Yesterday-AI
- 87 skills
- 0 followers
- 2 repo stars
- 2 days ago last updated
- ▌ Coordinate · yesterday-aiCoordinator mode for the session that owns a plan and delegates all of it, writing no product code itself. Use when many lanes are in flight, when a plan has dozens of work packages, when a session with open lanes continues after a compaction or a resume, or when the user says coordinate this, run the plan, you are the coordinator, keep the lanes moving, where does each lane stand. Not for one milestone with a handful of independent slices (spawn-milestone-team) and not for doing a task yourself (plan-task).
- ▌ Lane Retro · yesterday-aiLooks at a sample of finished lanes while coordinated work is still running and proposes checks and pointers for what went wrong in them. Use when several lanes finished, when a lane went wrong, when the same finding came back in a review, or when the user says lane retro, why does this keep happening, what do the lanes keep getting wrong. Not the retrospective of a finished milestone (retro) and not a review of one change (code-review).
- ▌ Quick Task · yesterday-aiQuick lane for a change the user can describe in one sentence (fix, tweak, rename, bump, small refactor) in a project with .ytstack/ and PREFERENCES quick_lane on: Q###-PLAN and Q###-SUMMARY under .ytstack/quick/, a verification command, no pitch, no review, no milestone bookkeeping. Not for new features, migrations, unknown root causes or more than about three files (plan-task, systematic-debugging).
- ▌ Code Review · yesterday-aiReviews the active task's commits with a fresh-context reviewer subagent and handles the feedback with technical rigor, through the vendored superpowers requesting-code-review and receiving-code-review procedures, with the task plan and commit range injected. Use after a task's commits exist and before summarize-task, before a merge or PR, or when the user says review this, code review, check my changes. Not for reviewing a plan (plan-eng-review) and not without commits for the task.
- ▌ Finish Lane · yesterday-aiTakes a delegated lane from the worker's report to a pull request merged at the reviewed commit, with every gate read from the host. Use in the coordinating session when a lane reported and its work has to become a merged pull request, or when the user says finish the lane, land this lane, get this lane merged. Not for the session's own branch (finish-branch), not for a release (ship) and not for the worker of the lane.
- ▌ Minimal Code · yesterday-aiWork contract the SessionStart hook points at when PREFERENCES minimal_code is on, and that every dispatched brief carries. Load before writing or changing code, before adding a check or a review round, and before reporting: it decides how little code and how little evidence is enough, and what must never be cut. Not user-invoked and not a procedure skill.
- ▌ Finish Branch · yesterday-aiDecides how a finished branch or worktree is integrated (merge locally, push + PR, keep) through the vendored superpowers finishing-a-development-branch procedure, with ytstack's branch, worktree and task-summary state injected. Use when the slice or milestone work on a branch is done and verified, or when the user says finish the branch, merge this, open the PR, wrap up the worktree. Not before verification-before-completion passed and not for closing a task (summarize-task).
- ▌ Handover Step · yesterday-ai bundlePrepares a step that only the human may perform (a production action, a check in a GUI application, anything behind their credentials or their eyes) as one staged script they start with one short command. Use when the plan, a gate or a standing instruction reserves a step for the human, or when the user says hand this over, prepare the production step, give me a script for it. Not for a step the agent may do itself, and not for a decision only the human can take (that is a question file under .ytstack/questions/, written with bin/ytstack-questions).
- ▌ Signal Intake · yesterday-aiReads the signal sources a project declares under Signals in RUNTIME.md (an error tracker, a latency report, alerts, logs) and records what is new, seen again or back after a fix as findings under .ytstack/signals/, changing nothing else. Use in a scheduled or unattended run, or when the user says look at what production reports, check the error tracker, anything new in production, go through the alerts, run the signal intake. Not for an outage that is happening now (incident), not for finding the cause of one finding (systematic-debugging) and not for watching a release after a merge (finish-lane).
- ▌ Visual Review · yesterday-aiIndependent visual review of a user interface change at the running product, against the project's design and product guidelines: the reviewer judges screens it rendered and captured itself, never code and never images from the author. Use when a review brief names a lens with visual evidence, or when the user says visual review, look at the UI of this commit, check how this change looks, review the screens. Not for reviewing code (code-review), not for checking behaviour (verification-before-completion), and not for fixing what it finds.
