impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…
explorateur de dépôts
az9713 · Dépôts et skills représentatifs - Page 2
Vue par dépôt de 405 skills collectés dans 106 dépôts GitHub.
hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade,…hyperframes-coreThe HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and…hyperframes-creativeNon-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns…hyperframesMandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any…media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music…skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…subagentsinvoke this skill when the user asks you to use subagentsweb-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
dependency-risk-plannerPre-flight dependency risk assessment for the planning phase. Use BEFORE writing code when choosing libraries, designing architecture, or setting up a new project. Prevents dependency hell, version conflicts, and abandoned-library traps. Especially critical…pic-auditView detailed audit log for workflow - shows agent executions, tool usage, and decision trailpic-conflictEscalate a conflict between PICs to the user for resolutionpic-decideRecord a formal decision document with rationale and alternativespic-handoffExecute a phase transition from current PIC to next PICpic-integrationRun an integration study to test components togetherpic-startInitialize a new PIC (Pilot in Command) workflow with a problem statementpic-statusDisplay current PIC workflow status and progress
awareness-analyzerDiagnose audience awareness level and market sophistication using Eugene Schwartz's Breakthrough Advertising frameworkcompetitor-analyzerAnalyze competitor positioning using browser automation (Claude in Chrome + Chrome MCP)content-generatorGenerate marketing content applying all 5 frameworks - for GitHub READMEs, landing pages, social media, and morecopy-optimizerApply tactical persuasion techniques from "Yes! 50 Scientifically Proven Ways to Be Persuasive"nesb-scorerScore headlines and copy against the NEW-EASY-SAFE-BIG framework from "Take Their Money" by Kyle Milliganpersuasion-auditorAudit marketing content against Cialdini's 7 persuasion levers from the book "Influence"tribe-builderGenerate tribe-building copy using Blair Warren's One Sentence Persuasion frameworkvoice-extractorAnalyze existing content to extract voice patterns for consistent brand messaging
content-extractionExtracts and organizes content ideas from long-form content into detailed platform-specific tables. Use when repurposing transcripts, articles, blog posts, or any long-form content into multiple pieces across platforms.key-takeawaysSummarizes key takeaways from long-form content into structured bullet lists and actionable insights. Use when creating show notes, content summaries, SEO descriptions, or quick reference guides.linkedin-postGenerates engaging LinkedIn posts from long-form content. Use when creating LinkedIn content, building thought leadership, or repurposing content for professional audiences.quote-extractorExtracts the most quotable, shareable statements from content and formats them for social media use. Use when finding pull quotes, social proof, or highlight-worthy statements.substack-noteGenerates Substack Notes from long-form content. Use when creating short-form content for Substack's social feed, building newsletter audience, or sharing quick insights.title-generatorGenerates compelling, click-worthy titles from content across multiple styles and platforms. Use when naming blog posts, videos, newsletters, social posts, or any content that needs a great headline.twitter-threadGenerates engaging Twitter/X threads from long-form content. Use when creating Twitter content, building audience, or breaking down complex topics into tweet-sized insights.
ems-clusterUse when reviewing accumulated signals to group repeated pains, identify which are noise versus interview candidates, and decide what to kill or promote to thesis. Use after 10 or more ledger entries exist.ems-conciergeUse when a signal has been validated through interviews showing urgency, to draft a specific priced manual offer that tests willingness to pay before building any software.ems-decideUse when reviewing all open signals to assign a definitive next action to each one, or when signals are accumulating without clear decisions. Use after a scan session or scoring batch.ems-interviewUse when a signal scores 9 or higher and needs interview outreach messages and a concrete plan for talking to users about their actual behavior, not their opinions about potential products.ems-scanUse when scanning communities for early market signals around a behavioral frontier, looking for pain, workarounds, and demand before a market category exists. Use when the user names a behavioral frontier and wants evidence gathered from web sources.ems-scoreUse when scoring a signal from weirdness_ledger.md or source_map.csv using the 0-16 demand quality rubric, or when the user asks how strong a signal is.ems-thesisUse when a signal cluster has appeared across 3 or more independent sources and is ready to be converted into a structured startup thesis file. Use after ems-cluster recommends promotion.
alignAsk targeted clarifying questions before executing a task so the agent and user align on scope, constraints, success criteria, and output format.burstGenerate multiple high-quality variations of an answer, plan, design, prompt, implementation, or artifact so the user can select the best branch and iterate.calibrateImprove future Claude Code behavior by extracting corrections, preferences, failures, and reusable workflow rules from the current session. Use at the end of a work session or when the user asks to calibrate, self-improve, update memory, or capture lessons.coordinateCreate or update a shared project workspace so multiple Claude Code sessions can work on the same project using shared context, session logs, decisions, and artifacts.devilPlay devil's advocate against a proposed plan, option, architecture, vendor, library, or argument. Use to counter sycophancy and surface risks before committing.onboardLoad an existing shared project into the current Claude Code session by finding its project folder and reading context, session logs, decisions, and open questions.tweakAdd an interactive HTML tuning panel to a visual artifact so the user can adjust design parameters with sliders and then bake the selected values back into the final design.
