setting up, adopting, or bootstrapping a guardrail framework in a repo that does not have one yet. Do NOT use for ordinary lint rule authoring unless the lint rule backs a guardrail, for runtime safety guardrails such as rate limiting, destructive-command protection, or input validation, for LLM or AI output guardrails, or for soft conventions and style preferences that are not hard rules.

bolasblack Bundle

Query up-to-date library documentation and code examples using Context7. Provides 2 tools for resolving library IDs and querying documentation.

bolasblack Bundle

Access and query GitHub repository documentation using DeepWiki's AI-powered knowledge base. Provides 3 tools for browsing documentation structure, viewing content, and asking questions.

bolasblack Bundle

Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.

bolasblack Bundle

Use when the user asks to create a new Agent Skill, revise an existing skill's authored behavior or activation, audit a complete skill package, design its eval suite, port it across agent harnesses, or prepare and validate its release. When a generic skill-authoring helper overlaps, this skill owns scope, structure, portability, validation, and release history. If the work neither changes nor audits an Agent Skill package, do not load this skill.

bolasblack Bundle

Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, custom prompt shortcut, or workflow automation command for Claude Code. Helps define command structure, frontmatter, arguments, and best practices.

bolasblack Bundle

End-to-end workflow for developing, debugging, configuring, and shipping pi-coding-agent extensions and pi packages. Use when building or maintaining extensions, skills, prompt templates, themes, settings.json setups, provider integrations, or when updating this skill after pi releases. Do NOT use for general coding questions unrelated to pi extension development.

bolasblack Bundle

Convert MCP servers to Claude Code skills with progressive disclosure. Use when creating a skill from an MCP server, updating an existing MCP skill, or converting MCP documentation to skill format. Accepts MCP documentation URLs, npm package names, or direct connection info.

bolasblack Bundle

Coordinate multiple agents working in parallel using git worktrees to avoid file conflicts. Use when needing concurrent agents to modify different files/components with worktree isolation, or when asked to use worktrees for parallel agent work.

rkortthinkwise Skill

Reload OAuth scopes for an HTTP MCP connector (e.g. sf_mcp) by querying its /mcp endpoint's OAuth protected-resource metadata and syncing the local "scopes" config to match what the server currently advertises. Use when a connector's available scopes may have changed, when tools are unexpectedly missing/denied, or when the user asks to "refresh"/"reload"/"resync" MCP scopes.

rkortthinkwise Bundle

Reference guide for creating and maintaining application menus, groups, and items — including per-role visibility — in a Thinkwise Software Factory model. Use via an MCP connector with Software Factory access whenever creating, inspecting, or securing a menu, and before deciding whether a new screen/report/task belongs on an existing menu/group or needs a new one.

rkortthinkwise Bundle

Reference guide for creating and maintaining cubes (analytical pivot/chart views) in a Thinkwise Software Factory model — the cube/cube_field/cube_field_query/cube_view/cube_view_field/cube_view_field_filter/cube_view_field_total/cube_view_field_conditional_layout/cube_view_grp family, dimensions vs. values, aggregation types, intervals and hierarchies, calculated fields, pivot and chart settings, editable values, and per-role/per-variant cube rights. Use before calling get_entity_definition/get_task_definition/execute_odata_query/stage_resource/stage_task against any of these entities, and before deciding whether a request needs a cube at all versus a Grid, report, or dedicated BI tool.

rkortthinkwise Bundle

Reference guide for the icon repository (icon/icon_grp/icon_tag) and every verified place an icon can be assigned in a Thinkwise Software Factory model — tables, tasks, reports, prefilters, menus, cube views, domain elements, message options, form/report navigation, conditional layouts — plus the semantic vocabulary for choosing the right icon per object/action/state. Use whenever an MCP connector with Software Factory access creates, inspects, reuses, replaces, or assigns an icon, or before calling get_entity_definition/execute_odata_query/stage_resource/stage_task against icon, icon_grp, icon_tag, or any `*icon_id`/`image_id` field.

rkortthinkwise Skill

Reference guide for creating and configuring tasks in a Thinkwise Software Factory model — task types, parameters, look-ups, form setup, variants, and table task assignment. Use whenever an MCP connector with Software Factory access creates, inspects, or troubleshoots a task, before working with the task, task_parmtr, task_ref, task_variant, or tab_task family of entities.