- ▌ Review Lessons · yesterday-aiLooks at the review-bot findings of merged pull requests that the project's own review roles missed and turns repeated or severe ones into a proposed line for the owning role's file, as a question for a person. Use after a pull request merged in a project whose REVIEW.md declares own reviewers, when PR watch or bin/ytstack-upkeep says a merged pull request has no escape check, or when the user says what did the bots catch that our reviewers missed, review lessons, learn from the bot findings. Not for reviewing a change before it merges (code-review) and not for what production reports (signal-intake).
- ▌ Adopt Brownfield · yesterday-aiBrings an existing codebase under ytstack by reference, without a greenfield pitch. Use when a repo has a README, docs, CHANGELOG, ADRs or months of commits but no .ytstack/ yet, when a project has .ytstack/ but no technical spec under .ytstack/spec/ yet (adds only the spec), or when the user says adopt ytstack, set up ytstack here, onboard this codebase, map the codebase, write the technical spec. Not for ideas without code yet (office-hours, then init-project) and not for repos that already have .ytstack/ with a spec (resume-session).
- ▌ Document Release · yesterday-aiWrites the release documentation for a version bump (CHANGELOG section, release notes), fed with the task summaries since the last tag. Use when a version is being cut, after ship or finish-branch landed the work, or when the user says write the changelog, release notes, document the release. Not for ad-hoc docs edits (quick-task) and not for the retrospective (retro).
- ▌ Ship · yesterday-ai bundleShips the current branch (merge the base, tests, coverage and plan audit, pre-landing review, version and CHANGELOG, docs sync, commit, push, pull request), gated on ytstack's slice state. Use when a slice or milestone is closed on paper and verified, or when the user says ship it, open the PR, land this, create a PR. Not before every task of the slice has a summary (summarize-task), not for merging into the base locally (finish-branch), and never for a merge without an explicit merge instruction.
- ▌ Grill · yesterday-aiRelentless questioning of an idea before it becomes a milestone, through the vendored superpowers brainstorming procedure with ytstack's pitch, project one-liner and decisions injected; writes the agreed design into the milestone context. Use between office-hours and plan-milestone, when a feature request is bigger than one sentence, or when the user says grill me, poke holes in this, let's think this through, design before we plan. Not for one-sentence changes (quick-task) and not for slicing or task plans (slice-milestone, plan-task).
- ▌ Retro · yesterday-aiMilestone retrospective fed with the milestone's task summaries, deviations and follow-ups plus the git history of the milestone window, written to M###-RETRO.md. Use after a milestone's last slice closed and reassess-roadmap ran, or when the user says retro, retrospective, what did we learn, lessons from this milestone. Not mid-milestone (reassess-roadmap) and not for closing a task (summarize-task).
- ▌ Lesson · yesterday-aiCloses an incident of any class with its lesson: names the class in one line, puts the lesson where a machine checks it (a test, a guard, a CI step, an alert) or else into KNOWLEDGE.md or the lane contract, and records it in the signals ledger so that a repeat of the class counts. Use at the end of incident, systematic-debugging, finish-lane and coordinate, which call it, or when the user says learn from this, what is the lesson, make sure this does not happen again, that is the second time this happened, always learn from incidents. Not for working the incident itself (incident, systematic-debugging), not for review-bot findings the own reviewers missed (review-lessons) and not for sampling finished lanes (lane-retro).
- ▌ Incident · yesterday-aiWorks a production incident together with a person: one record of what is seen, the timeline and the hypotheses, and every mitigation prepared as a staged script that the person starts. Use when the user says production is down, the site is broken for customers, we have an incident, users cannot log in or pay, we need to roll back, or comes back to an incident that is still open. Not for a defect that hurts no running user and not for finding the root cause afterwards (systematic-debugging), not for the routine reading of what production reports (signal-intake), and not for one planned production step (handover-step).
- ▌ Reconcile · yesterday-aiConsent-based cleanup of .ytstack/ leftovers: draft summary stubs, unfilled auto-drafts, milestones planned but never sliced, untracked .ytstack files, a .ytstack/.local without gitignore, history that grew inside STATE.md, slice and task files of closed milestones, and a large plan outside .ytstack/ (plans/*.md tables or checklists) that ytstack-frontier cannot see. Use when the SessionStart STATE lint reports warnings, or when the user says reconcile, clean up .ytstack, tidy the artifacts, the frontier shows nothing, map our plans into milestones. Never deletes; the only sanctioned way to move .ytstack artifacts.
