All authors
OutlineDriven avatar

Claude Skills by OutlineDriven

github.com/OutlineDriven
625 skillsA× 614B× 6C× 3D× 1F× 10 installs34 views
Single File Html DeckA

Use when an explicit request asks to create a Sentry presentation, build slides, or make a deck. Scaffolds one self-contained, keyboard-navigable HTML file with real-data charts and Sentry branding. For general HTML artifacts use html; for PowerPoint use pptx.

ai-agentsjavascriptgo
0
35
Snippet Image RenderingA

Use when the user explicitly names snipgrapher and wants code rendered to a polished PNG, SVG, or WebP at an explicit local path. Probes the installed CLI for supported flags and writes only the named image file. Not for other renderers, publishing, or remote actions.

ai-agents
0
35
Tasty AbstractionA

Use when a user wants to design an abstraction boundary that collapses a complex implementation into a simpler interface without leaking internal state. Produces a specification with the boundary, leak surface, escape hatches, and usage constraints. Stops before implementation.

ai-agents
0
35
Training ReportA

Use when a trainer wants a training session documented as a compte rendu. Runs a structured interview, iterates a Markdown draft under user lead, then generates a .docx once after explicit content confirmation via python-docx. Not for remote, credential, publish, deploy, or irreversible changes.

ai-agentspythongo
0
35
Visual SlidesA

Use when the user explicitly requests a slide deck by command, flag, or natural language. Generates a self-contained HTML deck in the diagrams directory with embedded CSS, JavaScript, keyboard navigation, and a progress indicator. Not for PowerPoint files; use pptx.

ai-agentsjavascriptjava
0
35
Visualise ExplainerA

Use when asked to create an interactive HTML concept explainer with controls and live state, returned in a visualizer fence for sandboxed rendering. Validates controls via a local DOM trace, not a mental trace. Not for tasks that require source or remote-system changes.

ai-agentsjavascriptgo
0
35
Waterfall GuideA

Use when a user wants to lock greenfield architecture and interfaces early for coherent parallel execution. Produces a locked architecture document with module inventory, interface contracts, cross-cutting ownership, and open questions, distributed to execution teams as the coordination contract.

ai-agentsgo
0
35
Architecture DiagramA

Use when the user asks to visualize an architecture as a self-contained HTML artifact with a hash-bound receipt. Also handles delta mode: comparing two snapshots, rendering what changed when both are supplied. Not for remote, credential, publish, deploy, or irreversible changes.

ai-agentsjavascriptrust
0
35
Buzzword HijackA

Use when a user wants to choose and execute a bounded positioning move that rides a jargon wave without confusing trend with truth. Produces a written positioning artifact at a named output path. Not for describing the jargon landscape.

ai-agentsgo
0
35
Changelog UpdatesA

Use when a release or a since-tag window needs user-facing release communication drafted. Composes a draft release note covering exactly that window and advances the file-based since-tag marker once without publishing.

ai-agentsgogit
0
35
Clean And TrueA

Use when the automatic trigger applies: after editing a durable artifact, or when the user says "clean and true", "run the hygiene pass", or "taste the output". Routes the just-changed artifact through the hygiene passes the change earned and skips the rest.

ai-agents
0
35
Compile 3d WorkflowA

Use when the user asks for direction and a compilable 3D workflow from an interview. Produces a validated local artifact file combining a DAG topology, ontology groups, and closed control loops. No remote, credential, publish, deploy, or irreversible mutation.

ai-agentsnode
0
35
ConvergeA

Use when the user wants to collapse an open decision field to one decision and record its rationale locally. Not for multi-lens pressure testing. No remote or irreversible changes.

ai-agentstesting
0
35
Dataflow DiagramA

Use when asked to visualize data movement, ETL or ELT, lineage, transformations, custody, governance, stores, sources, or consumers. Produces a typed dataflow JSON spec and one self-contained interactive HTML artifact with a hash-bound receipt and truthful visual-review status.

ai-agentsgonode
0
35
Debloat Respect RichnessA

Use when a user asks to tighten verbose-but-correct prose without a full rewrite. Cuts words in place to load-bearing density, preserving every load-bearing claim, respecting intended richness, and handing genuine duplication or drift off rather than force-compressing it.

ai-agents
0
35
Define GoalstateA

Use when the user wants the finished-system contract for a piece of work. Authors an approved success-predicate document naming behavior, protocols, allowed states, forbidden states, and impossible states, with a concrete state-space proof and terminal failure behavior.

ai-agentsgogit
0
35
DivergeA

Use when the user wants to expand a decision field with additional options and dimensions. Not for selecting or applying an option — use decide. No source or remote-system changes.