rkortthinkwise Bundle

Reference guidelines for designing and naming domains, tables, and columns in a Thinkwise Software Factory data model — naming conventions, entity classification, column order, data types, references, and menu placement. Use whenever designing or reviewing a data model, or making sf_mcp calls that create or inspect domains, entities, columns, or references, to check names, types, and structure against these conventions before proposing or executing changes.

rkortthinkwise Skill

Base check to run before doing real work through any MCP connector that provides Thinkwise Software Factory access (e.g. sf_mcp, meta_dev, indicium). Confirms which connector, which application model, and which branch (model_id/branch_id) apply, since one Software Factory repository commonly hosts several application models with multiple branches each and most entities are keyed by model_id/branch_id. Use once near the start of a task that will call get_domain_definition/search_capabilities/get_entity_definition/execute_odata_query/stage_resource/stage_task/patch_resource/commit_resource — not before every individual tool call.

rkortthinkwise Skill

Reference guide for creating, configuring, and maintaining table, task, and report variants in a Thinkwise Software Factory model — the field-level-vs-snapshot inheritance mechanism and the Changes-compared-to-default/where-used mechanics. Use whenever creating, inspecting, or troubleshooting a variant via an MCP connector with Software Factory access, and before deciding whether a request needs a new variant at all versus a prefilter, a new screen type, or a separate table/task/report.

rkortthinkwise Bundle

Reference guide for creating and configuring prefilters and prefilter groups (tab_prefilter, tab_prefilter_grp, tab_variant_prefilter_overview) in a Thinkwise Software Factory data model — column-based vs. query-based prefilters, and prefilter groups. Use whenever an MCP connector with Software Factory access creates, inspects, or troubleshoots a prefilter or prefilter group, including before calling get_entity_definition/execute_odata_query/stage_resource against these entities.

rkortthinkwise Bundle

Interview the user about a goal or problem in a Thinkwise Software Factory application, then produce a reasoned build plan across data model, screens, tasks, process flows, control procedures, subroutines, and messages. Use when the user brings a raw goal or feature idea without an already-formed technical plan — not for stress-testing an existing plan, or a small, self-evident ask. Hands off each artifact to the skill that implements it; this skill only plans.

rkortthinkwise Bundle

Reference guide for creating and configuring process flows (and system flows) in a Thinkwise Software Factory model — process_flow/process_action/process_step/process_variable/process_flow_schedule entities, every process action type, which types can be a starting point, control-procedure-backed logic, loops, alignment, and naming conventions. Use whenever an MCP connector with Software Factory access (e.g. sf_mcp, indicium) creates, inspects, or troubleshoots a process flow — before calling get_entity_definition/execute_odata_query/stage_resource/stage_task against process_flow, process_action, process_step, process_variable, process_flow_schedule, or process_action_start_object_available.

rkortthinkwise Bundle

Reference guide for creating and using Web Connections and OAuth servers in a Thinkwise Software Factory model, the preferred mechanism for calling external HTTP/REST APIs. Covers authentication, endpoint and parameter setup, response parsing, and wiring a connection into a process flow. Use whenever an MCP connector with Software Factory access creates, inspects, or troubleshoots a web connection or OAuth server, in place of a one-off http_connector process action.

rkortthinkwise Bundle

Reference guide for the screen components that present a Thinkwise Software Factory subject (table or view) — Grid, Form, Card List, Treeview, and Drag-and-drop — covering the tab/col-level settings (tree_*/card_list_*/form_*/grid_* fields), their tab_variant_*_overview per-variant counterparts, and the drag_drop/drag_drop_parmtr/drag_drop_matrix family. Use whenever an MCP connector with Software Factory access (sf_mcp, indicium) is setting up or troubleshooting a subject's Grid/Form/Card List/Tree/Drag-drop behavior — before calling get_entity_definition/execute_odata_query/stage_resource against tab, col, tab_variant_grid/form/tree/card_list(_overview), or drag_drop*.