- ▌ Wrapup 2 · yesterday-ai bundleGeneric end-of-conversation sweep -- works in any project, at any point. Looks at what the current repo actually has (docs, planning files, agent context, changelog, ADRs, memory layers...) and proposes which of them to extend with the learnings, decisions, and follow-ups that surfaced in the conversation. Then prepares a paste-ready resume prompt for after /compact. Use when the user says "wrapup", "wrap up", "wrap things up", "lass uns wrappen", or before /compact.
- ▌ Miro Board 2 · yesterday-ai bundleCreate and read Miro board content via MCP tools. Diagrams (flowcharts, mindmaps, UML, ER), documents (markdown), tables, and context extraction. Use when: user asks to create or read diagrams, documents, or tables on Miro boards, or to extract structured content from existing boards. Requires: Miro MCP server connected (npx miro-mcp).
- ▌ Web Design 2 · yesterday-ai bundleBuild distinctive, production-grade frontend interfaces with high design quality. Use when asked to build websites, landing pages, dashboards, web apps, or any web UI that should look polished and modern. Generates creative, polished code that avoids generic AI aesthetics. Includes Yesterday corporate identity briefing for branded reports and deliverables.
- ▌ Vrr Efa API 2 · yesterday-ai bundleLive-Fahrplanauskunft für den VRR (Verkehrsverbund Rhein-Ruhr) via EFA API. Abfahrten, Verbindungen, Haltestellen -- Echtzeit, kostenlos, kein API Key. Use when: user asks for train/bus/tram connections, departures, or transit info in NRW/Ruhrgebiet. Also works for DB Regionalverkehr in the region.
- ▌ Paperclip API 2 · yesterday-ai bundleManage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API. Use when creating companies, hiring agents, assigning tasks, managing budgets, approving hires, or checking dashboards on a Paperclip instance.
- ▌ Voxtral Tts API 2 · yesterday-ai bundleText-to-speech via Mistral Voxtral TTS API. Generate natural, emotionally expressive speech in 9 languages. Supports voice cloning from 3s audio samples, preset voices, streaming, and cross-lingual synthesis. Use when you need to generate speech, narrate content, create voice messages, or build voice agents.
- ▌ Figma Console MCP 2 · yesterday-ai bundleConnect AI agents to Figma via the Figma Console MCP server. Enables design system extraction, UI component creation, variable/token management, visual debugging, FigJam boards, and Slides presentations. Use when an agent needs to read, create, or modify Figma designs programmatically.
- ▌ Para Memory Files 2 · yesterday-ai bundleFile-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.
- ▌ Excalidraw Diagram 2 · yesterday-ai bundleCreate Excalidraw diagram JSON files that make visual arguments -- workflows, architectures, concepts. Use when the user wants to visualize systems, processes, or ideas as .excalidraw files. Covers design methodology, section-by-section building, render-validate loop, and quality checklist.
- ▌ Creative Productivity 2 · yesterday-ai bundleGenerate professional consulting deliverables: Excalidraw diagrams, Mermaid visualizations, Reveal.js/Marp presentations, draw.io architecture diagrams, one-pagers, and proposal documents. Use when a user asks for visual artifacts, slides, diagrams, architecture visuals, consulting documents, pitch decks, workshop materials, or any creative deliverable for client-facing or internal use. Covers the full "Consulting as Code" creative pipeline.
- ▌ Create Shareable Skill 2 · yesterday-ai bundleTurn an existing skill or a fresh idea into a catalog-ready shareable skill -- run the quality gate, decide public-vs-private catalog and standalone-vs-bundle placement, pick the category, scaffold SKILL.md (+ optional .plugin.json), update the catalog docs, and open a PR to main. Use when adding a new skill to this repo, promoting a personal or ad-hoc skill into a shareable one, or routing a skill into the right catalog.
- ▌ Plan Task · yesterday-aiFlesh out a single task within the current slice. Reads M###-S##-PLAN.md, picks the next unplanned task, writes M###-S##-T##-PLAN.md with exact file paths + verification steps. Enforces fits-one-context-window rule. Run after slice-milestone, before executing the task.