learn-anythingLearn any topic 10x faster using the Specificity Method — a 5-step loop that turns "I don't know what I don't know" into a verified, tested mental model. Use when the user is confused, stuck, says "I don't get X", "I don't know what I don't know about X",…learn-apply-testStep 5 of the Specificity Method. Prove a mental model with a real test — Predict, Run, Compare, Fork. Use after the user can explain a concept in their own words, when learning needs proof in practice, or as the final step of learn-anything. A mismatch is a…learn-articulateStep 1 of the Specificity Method. Turn a vague feeling ("I don't get AI agents", "this confuses me", "I can't even phrase my question") into one specific, actionable "I don't know X". Use when the user's question is too fuzzy to act on, when they ask to "get…learn-decomposeStep 2 of the Specificity Method. Break a specific "I don't know X" into its smallest moving parts, mark each piece known or unknown, and surface hidden unknowns. Use after the gap is articulated, when a topic is still a black box, or as step 2 of…learn-reconstructStep 4 of the Specificity Method. Have the user explain the concept back in their own words, then judge fake vs real understanding. Use after research is verified, when checking whether someone actually understands something or is just reciting jargon, or as…learn-verifyStep 3 of the Specificity Method. Verify AI answers with six accuracy checks — citations, citation verification, triangulation, date-check, uncertainty probing, and what's-missing — before trusting them. Use after decomposing a topic, when an answer sounds…
vault-captureSave web content to the Obsidian vault. Given a URL, extracts clean content via defuddle, creates a formatted note with frontmatter and wikilinks to related vault content, and files it in a new project folder. Use when the user shares a URL to save to their…vault-healthAudit vault health: unresolved links, orphan notes, dead-end files, missing frontmatter, structural gaps. Produces an actionable report note with prioritized fix suggestions. Use when wanting to clean up, organize, or assess the current state of the vault.vault-journalLog a research entry to today's Obsidian daily note, automatically finding and wikilinking related vault projects. Use when the user wants to capture something they learned, worked on, or found interesting about Claude Code or AI tooling.vault-mocGenerate a Map of Content (MOC) note that categorizes and wikilinks vault project folders by theme. Can create a full vault index or a focused MOC for a specific category (e.g., "skills", "agents", "browser automation"). Use when wanting to create a…vault-saveCapture insights, solutions, or learnings from the current Claude Code conversation into a formatted Obsidian note with wikilinks. Use when the user wants to save something discovered during a conversation — a technique, a solution, a workflow decision, or a…vault-synthesizeDeep-search the vault on a topic, read the most relevant project files, and produce a synthesis note that consolidates knowledge with wikilinks. Use when wanting to understand what this vault knows about a topic, or to create a reference note from scattered…
code-reviewerThorough code review with security analysis and best practicesdata-analystData exploration, analysis, and visualizationdevops-agentInfrastructure, deployment, and operations automationresearch-agentDeep web research with citations and cross-referencingscheduler-agentCalendar and reminder management with smart schedulingwriter-agentLong-form content creation with research and editing
parallel-sandboxUse to run the parallel-worktree demo loop — multiple makers fix different modules concurrently, each in its own git worktree, then an integrator merges and runs the full suite. Triggers on "parallel loop test", "run the parallel sandbox", "worktree loop…demo-loopUse to run a zero-dependency sandbox loop that proves the loop machinery works end to end. Triggers on "run the demo loop", "test the loop", "quick loop test", "demo loop", "make the sandbox tests pass". Fixes intentionally-broken code until `python -m…draft-postmortemUse after an incident/outage to draft a blameless postmortem with a verified root-cause hypothesis. Triggers on "draft a postmortem", "incident writeup", "root cause analysis", "RCA", "what caused the outage". Investigates read-only, red-teams the cause, and…reconcile-docsUse when documentation is stale or drifting from the code — to reconcile docs with the current source. Triggers on "reconcile docs", "docs are stale", "update docs to match code", "doc drift", "fix outdated documentation". Rewrites affected pages and verifies…triage-flakyUse when a test is intermittently failing or you need to triage/quarantine flaky tests. Triggers on "flaky test", "triage flaky", "quarantine flaky test", "test fails intermittently". Reproduces with a 50x rerun harness, classifies flaky vs real regression,…upgrade-depsUse when upgrading dependencies, bumping packages, or patching security vulnerabilities. Triggers on "upgrade dependencies", "bump deps", "security upgrade", "patch vulnerabilities", "update packages". Runs an autonomous maker/checker upgrade loop that opens…
cold-start-interviewCold-start interview — builds your watchlist, indexes the policy library, and learns your materiality threshold so the monitor surfaces signal instead of noise. Use on fresh install, when reconfiguring (--redo), or when re-checking what connectors are…customizeGuided customization of your regulatory practice profile — change one thing without re-running the whole cold-start interview. Adjust watched regulators, policy library index, materiality threshold, gap response process, feed configuration, or matter…cold-start-interviewRun the cold-start interview to learn your commercial contracts practice and write your team practice profile. Use on first use of the plugin, when `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` is missing or still contains template…customizeGuided customization of your commercial contracts practice profile — change one thing without re-running the whole cold-start interview. Adjust risk posture, escalation contacts, playbook positions, NDA triage preferences, house style, review preferences, or…customizeGuided customization of your privacy practice profile — change one thing without re-running the whole cold-start interview. Adjust risk posture, escalation contacts, DPA playbook, privacy policy commitments, PIA house style, DSAR process, or matter workspace…customizeGuided customization of your product counsel practice profile — change one thing without re-running the whole cold-start interview. Adjust risk calibration, escalation contacts, launch review framework, marketing claims posture, or matter workspace paths. Use…