All authors
Claude Skills by OutlineDriven
github.com/OutlineDriven865 skills3 installs846 views
- Ui DesignUse when directing, building, or auditing React/Next.js Tailwind UI: visual direction, responsive/dark-mode retrofits, UX audits. Not for typography or motion: use typography-audit or ui-animation.Votes: 0GitHub stars: 52
- Universal Invariant BaselineUse when invoked to apply an invariant-first, fail-fast, special-case-eliminating baseline. Not for domain models in types: use type-driven. Not for design-by-contract: use contract-driven.Votes: 0GitHub stars: 52
- UnlazyUse when task decomposition needs gate-file proof before a done claim, or when the user says "unlazy", "depth tree", "gates", or "do not stop until it is done". Detects half-done work, premature done claims, stubs, and silently narrowed scope. In orchestrated mode (tree 4+), enforces dispatch-state, human approval binding, and parent reverification before a done claim.Votes: 0GitHub stars: 52
- Unleak AbstractionUse when an abstraction leak must be sealed as a module seam, configuration option, or explicit override, or exposed as a named boundary. Not for detecting concealment patterns: use no-hide.Votes: 0GitHub stars: 52
- UnslopUse when prose is drafted or edited, reviewed for AI tells, or the user asks to remove AI patterns, humanize, or add voice. Offers dedash and detool modes. Not for code debris: use deslop.Votes: 0GitHub stars: 52
- Validate Changes Match SpecsUse when asked to compare implementation against repository specs, report mismatches, resolve by user decision, or check PR-review commitments. Not for general fact-checking: use verify-both-ways.Votes: 0GitHub stars: 52
- Validation First DrivenUse when protocols, workflows, concurrency, or lifecycle state need states, transitions, and temporal properties. Not for domain models: use type-driven. Not for contracts: use contract-driven.Votes: 0GitHub stars: 52
- Validation Self AuditUse when asked to audit validation that looks too clean or self-confirming. Identify each independence failure that applies, prescribe its fix, and audit the auditor''s own evidence. Not for checking eval leakage — use evaluation-leakage-audit.Votes: 0GitHub stars: 52
- Variant HuntUse when a confirmed root cause must be searched across a codebase or turned into a search rule. Returns triaged variants, false positives, and a CI-ready regression rule. Not for graph-neighborhood seeding — use variant-neighborhood-seeding.Votes: 0GitHub stars: 52
- Variant Neighborhood SeedingUse when a confirmed or plausible issue maps to a graph node and the user needs a ranked handoff packet of graph-neighborhood review targets to seed variant analysis. Produces a local markdown file with ranked candidates, exclusion rationale, and search guidance. Not for searching codebase manifestations of a root cause — use variant-hunt.Votes: 0GitHub stars: 52
- Vector ForgeUse when crypto implementations and a vector harness need mutation-driven cross-implementation test vector expansion. Not for Wycheproof: use wycheproof. Not for fuzzing: use fuzz-harness-writing.Votes: 0GitHub stars: 52
- Verification Before CompletionUse when a task, feature, or fix is called done, complete, finished, or fixed, or before a commit, PR, or next task. Not for fact-checking: use verify-both-ways. Not for measuring: use verify-this.Votes: 0GitHub stars: 52
- Verification SkillUse when asked to create a project-local executable verification skill, or repair one whose commands, paths, or assertions drifted. Not for remote or deployed verification.Votes: 0GitHub stars: 52
- Verify Both WaysUse when a claim needs checking both ways, "fact-check this", or an artifact or HTML document needs claims verified and corrected in place. Modes: claim, artifact. Not for measuring: use verify-this.Votes: 0GitHub stars: 52
- Verify ThisUse when a measurable claim needs before/after proof. Not for fact-checking or done-claim gating: use verify-both-ways or verification-before-completion.Votes: 0GitHub stars: 52
- Viral Opportunity ScoutUse when asked to find distribution opportunities for a template, tool, or artifact. Not for content creation or campaign management.Votes: 0GitHub stars: 52
- Visual Argument DiagramUse when a user wants a conceptual, workflow, or architecture diagram, a layout repair, or a PNG render of an existing .excalidraw file. Not for HTML or chat visuals: use visual-diagram or show-me.Votes: 0GitHub stars: 52
- Visual Brainstorm CompanionUse when a brainstorming question is genuinely clearer shown than told: a real mockup, layout, or diagram. Starts a local key-gated HTTP/WebSocket server, pushes HTML fragments to the browser, and merges click selections back into the terminal reply. Not for text-only idea exploration; use brainstorm or ideate.Votes: 0GitHub stars: 52
- Visual DiagramUse when asked to diagram, or a tool or --quick flag renders a structured spec to HTML. Modes: interactive, quick-render. Interactive families: flowchart, structural, illustrative, architecture (components, boundaries, or two-snapshot delta compare), dataflow (data movement, ETL or ELT, lineage, custody), lifecycle (states, waits, retries, transitions, terminals), sequence (time-ordered interaction between participants), workflow (process, approval flow, runbook, CI/CD path, responsibility la...Votes: 0GitHub stars: 52
- Visual Diff ReviewUse when asked to review a diff and produce a 7-section visual page. Not for interactive review walks or PR-specific review: use show-review.Votes: 0GitHub stars: 52
- Visual Fact CheckUse when invoked as visual-fact-check with a document path. Verifies every factual claim against its cited sources, corrects errors in place, and appends a verification summary. Not for both-ways fact-checking of assertions — use verify-both-ways.Votes: 0GitHub stars: 52