- ▌ Oss Project · yesterday-ai bundleScaffold, polish, and publish open-source projects with AI-first documentation, governance, and CI. Use when: Starting a new OSS package, polishing/publishing an existing repo, setting up AGENTS.md / CONTEXT.md / DECISIONS.md / ROADMAP.md, onboarding AI agents to a codebase, or creating standard community files (README, LICENSE, CONTRIBUTING, CHANGELOG, CI pipelines, issue templates). Outputs repo description and tags at the end.
- ▌ Init Project · yesterday-aiScaffold a ytstack project's `.ytstack/` directory with the 6 core artifacts (PROJECT.md, DECISIONS.md, KNOWLEDGE.md, RUNTIME.md, STATE.md, PREFERENCES.md). Use AFTER a pitch has been validated via office-hours (and optionally plan-ceo-review / plan-eng-review in concept-mode) -- init-project reads OFFICE-HOURS.md frontmatter to populate PROJECT.md name + one-liner. Do NOT use as the greenfield entry-point for unvalidated ideas; run office-hours first.
- ▌ Office Hours · yesterday-aiUse as the first step when a new project, feature, or initiative has not yet been validated, or whenever the premise needs a forcing-question test. Six forcing questions expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Produces OFFICE-HOURS.md pitch artifact with name + one-liner frontmatter that downstream skills (plan-ceo-review concept-mode, init-project, plan-milestone) consume. Thin ytstack wrapper around the vendored gstack office-hours procedure.
- ▌ Atomic Design · yesterday-aiAtomic Design methodology for structuring React/Next.js component libraries. Defines five levels (atoms, molecules, organisms, templates, pages) with hard import rules, classification tests, and anti-patterns. Use when creating, reviewing, or restructuring frontend components.
- ▌ Using Ytstack · yesterday-aiEstablishes how agents find and invoke ytstack skills. Requires Skill-tool invocation before any response when a ytstack skill applies. Auto-injected by the SessionStart hook. Not meant for direct user invocation.
- ▌ Plan Milestone · yesterday-aiPlan the next milestone: goal, exit criteria, rough size. Creates M###-CONTEXT.md and M###-ROADMAP.md. Run after init-project has scaffolded `.ytstack/`, before slice-milestone. Draws the goal from a validated pitch when available (OFFICE-HOURS.md or prior milestones); if no pitch exists yet in greenfield, prefer office-hours first so the milestone is grounded in real demand. Updates STATE.md with the new current_milestone.
- ▌ Resume Session · yesterday-aiReconstruct working context at the start of a new session. Reads STATE.md + HANDOFF.md (if present) + latest 3 T##-SUMMARY.md files and synthesizes a 'where we are' briefing. Run at session start before doing anything else.
- ▌ Summarize Task · yesterday-aiAfter executing a task, write its outcome summary. Reads M###-S##-T##-PLAN.md, prompts for what happened, writes M###-S##-T##-SUMMARY.md, flips checkbox in slice-plan, updates STATE.md. Optionally stages git. Run once per task completion.
- ▌ Handoff Session · yesterday-aiUser-triggered session handoff. Writes a detailed HANDOFF.md with current state, open items, pending decisions, and recommended resume prompt. Use before switching machines, before long breaks, or when you need to clear context intentionally. Parallel to the automatic pre-compact hook.
- ▌ Plan Ceo Review · yesterday-aiChallenge premise, scope, and ambition via four modes: SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) before any scaffolding exists; milestone-mode reviews a committed milestone (M###-CONTEXT.md + M###-ROADMAP.md) before slicing. Use concept-mode right after office-hours to stress-test the pitch; use milestone-mode after plan-milestone and before slice-milestone. Thin ytstack wrapper around the vendored gstack plan-ceo-review procedure.
- ▌ Plan Eng Review · yesterday-aiReview execution approach for feasibility, architecture, data flow, edge cases, test coverage, performance, and security risks. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) for technical feasibility before any scaffolding; milestone-mode reviews slice-plans (M###-S##-PLAN.md) before plan-task. Use concept-mode optionally after plan-ceo-review to sanity-check the pitched approach; use milestone-mode after slice-milestone to lock architecture before implementation. Thin ytstack wrapper around the vendored gstack plan-eng-review procedure.
- ▌ Slice Milestone · yesterday-aiBreak the current milestone into slices. Reads M###-ROADMAP.md, asks for slice content until all slices are filled. Creates M###-S##-PLAN.md per slice. Enforces 1-7 tasks per slice (iron rule). Run after plan-milestone, before plan-task.
