RADAR DE SKILLS · GITHUB
Agent Skills úteis, classificados pelo uso real.
Compare Skills verificados por finalidade, conteúdo do pacote, instalações e evidências da fonte antes de adicioná-los.
- ESCOPO DO CATÁLOGO
- VERIFICADO
- Skills
- 10.772
- repositórios
- 1711
- última sincronização
- 23 de set. de 2026
social-media-skillshashtag-strategy
- Use to build a hashtag and discoverability strategy for social posts — the modern (2026) approach, not the outdated "30 hashtags to go viral" playbook. Run when the user says "hashtags," "what hashtags should I use," "how many hashtags," "hashtag strategy," "help me get discovered/reach," asks "do hashtags still work / are hashtags dead," or asks how to tag a post. Reads brand-profile and audience first. Sets the keyword/social-SEO layer first (caption, on-screen text, spoken audio) because that — plus engagement and the content itself — drives discovery far more than hashtags now; then picks a tight, relevant, per-platform hashtag set (respecting caps like Instagram's enforced 5-tag limit), favors niche/mid-tier tags over generic mega-tags, and designs branded/campaign hashtags for community and tracking. Rotates sets rather than copy-pasting one block, and hands placement/publishing to scheduling-and-queue. Sets honest expectations: hashtags categorize and aid search; they are not a reach hack.
- instalações
- 1
- GitHub Stars
- 78
- Atualizado
- 3 de set.
social-media-skillsinfographic-and-data-viz
- The craft of turning real data into honest, scannable, shareable infographics and charts. Use when someone wants to visualize data, make an infographic, build a chart/graph, turn a finding or stat into a visual, or fix a chart that's confusing or misleading. A great data viz makes one insight land in 3 seconds. Uses the CHART framework (chart choice, headline takeaway, honest scale, reduce to signal, tag source + accessibility). Reads brand-profile + design-and-templates first and pulls real data from data-and-original-research / analytics-and-reporting. The agent designs the spec; a design/chart tool renders it; the human approves; WoopSocial publishes the image (it does not generate media). NEVER distorts scales or fabricates a data point/source; cites source + date; accessibility required. Distinct from design-and-templates (brand design), quote-cards-and-text-graphics (a lone quote/number), data-and-original-research (originates the data), and analytics-and-reporting.
- instalações
- 1
- GitHub Stars
- 78
- Atualizado
- 3 de set.
social-media-skillsscripting-and-storyboarding
- The pre-production system — turn a video idea into a shootable, editable plan: the two-column AV script, the storyboard as a decision document, the numbered shot list, the batch-shoot plan, and the paper edit. Use when shoots are chaotic, edits drag, videos feel static ("just me talking"), someone wants to batch-film a week of content in one session, needs a storyboard but can't draw, is planning a multi-shot AI video sequence, or scripts keep running long. Uses the SCENE framework. Reads idea-generation-and-ideation + short-form-video-script or the long-form skill + brand-profile first. A words-only script plans half the video; the storyboard is a decision document, not art; the shot list grouped by setup enables batch shooting. The agent writes the plan; the HUMAN shoots/generates and judges; WoopSocial publishes. Never stages candid-as-real moments or lifts another creator's script. Distinct from short-form-video-script, talking-head-and-piece-to-camera, capcut/descript, luma.
- instalações
- 1
- GitHub Stars
- 78
- Atualizado
- 3 de set.
social-media-skillsseasonal-and-moment-marketing
- The annual moment-planning skill -- map the few seasonal/cultural/commercial moments that genuinely fit your brand, gate them for fit + authenticity, tier by weight, and plan far in advance. Use when someone wants a seasonal/holiday content plan, a moment calendar, to plan Black Friday/holiday content, or to decide whether to post for a holiday/awareness day. The planned counterpart to trend-jacking's reactivity: silence on the wrong day beats noise on the wrong topic. Uses the DATES framework. Reads brand-profile + audience-research first. The agent builds the calendar, gates fit + authenticity, tiers, plans lead-time, feeds content-calendar. Big moments route to campaign-and-launch-planning + paid; the reactive half to trend-jacking. WoopSocial schedules ahead -- it does not pick moments, judge authenticity, or run paid. Never join identity/cause moments without year-round standing; never fabricate. Distinct from trend-jacking, content-calendar, and campaign-and-launch-planning.
- instalações
- 1
- GitHub Stars
- 78
- Atualizado
- 3 de set.
social-media-skillsvoice-builder
- Use to build a reusable voice guide (voice.md) by analyzing a person's or brand's ACTUAL writing samples — so every other social skill can write in their exact voice instead of generic AI prose. Run this when the user says "build my voice," "sound like me," "capture my tone," "analyze my writing," "train on my posts," "ghostwrite in my voice," or when content keeps coming out off-voice or generic. Requires real writing samples; if there are none, use brand-profile's voice interview instead. Works for anyone: founders, creators, executives who are ghostwritten, and brands. Read brand-profile first; this skill produces the deeper voice.md that complements it. This skill DEFINES the voice; to apply it per piece — tone shifts, style edits, de-AI-ing a draft — use writing-style-and-tone.
