Menu
SkillsMP has collected 36 skills from SiddheshKGupta/Escapement. Open a skill to review its source and details.
Showing 36 of 36 collected skills.
Use at the start of MATERIAL or PROGRAM work when the user has a rough request, unclear success criteria, hidden trade-offs or missing decisions. Ask only high-impact questions, recommend defaults and produce a better execution brief.
Use when a project needs persistent storage and no database technology has been chosen yet, or an existing choice is being reconsidered. Selects a database with stated trade-offs, then designs the schema and API surface together against that choice. Do not…
Use for new UI, redesign, frontend implementation, screen or component review, responsive work, accessibility, generic AI appearance, or usability problems. Do not use for backend-only work.
Use when building dashboards, KPI tiles, management reports, or reconciliation views -- covers KPI breakdown completeness, the three-layer reporting model, and locale-correct currency/number formatting (symbol, digit grouping, unit scale) applied uniformly…
Use for design direction, brand, colour, typography, layout, visual style, animation, motion, responsiveness, design tokens, or creation/update of DESIGN.md. Also use when UI looks generic or inconsistent. Do not use for backend-only work.
Use during DISCOVER, immediately after inspecting the repository, to check whether the deterministic phase plan actually fits the task. Revise it with replan-phases when it does not. Do not use to invent phases outside the fixed ten-phase catalog.
Use when a domain problem may benefit from an existing AI agent implementation, including the 500+ AI Agents catalogue. Discover blueprints, inspect the exact linked repository and recommend reuse, adaptation or rejection. Never deploy a catalogue entry…
Use when a plan contains independent research, implementation or review tasks that benefit from fresh-context subagents or parallel execution. Do not parallelise tasks that modify the same state without a merge protocol.
Use to specify, build or review AI agents, LangGraph or LangChain systems, RAG, tool calling, memory, structured extraction, multi-agent workflows, evaluations, human approval and agent deployment. Do not deploy a catalogue blueprint without validating the…
Use when the primary deliverable is a report, SOP, proposal, presentation, spreadsheet, Word document, PDF, management note, governance tracker, or other reusable business artifact. Do not use for a tiny wording fragment.
Use for n8n, workflow automation, scheduled jobs, event triggers, webhooks, background processing, notifications or operational automations. Do not automate an undefined or uncontrolled business process.
Use for consulting analysis, business-model questions, management recommendations, operating-model design, transformation, requirements, stakeholder decisions, or when the user asks for a consultant view. Do not use for a purely technical implementation…
Use for exploratory analysis, statistical analysis, trends, cohorts, segmentation, variance drivers, forecasting inputs, analytical visualisation or decision insights. Do not use when the primary need is a reusable ingestion or transformation pipeline.
Use for ingestion, ETL or ELT, data pipelines, mapping, cleansing, validation, reconciliation, lineage, warehousing, dimensional models, semantic layers, file or API ingestion, data-quality monitoring, SQL or reporting datasets. Do not use for a simple…
Use after an approach is approved to create an implementation plan with bounded tasks, dependencies, exact outputs and verification. Prefer Superpowers writing-plans or GitHub Spec Kit when installed and appropriate.
Use when industry standards, regulation, current practices, competitors, market trends, professional norms or domain vocabulary may materially affect the recommendation. Use authoritative sources first and community signals only as supporting evidence.
Use for architecture, system design, code review, debugging, refactoring, technical debt, data models, testing strategy, performance, reliability, or implementation quality. Do not use for business analysis without a technical decision.
Use for accounting logic, financial analysis, reconciliation, portfolio analysis, management reporting, data validation, variance analysis, or KPI definitions. Do not invent figures, accounting treatment, or source data.
Use to implement approved UI, UX, pages, components, dashboards or frontend flows. Requires an approved DESIGN.md or explicit design direction. Do not use to invent the product design during implementation.
Use for governance, risk, compliance, RCSA, audit, maker-checker, approval authority, control design, exception management, privacy, or accountability. Do not invent policy or regulatory requirements.
Use for portfolio monitoring, unit economics, returns analysis, due diligence, investment theses, scenario analysis or investment committee memoranda. Do not recommend transactions from incomplete or unverified data.
Use for contract review, NDA triage, clause analysis, compliance mapping, regulatory requirements, vendor legal review or legal-risk assessment. Requires jurisdiction and authoritative sources. This skill supports professional review; it does not replace…
Use to create or review PRDs, BRDs, FRS documents, user stories, acceptance criteria, role models, journeys, information architecture, status models, KPI catalogues or feature tickets. Do not use after the specification is already approved unless behaviour…
Use to define or execute unit, integration, contract, end-to-end, negative, role, accessibility, performance, migration, reconciliation or UAT verification. Do not use to claim PASS without executed evidence.
Use when a user asks to find, compare, install, or use an external skill, plugin, GitHub repository, CLI, MCP server, service, agent framework, or open-source component; also use when Escapement lacks a specialised capability. Do not install anything before…
Use for authentication, RBAC, permissions, secrets, hooks, MCP servers, privacy, PII, payments, deployments, external integrations, vulnerabilities, or authorised security testing. Do not perform offensive testing without explicit written permission and scope.
Use only when auditing skill selection, overlap, effectiveness, installation, evaluation, promotion, retirement, or harness behaviour. Do not auto-load this skill for ordinary development work; the runtime records basic evidence internally.
Use to implement an approved bounded software task when no more specialised frontend, data, API, automation or AI-agent implementation skill applies. Do not use before requirements and acceptance are sufficiently clear.
Use before planning a new feature, product, module, workflow or material redesign. Explore alternatives through structured questions and trade-offs before selecting a design. Prefer the installed Superpowers brainstorming skill when available and compatible.
Use for complete emails, reports, proposals, SOPs, management communication, website copy, or when prose sounds generic, repetitive, artificial, or unclear. Do not use for code-only work.
Use for an API, connector, webhook, OAuth, endpoint, third-party service, MCP server, or system integration. Do not use for internal code with no external contract.
Use for dashboards, KPIs, MIS, metrics, management reporting, analytics, charts, drill-down, ageing, or reconciliation. Do not use for decorative data visualisation without an operational decision.
Use for a new product, application, module, architecture, major workflow, executable specification, or material change with unresolved scope. Do not use for an approved isolated bug or copy-only change.
Use for release, production deployment, go-live, rollout, launch, UAT, handover, or release approval. Do not use during ordinary local implementation.
Use for business processes, approvals, state machines, exception management, maker-checker controls, journeys, escalations, ownership, or SLA. Do not use for a purely visual page with no process behaviour.
Use for approved current web research through official Perplexity skills, CLI, or MCP. Do not use without approval, current licence review, and credential handling.