- ▌ Reassess Roadmap · yesterday-aiAfter a slice completes, review whether the milestone roadmap still fits reality. Reads recent summaries, surfaces deviations, prompts for roadmap changes (add/split/reorder/remove slices). Run at slice boundaries, not mid-slice.
- ▌ Spawn Milestone Team · yesterday-aiDispatch the current milestone's slices to a Claude Code Agent Team. Each teammate works on a slice in parallel with its own 200k context (replaces GSD's fresh-subprocess-per-task pattern). Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 and v2.1.32+. Run after slice-milestone + plan-eng-review.
- ▌ Systematic Debugging · yesterday-aiRoot-cause debugging in four phases: investigate, analyze, hypothesize, implement. Iron Law -- no fixes without root cause. Thin ytstack wrapper around the vendored superpowers systematic-debugging procedure, routing findings into KNOWLEDGE.md / DECISIONS.md. Use when hitting a bug, test failure, or unexpected behavior.
- ▌ Deutschland Stack API · yesterday-aiUse when picking technologies for German public-sector projects (Bund/Länder/Kommunen), EU digital sovereignty contexts, or when user mentions Deutschland-Stack / DS-konform / Verwaltungs-IT. Biases tech choices toward the 128 graduated open-source standards catalogued by the German government. Fetches live data from technologie.deutschland-stack.gov.de.
- ▌ Software Craftsmanship · yesterday-ai bundleClean code, robust architecture, no test slop. Foundational skill for high-quality software engineering, code structure, and reviews.
- ▌ Test Driven Development · yesterday-aiRED-GREEN-REFACTOR: write a failing test, watch it fail, write minimal code, watch it pass, commit. Thin ytstack wrapper around the vendored superpowers test-driven-development procedure, injecting the current task's plan as context. Use during task execution.
- ▌ Check Consistency · yesterday-aiAudit ytstack internal consistency. Compares README (source of truth) against docs/concept.md, .ytstack/DECISIONS.md, and actual plugin content (skills/, hooks/, agents/, artifacts). Reports drift: missing or extra skills, workflow mentions that do not resolve to real skills, trigger-map gaps, hook-list mismatches, skill-count drift, banned-words hits. Run before approving doc changes or after a vendor subtree pull. Does not fix anything -- humans decide how to reconcile.
- ▌ European Alternatives API · yesterday-aiUse when picking software for EU customers, GDPR-driven replacements, digital-sovereignty contexts, or when user asks for the European / open-source version of a US product (Google Drive, Dropbox, Slack, …). Biases tech choices toward the 289 community-curated alternatives at european-alternatives.cloud. Fetches live data. Complements deutschland-stack-api (community-curated vs. government-graduated).
- ▌ Verification Before Completion · yesterday-aiRun verification commands and confirm output before claiming work is complete. Evidence before assertions. Thin ytstack wrapper around the vendored superpowers verification-before-completion procedure, injecting the current task's verification command. Use before commit, before PR, before summarize-task, before any 'done' claim.
- ▌ Wrapup · yesterday-ai bundleGeneric end-of-conversation sweep -- works in any project, at any point. Looks at what the current repo actually has (docs, planning files, agent context, changelog, ADRs, memory layers...) and proposes which of them to extend with the learnings, decisions, and follow-ups that surfaced in the conversation. Then prepares a paste-ready resume prompt for after /compact. Use when the user says "wrapup", "wrap up", "wrap things up", "lass uns wrappen", or before /compact.
- ▌ Vrr Efa API · yesterday-ai bundleLive-Fahrplanauskunft für den VRR (Verkehrsverbund Rhein-Ruhr) via EFA API. Abfahrten, Verbindungen, Haltestellen -- Echtzeit, kostenlos, kein API Key. Use when: user asks for train/bus/tram connections, departures, or transit info in NRW/Ruhrgebiet. Also works for DB Regionalverkehr in the region.
- ▌ Audit Skills · yesterday-ai bundleAudit this repo's skills + plugins on three axes -- (1) leaks of personal info or Yesterday-internal references in user-facing artifacts, (2) catalog consistency (folder/name/dep/install-target alignment), (3) plugin-spec compliance (Claude Code + Cursor manifest schemas, layout rules). Reports findings as a triage list; does not auto-fix. Use before publishing, before merging skill PRs, or as a periodic hygiene pass.