- Visual PlanUse 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.Votes: 0GitHub stars: 52
- Visual Project RecapUse when a developer returns to a project or loses context. Produces an 8-section HTML recap page so they can rebuild the mental model and derive next steps only from evidence. Not for session handoff snapshots; use handoff.Votes: 0GitHub stars: 52
- Visual Render ToolUse 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.Votes: 0GitHub stars: 52
- Visual SlidesUse 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.Votes: 0GitHub stars: 52
- Visualise ChartUse 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.Votes: 0GitHub stars: 52
- Visualise ExplainerUse 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.Votes: 0GitHub stars: 52
- Visualise WidgetUse 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.Votes: 0GitHub stars: 52
- Vulnerability Triage BrocardsUse when a vulnerability report, CVE, bug-bounty submission, or automated finding needs triage before deep verification. Don''t use for tasks that require source or remote-system changes.Votes: 0GitHub stars: 52
- Wait WhatUse when the user says "wait, what", "the explanation is unclear", "say that again", or asks to restate the last response in plain language. Not for tasks that require source or remote-system changes.Votes: 0GitHub stars: 52
- Walk With MeUse when the user wants to be walked through code, not handed a report: "walk through this", "guided code walk", or "explain this codebase". Not for tasks that require source or remote-system changes.Votes: 0GitHub stars: 52
- Watch And Repair PrUse when a human explicitly invokes a watcher cycle for an open pull request that must be watched until mergeable or blocked. Not for merge, force-push, or work outside the invoked cycle.Votes: 0GitHub stars: 52
- Watch For Harness ModeUse when a proven watch pattern should become a reusable harness artifact with configurable inputs. Not for remote, credential, publish, deploy, or irreversible changes.Votes: 0GitHub stars: 52
- Watch For StructuredUse when the user wants to classify a surface state and page an on-call API when triggered. Not for read-only anomaly watching without paging: use watch-for.Votes: 0GitHub stars: 52
- Watch ForUse when monitoring a file, log, endpoint, or artifact for drift or errors, or polling a target until a predicate holds. Modes: watch (default), until. Not for source or remote-system changes.Votes: 0GitHub stars: 52
- Watch UntilUse when asked to poll a named changing job, log, or artifact until a supplied completion predicate holds. Returns a terminal verdict: predicate-holds, non-converged, or blocked. Not for source or remote-system changes. Not for continuous anomaly monitoring: use watch-for.Votes: 0GitHub stars: 52
- Waterfall GuideUse 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.Votes: 0GitHub stars: 52
- WayfinderUse when a greenfield project or large feature build will not fit in a single agent session. Don''t use for implementation, remote credential changes, or work that fits in one session.Votes: 0GitHub stars: 52
- Web Accessibility AuditUse when the user requests an accessibility audit, a11y check, or WCAG compliance review. Don''t use for tasks that require source or remote-system changes.Votes: 0GitHub stars: 52
- Web Design ReviewUse when the user runs /web-design-review with a URL to visually audit and fix a live UI. Not for design direction: use design. Not for variant galleries: use design-variants.Votes: 0GitHub stars: 52
- Web Performance AuditUse when asked to audit, profile, or debug page load performance, Lighthouse scores, or site speed. Don''t use for tasks that require source or remote-system changes.Votes: 0GitHub stars: 52
- Webapp TestingUse when asked to verify frontend or UI behavior, or capture browser screenshots and console logs. Not for read-only inspection: use browser-testing. Not for remote or deploy changes.Votes: 0GitHub stars: 52
- Weekly ReviewUse when asked to summarize authored work over the last week or a named date range, commit range, or branch. Not for source or remote-system changes.Votes: 0GitHub stars: 52
- Weekly SynthesisUse when the user asks for a weekly synthesis, a weekly report, or a "what you need to know this week" digest from team reports. Not for the underlying reports or ad-hoc summaries.Votes: 0GitHub stars: 52
- What Did I Get DoneUse when a user asks what was completed in a named date or commit range. Reads git log and returns a concise dated status report. Don''t use for tasks that require source or remote-system changes.Votes: 0GitHub stars: 52
- WhyUse when asked why something works this way, for design rationale, a postmortem, a data-backed threshold, or a source-tiered evidence report. Not for current runtime behavior: use how.Votes: 0GitHub stars: 52
- WontfixUse when the user wants to elicit refused directions, generalize them, and close matching tracker items as not planned. Not for duplicates, spam, or items closed as completed or obsolete.Votes: 0GitHub stars: 52
- WorkUse when implementing from a plan, spec, clear build request, or settled ticket, orchestrated or standalone. Don''t use for open-ended debugging (figure-it-out), exploration, or read-only research.Votes: 0GitHub stars: 52
- Workflow DiagramUse 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.Votes: 0GitHub stars: 52
- Workflow Evidence MiningUse when authorized workflow history may contain a repeated process worth extracting and replay-testing. Produces a contradiction-tested workflow mined from authorized history.Votes: 0GitHub stars: 52