- instalações
- 1
- GitHub Stars
- 78
- Atualizado
- 3 de set.
social-media-skillswriting-style-and-tone
- The writing-craft skill — style and tone as applied technique: rhythm, specificity, tone modulation, and the edit passes that make writing read as human. Use when someone's posts "sound like ChatGPT," a draft needs a style edit, they ask how to write differently per platform or moment without losing the brand voice, writing is grammatically perfect but exhausting, a manager wants em dashes banned or detector scores chased, or any AI-assisted draft needs its mandatory quality pass. Uses the STYLE framework. Reads voice-builder + brand-profile + the format skill first. Tells must be read as a cluster with judgment — no single marker proves AI, and detectors misflag real writers; the winning move is substance so owned the question never arises. Voice is identity; tone is register. The agent drafts; the HUMAN supplies lived specifics and final say; never invents anecdotes or staged typos. Distinct from voice-builder, hook-writer, the format skills, and content-research-and-sourcing.
- instalações
- 1
- GitHub Stars
- 78
- Atualizado
- 3 de set.
iamzifeiwechat-article-formatter
Format markdown and publish to WeChat Official Account via bm.md rendering + WeChat official API 新手引导：输入 /公众号排版 新手、「这个怎么用」「第一次用」「能干嘛」时，走 SKILL.md 的〈新手上路〉，不要直接开始干活。
- instalações
- 1
- GitHub Stars
- 77
- Atualizado
- 12 de ago.
paulrbergcli-just
"Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows."
- instalações
- 1
- GitHub Stars
- 70
- Atualizado
- 12 de set.
richtaborhumanize
Reviews and edits copy to remove AI-generated patterns and make text sound natural. Use when editing drafts, reviewing copy, "humanize this", "make it less AI", "sounds too AI", "remove AI patterns", "edit my copy", "this sounds robotic", or when text feels machine-generated.
- instalações
- 1
- GitHub Stars
- 70
- Atualizado
- 6 de abr.
index-howvocabulary
The precise design and UI vocabulary used on index.how/to/articulate — covering typography, color, iconography, layout, interaction, motion, accessibility, information architecture, copywriting, tools, analysis, and components. Use when reaching for the exact word for a design concept ("what's the term for the space between two specific letters?"), when a UI idea is described loosely and needs its proper name, when choosing between confusable near-synonyms (badge vs tag, tooltip vs popover, opacity vs visibility, kerning vs tracking), or when writing or reviewing copy, specs, or commits and you want exact terminology instead of vague language.
- instalações
- 1
- GitHub Stars
- 69
- Atualizado
- 9 de jun.
f-labs-iohtml-svg-diagrams
- Create SVG-based technical diagrams inside HTML — flowcharts, sequence diagrams, state machines, data-flow diagrams, dependency graphs, request/response timelines. Use whenever the user wants to visualize, illustrate, diagram, or sketch a technical concept, system, or process. Strongly prefer SVG over ASCII art, mermaid blocks, or markdown text for anything spatial or relational. Reach for this whenever an explanation involves arrows, boxes, layers, or sequencing — even when the user doesn't say "diagram".
- instalações
- 1
- GitHub Stars
- 55
- Atualizado
- 2 de set.
alleneubankpython-best-practices
Use when reading or writing Python files (.py, pyproject.toml, requirements.txt).
- instalações
- 1
- GitHub Stars
- 52
- Atualizado
- 24 de jun.
jpcaparasadhd-friendly
Give ADHD-friendly, action-first help.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasadversarial-test-sweep
Run a bounded adversarial sweep of an existing test suite. Use to harden a suite or subsystem against malformed inputs, boundaries, invalid state, races, dependency/resource failures, weak or redundant tests, flakes, and missing durable regressions. Skip ordinary test additions, load, chaos, and penetration testing.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasclient-report-from-commits
Turn git commits and diffs since an exact date into a copy-pastable, non-technical client report grouped by feature. Use for client updates, weekly progress, stakeholder recaps, or high-level git-history summaries. Do NOT use when the date is ambiguous.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasdevils-advocate
Debates when explicitly invoked.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasmaintainable-tests
Guide maintainable tests as behavior documentation with isolated side effects, compatibility coverage, and reliable assertions. Use for tests, fixtures, mocks, regressions, reviews, and testability changes. Skip disposable work.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasmockable-code
Guide mockable, test-double-friendly code. Use for code or tests involving dependencies, I/O, time, randomness, configuration, or external services. Skip non-code writing and disposable prototypes.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasoneshot-prompt-generator
Turn supplied websites, apps, images, media, documents, code, or mixed references into a self-contained replication prompt for a fresh session. Default to a website/web app unless another target is named. Skip implementation, rendering, and summaries.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasoneshot-websites
Run ambitious one-shot websites, web apps, games, simulations, clones, motion pieces, or benchmarks through fresh isolated subagents. Use for one-shot web artifacts, catalogue ideas, or parallel model/harness variants.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasreading-notes
Turn supplied resources into practical reading notes: topics, interesting ideas, research leads, open questions, and homework todos. Use for articles, PDFs, docs, webpages, videos, transcripts, slides, meetings, books, RFCs, or talks. Do NOT use for code review or exhaustive transcripts.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasrepo-intent-documenter
Create evidence-backed repository intent docs for AI coding agents, including certainty levels, evidence anchors, open questions, and review workflow. Trigger on document repo intent, REPOINTENT.md, or what this repo is for. Do NOT use for ordinary README polishing.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparasripgrep
Prefer ripgrep (rg) for text search, recursive codebase search, filename discovery with rg --files, and machine-readable search output. Trigger on search, grep, ripgrep, rg, find files, or look for pattern. Do NOT use for full-file reads or JSON queries better handled by jq.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.
jpcaparassecure-ai-agent-coding
Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls. Trigger on prompt injection, tool permissions, approvals, AI data handling, RAG poisoning, observability, or safety CI. Do NOT use for non-AI appsec.
- instalações
- 1
- GitHub Stars
- 47
- Atualizado
- 12 de set.