rkortthinkwise Bundle

Reference guide for translating model objects in a Thinkwise Software Factory model — the transl_object/transl_object_transl entities, appl_lang/branch_appl_lang, the approval_status review workflow, naming/plural/help-text conventions, and linking a base model to back-fill an officially supported language instead of hand-translating it. Use whenever an MCP connector with Software Factory access (e.g. sf_mcp, sf_dev_wiz_mcp, insights) reads, writes, generates, or reviews translations, or adds a new application language — before calling get_entity_definition/get_task_definition/execute_odata_query/stage_task against transl_object, transl_object_transl, appl_lang, branch_appl_lang, linked_model, or linked_model_available.

wonderslife Bundle

PDD Entropy Reduction Agent, continuously monitors and repays technical debt to prevent system decay. Automatically triggered when users need code cleanup, documentation updates, technical debt management, architecture alignment, entropy reduction, or garbage collection. Core Objective: Combat system "entropy increase" and "decay" by periodically running agents to discover documentation inconsistencies or architecture constraint violations. Trigger Scenarios: - User requests "entropy reduction", "clean up technical debt", "code cleanup", "garbage collection" - User requests checking documentation and code consistency - User requests architecture constraint checking - User requests technical debt audit - Scheduled trigger (recommended weekly) - Automatic trigger after code commit (optional) - Automatic trigger after PR merge (optional) 支持中文触发：熵减、清理技术债务、代码清理、文档更新、技术债务管理、架构对齐、垃圾回收、PDD熵减。

paulieb89 Bundle

Investigate a UK Member of Parliament. Pulls financial interests, voting record, Hansard contributions, and cross-references with Companies House. Use when someone asks "dig into my MP", "what are their interests", "how did they vote on X", "who funds them", or names a specific MP. Requires UK Legal MCP and UK Due Diligence MCP servers.

paulieb89 Bundle

Run a full due diligence check on a UK company or director. Cross-references Companies House, Gazette insolvency, HMRC VAT, and the Disqualified Directors register, then scores against a configurable risk profile (lender, journalist, acquirer, AML, or your own). Produces a CLEAR / WATCH / FLAG verdict with weighted reasons. Use when someone asks "check this company", "due diligence on X", "is this company legit", "who owns X Ltd", "is this director disqualified". Requires the UK Due Diligence MCP server.

paulieb89 Bundle

Screen a UK property investment deal from a Rightmove URL or address. Pulls comps, yield, EPC, stamp duty, and rental data, then applies underwriting criteria to produce a BUY/WATCH/PASS decision with reasoning. Use when someone says "should I buy this?", "screen this property", "is this a good deal?", or pastes a Rightmove URL. Requires the Property MCP server (property-shared) to be connected.

paulieb89 Bundle

Research a UK legal question and produce a structured brief. Finds relevant legislation with section text, case law, OSCOLA citations, and a plain English summary. Use when someone asks about UK law, compliance, case law, or "what does the law say about X". Requires the UK Legal MCP server.

paulieb89 Bundle

Researches a UK company you want to pitch to and drafts a credible cold outreach email with a specific, verifiable opening hook. Combines Companies House data (profile, officers, PSC, insolvency, VAT, land registry) with a web sweep for recent press, hires, launches, and public statements. Produces two outputs: a scannable research brief and a first draft email under 150 words. Use when the user says "help me pitch X", "draft a cold email to X", "research X for outreach", "I want to approach X about Y", "prep me to pitch X", "write an outreach email to X", or similar outbound prospecting requests. Requires the UK Due Diligence MCP server. UK companies only (non-UK targets get web-only research with a caveat).

paulieb89 Skill

Produce an earned value management (EVM) report from a Primavera P6 XER file. Calculates PV, EV, AC, CPI, SPI, and forecasts, with progress breakdown by WBS and resource utilisation. Use when someone says "earned value report", "EVM analysis", "is this project on budget", "CPI/SPI", or needs cost and schedule performance metrics from a P6 file. Requires the PyP6Xer MCP server (pyp6xer-mcp) to be connected.

paulieb89 Skill

Audit a Primavera P6 XER schedule file. Produces a health score, critical path analysis, float distribution, logic quality assessment, and prioritised recommendations. Use when someone uploads an XER or asks to check, audit, or review a schedule. Requires the PyP6Xer MCP server.