- ▌ X Reader · yesterday-ai bundleRead Twitter/X posts, threads, and articles. Handles login walls and JS rendering. Use when a user shares an x.com or twitter.com link.
- ▌ Webflow · yesterday-aiManage Webflow sites via the official Webflow MCP server -- pages, CMS, assets, components, styles, variables, custom code, comments, localization, and publishing. Covers the headless Data API tools and the Designer API tools (which need the Webflow Designer open in the foreground). Use when: reading, auditing, or editing a Webflow site; building or duplicating pages; managing CMS collections or assets; or adding legal/marketing pages. This plugin ships the Webflow MCP server; just authenticate (OAuth).
- ▌ Miro Board · yesterday-ai bundleCreate and read Miro board content via MCP tools. Diagrams (flowcharts, mindmaps, UML, ER), documents (markdown), tables, and context extraction. Use when: user asks to create or read diagrams, documents, or tables on Miro boards, or to extract structured content from existing boards. Requires: Miro MCP server connected (npx miro-mcp).
- ▌ Web Design · yesterday-ai bundleBuild distinctive, production-grade frontend interfaces with high design quality. Use when asked to build websites, landing pages, dashboards, web apps, or any web UI that should look polished and modern. Generates creative, polished code that avoids generic AI aesthetics. Includes Yesterday corporate identity briefing for branded reports and deliverables.
- ▌ Paperclip API · yesterday-ai bundleManage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API. Use when creating companies, hiring agents, assigning tasks, managing budgets, approving hires, or checking dashboards on a Paperclip instance.
- ▌ Web Scraper · yesterday-ai bundleExtract content from any web page. Provides a tiered approach from lightweight fetch to full browser rendering. Use when web_fetch fails or pages require JavaScript.
- ▌ Using Github · yesterday-aiOperating policies for safe GitHub interaction via the `gh` CLI and `git`. Use this skill before any PR edit, comment, branch operation, push, or merge interaction. Covers state-before-action checks, force-push discipline, squash-merge divergence handling, and verification that mutations actually landed.
- ▌ Exa Search API · yesterday-ai bundleSemantic web search via Exa AI API. Returns full-text content, not just snippets. Use for deep research, competitor analysis, or finding specific technical content.
- ▌ Figma Console MCP · yesterday-ai bundleConnect AI agents to Figma via the Figma Console MCP server. Enables design system extraction, UI component creation, variable/token management, visual debugging, FigJam boards, and Slides presentations. Use when an agent needs to read, create, or modify Figma designs programmatically.
- ▌ Excalidraw Diagram · yesterday-ai bundleCreate Excalidraw diagram JSON files that make visual arguments -- workflows, architectures, concepts. Use when the user wants to visualize systems, processes, or ideas as .excalidraw files. Covers design methodology, section-by-section building, render-validate loop, and quality checklist.
- ▌ Voxtral Tts API · yesterday-ai bundleText-to-speech via Mistral Voxtral TTS API. Generate natural, emotionally expressive speech in 9 languages. Supports voice cloning from 3s audio samples, preset voices, streaming, and cross-lingual synthesis. Use when you need to generate speech, narrate content, create voice messages, or build voice agents.
- ▌ Create Shareable Skill · yesterday-ai bundleTurn an existing skill or a fresh idea into a catalog-ready shareable skill -- run the quality gate, decide public-vs-private catalog and standalone-vs-bundle placement, pick the category, scaffold SKILL.md (+ optional .plugin.json), update the catalog docs, and open a PR to main. Use when adding a new skill to this repo, promoting a personal or ad-hoc skill into a shareable one, or routing a skill into the right catalog.
- ▌ Agent Swarm · yesterday-ai bundleOrchestrate specialized coding agents in isolated worktrees for parallel development tasks.
- ▌ Creative Productivity · yesterday-ai bundleGenerate professional consulting deliverables: Excalidraw diagrams, Mermaid visualizations, Reveal.js/Marp presentations, draw.io architecture diagrams, one-pagers, and proposal documents. Use when a user asks for visual artifacts, slides, diagrams, architecture visuals, consulting documents, pitch decks, workshop materials, or any creative deliverable for client-facing or internal use. Covers the full "Consulting as Code" creative pipeline.