ai-agents
0
35
Doc CoauthoringA

Use when drafting a doc, proposal, spec, RFC, design doc, decision doc, or PRD in chat. Produces a structured document that passes fresh-reader testing and meets its impact goal. Not for reviewing an existing plan — use doc-review. No source or remote-system changes.

ai-agentsgotesting
0
35
Docs UpdateA

Use when documentation has drifted from code changes and the user asks to synchronize them, selecting a local commit or reviewable PR. Filters user-facing commits, maps coverage gaps across Diataxis categories, protects CHANGELOG, and delivers scoped commits or PRs. Not for ADRs or architectural rationale — use docs-and-adrs; not for writing an isolated document from a settled brief — use docs-writing.

ai-agentsgogit
0
35
Docs WritingA

Use when asked to write, restructure, or audit documentation using Diataxis types and a rule-based audit, to draft a first-pass feature docs page grounded in a specification and codebase, or to draft documentation or diagram source for a named subject and audience. Present the draft for review before writing. Not for ADRs or architectural rationale. No remote or irreversible changes.

ai-agentsgoexpress
0
35
Embed DiagramA

Use when the user runs /embed-diagram to render a Mermaid diagram offline and embed the SVG or PNG into a target document. Uses a local CLI renderer, not a remote page. Not for code-derived diagrams. No remote, credential, publish, deploy, or irreversible changes.

ai-agentsnodegit
0
35
Good ReadmeA

Use when the user asks to create, rewrite, review, or polish an open-source README into a progressively disclosed, evidence-grounded guide whose claims are sourced and whose headings alone tell the story. Also produces shop-window READMEs with section templates, badges, and a quality checklist, and enforces a house standard with pre-ship verification gates. Not for remote, credential, publish, deploy, or irreversible changes.

ai-agentsgoswift
0
35
IdeateA

Use when a human asks to brainstorm, asks what to build, requests ideas for a divergent subject, or invokes /ideate. Produces a grounded ideation artifact committed locally with adjudicated survivors and a reason for every rejection.

ai-agents
0
35
Lifecycle DiagramA

Use when states, waits, retries, decisions, transitions, and terminals need a lifecycle view. Produces a fail-closed lifecycle JSON spec and self-contained interactive HTML topology. Don''t use for remote, credential, publish, deploy, or irreversible changes.

ai-agentsgonode
0
35
Markdown To PdfA

Use when the user runs /markdown-to-pdf on Markdown to render a publication-quality PDF with emoji, diagram, landscape, and combined gates green. Not for remote, credential, publish, deploy, or irreversible changes.

ai-agentsgo
0
35
Pr WalkthroughA

Use when a user asks for a zoomable PR map or graph-canvas orientation. Produces a fully self-contained static HTML site with four D3 views and guided tours, bundling all assets locally. Not for remote, credential, publish, deploy, or irreversible changes.

ai-agentsjavascriptjava
0
35
Prototype LogicA

Use when someone needs to press buttons and watch state change to check a state-model, logic, or data-shape question. Produces a throwaway HTML demo whose isolated logic answers the question and folds into real code after validation. Not for visual design — use prototype.

developmentjavascriptgo
0
35
PrototypeA

Use when asked to prototype one design question through a cheap logic or UI experiment. Builds a throwaway artifact, records the one-line verdict, and folds the decision into real work without polluting main. Not for interactive state-model demos — use prototype-logic.

developmentpythongo
0
35
Purge Slop DocsA

Use when a human asks to purge stale docs, clean Markdown, or reorder the documentation hierarchy. Inspects a bounded Markdown tree, cuts four evidence-backed defect classes, and repairs hierarchy with per-deletion approval. Not for code debris — use deslop.

ai-agentsgoapi
0
35
Render Excalidraw DiagramA

Use when a user supplies an existing .excalidraw file and asks for PNG rendering. Validates the JSON, renders via headless Chromium using the Excalidraw library fetched from esm.sh, and writes a PNG beside the source or to a specified output path. Not for creating or editing Excalidraw diagrams.

ai-agents
0
35
Reorder Respect DeliberateA

Use when a user asks to fix a listing whose order has gone arbitrary while preserving intentionally ranked items. Reorders by a named principle without adding, removing, or rewording any item. Not for freely reorderable listings — use reorder.

ai-agentsgo
0
35
ReorderA

Use when asked to reorder a drifted listing under one stated principle, moving items only and rewording nothing. Handles catalogs, indexes, tables of contents, enums, and menus. Not for listings with intentionally ranked items — use reorder-respect-deliberate.

ai-agents
0
35
Rewrite Clean V0A

Use when a document or file has been edited piecemeal and reads as sediment. Rewrites the artifact as a clean v0 so stale deltas, duplicated passages, and changelog scars do not survive. Not for re-deriving a code subsystem contract — use breaking-driven.

ai-agents
0
35
Rewrite Denoise V0A

Use when a user asks to clean up, sync, dedupe, de-noise, or rewrite an iterated artifact. Rewrites it as a clean v0 with no patch traces, changelog scars, or source noise. Not for a sediment rewrite of prose — use rewrite-clean-v0.

ai-agents
0
35
Save MdA

Use when asked to save a named source as a .md file with frontmatter. Captures a URL, file, or pasted text as one Markdown artifact with provenance and without summarization. Don''t use for remote, credential, publish, deploy, or irreversible changes.

ai-agents
0
35
Sequence DiagramA

Use when a user asks to visualize a time-ordered interaction. Authors a typed sequence JSON spec and a self-contained interactive HTML artifact named by the user. Not for static architecture diagrams.

ai-agentsapi
0
35
Show MeA

Use when the user says show this or diagram this about the current topic. Emits one ephemeral chat visual and nothing on disk. Not for an auditable decision log: use show-me-your-work.

ai-agents
0
35
Show WayA

Use when the user asks for a flattened view of roadmaps and next actions. Returns a dependency-ordered task list with status glyphs and a next-actions frontier as chat output, without taking execution authority. Not for multi-session route planning — use wayfinder.

ai-agentsgit
0
35
SolidateA

Use when a user invokes this skill to harden a chosen but tentative artifact into one durable result. Resolves assumptions, names invariants, removes temporary choices, and verifies the stable end state. Not for remote, credential, publish, deploy, or irreversible changes.

ai-agents
0
35
State Machine WorkflowA

Use when work has distinct modes and the user wants states, events, guards, outcomes, and illegal transitions instead of a prose todo list. Produces a codable state-machine specification. Don''t use for remote, credential, publish, deploy, or irreversible changes.

ai-agentsgo
0
35
Sync DocsA

Use when a behavioral diff may have left docs or CHANGELOG stale. Detects docs-vs-code drift and applies only safe fixes. Also handles stale code comments when tidy targets them. Not for roadmap drift — use drift-detect. Don''t use for remote or irreversible changes.

ai-agentsgobash
0
35
Technical WritingA

Use when technical prose needs writing or reviewing with real symbols and controlled English, including draft editing when generation is unnecessary. Also handles draft editing when generation is unnecessary. Not for general prose deliverables — use writer; not for remote or irreversible changes.

ai-agentsgoexpress
0
35
Visual Argument DiagramA

Use when a user wants to create a conceptual, workflow, architecture, or protocol diagram, or repair an existing diagram''s visual layout. Produces a .excalidraw.json and rendered PNG passing quality checks. Not for HTML diagrams or chat visuals — use visual-diagram or show-me.

ai-agentsangularnode
0
35
Visual DiagramA

Use when the user asks to diagram, draw, map out, walk through, or visually explain a topic, system, process, or architecture. Produces a durable self-contained HTML file opened in the browser, or an ephemeral inline SVG fragment in a visualizer fence. Not for Excalidraw diagrams or document-embedded diagrams; use visual-argument-diagram or embed-diagram.

ai-agentsjavascriptgo
0
35
Visual PlanA

Use when the user wants an implementation plan built and visualized for a goal. Researches the repository and writes a self-contained HTML plan page ending in an observable acceptance checklist. Not for prose plan documents; use plan.

ai-agentsgoapi
0
35
Visual Render ToolA

Use when a model-invoked tool renders visual explanations of plans, architectures, diffs, or implementations into self-contained HTML files under the output jail; opens the browser or Glimpse viewer on demand. Also use when --quick is passed on diagram, diff-review, plan-review, or project-recap outcomes to render a validated spec to HTML. Don''t use for remote, credential, publish, deploy, or irreversible changes.

ai-agentsgo
0
35
Visualise ChartA

Use when the user asks to visualise data as a chart. Returns a self-contained HTML chart fragment using inline SVG or Canvas in a visualizer fence. Don''t use for tasks that require source or remote-system changes.

ai-agentsrust
0
35
Visualise WidgetA

Use when a user requests a comparison table, data record, metric card, stepper, or mockup widget. Returns a self-contained HTML fragment in a visualizer fence for sandboxed iframe rendering. Don''t use for tasks that require source or remote-system changes.

ai-agents
0
35
Workflow DiagramA

Use when a user asks to visualize a process, approval flow, runbook, CI/CD path, responsibility lanes, or tool calls. Produces a schema-validated spec and one self-contained interactive HTML artifact with a hash-bound receipt. Don''t use for remote, credential, publish, deploy, or irreversible changes.

ai-agentsnodeci/cd
0
35
Write PrdA

Use when a user asks to write a PRD or draft feature requirements. Produces a structured PRD with evidence-driven citations and opens a PR. Not for product specs with behavioral invariants; use write-product-spec. Not for tech specs; use write-tech-spec.

ai-agentsgogit
0
35