- ▌ Slack Best Practices · yesterday-aiA collection of formatting rules, emoji quirks, and communication etiquette for Slack. Use when composing messages for Slack to ensure correct rendering and team-friendly communication.
- ▌
- ▌ Project Engine · yesterday-aiAutonomous project execution engine for AI agents. Orchestrates scheduled cron jobs per project using workflow templates (dev-autonomous, research, ops). Integrates PR-Gate, GitHub workflow, ROADMAP tracking, and human notification via project-tracking. Use when: setting up scheduled project work, running an autonomous session, or designing an agent's development loop. Builds on forward-momentum (philosophy) and implements it as a concrete system.
- ▌
- ▌ Para Memory Files · yesterday-ai bundleFile-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.
- ▌ Github Workflow · yesterday-aiStandardized Git + GitHub workflows for AI agents. Branching, committing, PRs, reviews, CI checks.
- ▌ Capability Check · yesterday-aiDiscover available tools, sub-agents, and skills at session start or when unsure about capabilities.
- ▌ Forward Momentum · yesterday-aiFoundational philosophy for autonomous agent work. Breaks analysis paralysis and enforces tangible output per interaction. Use when: a conversation feels circular, a session risks ending without an artifact, or an agent needs a reminder to act instead of plan. Generic -- applies to any domain or toolchain.
- ▌ Github Pr Review · yesterday-aiQualified, critical code reviews using GitHub's pending review API. Inline comments, verification, and validation.
- ▌ Project Tracking · yesterday-aiStandardisiertes Projekt-Tracking für Yesterday KI-Agenten. Use when: setting up a new agent workspace, responding to a status request from another agent or a human team member, or aggregating fleet-wide project status. Covers: PROJECTS_TRACKING.md structure, YAML frontmatter, responsibility matrix, status definitions, and the Project Status Report format.
- ▌ Pm Patrol Routine · yesterday-aiProject Manager patrol for GitHub repos. Triages new issues, reviews PRs for completeness (not code quality), verifies fixes match issue requirements, closes resolved issues, and coordinates between engineer and reviewer. Integrates with issue-patrol-routine (Scotty) and review-patrol-routine (Rémy).
- ▌ Butler Deploy · yesterday-aiPublish or update an HTML5 game on itch.io via the butler CLI. Covers install, login, channel push with versioning, and first-time page setup. Use when deploying a web game build (e.g. dist/) to an itch.io channel.
- ▌ Railway Deploy · yesterday-ai bundleDeploy, manage, and debug services on Railway via the Railway CLI. Covers authentication, project + service creation, env variables, private networking, logs, and config-as-code. Use whenever creating, deploying, or troubleshooting Railway services. See references/ for the full CLI command reference and a Next.js+Prisma deploy recipe.
- ▌ Agentic News Digest · yesterday-aiEnd-to-end skill for curated team news digests. Covers the full pipeline: team inbox (manual submissions & co-authored drafts), source aggregation (RSS, Twitter, GitHub, web search), research & fact-checking, relevance scoring, article formatting (5 templates), and scheduled delivery to Slack/Discord/WhatsApp. Handles the critical handoff between conversational sessions (where links are received) and isolated cron sessions (where digests are built).
- ▌ Issue Patrol Routine · yesterday-ai bundlePeriodic scan of GitHub repos for open issues. Classifies issues into actionable queues (new, needs-clarification, ready-to-implement, in-progress, blocked) and persists state across heartbeat cycles. Use when an engineering agent needs to autonomously discover and triage work.
- ▌ Issue To Pr Workflow · yesterday-ai bundleEnd-to-end workflow for turning a GitHub issue into a merged PR. Covers issue analysis, branch creation, implementation, PR with reviewer assignment, and handling review feedback loops. Use when an engineering agent picks up an issue from a patrol queue and needs to implement it.
- ▌ Systemic Persistence · yesterday-aiZwingt den Agenten dazu, aus gelösten Problemen nachhaltig zu lernen. Stellt sicher, dass Fixes Reboots überleben, dokumentiert sind und nicht zu neuen Problemen (wie vollen Festplatten) führen.
- ▌ Review Patrol Routine · yesterday-ai bundleDeterministic, stateful PR review patrol for GitHub repos. Use when an agent must review pull requests periodically instead of opportunistically, keep persistent patrol state across resets, classify new-review vs re-review queues, and drive heartbeat-based review cycles with explicit repo scope.