<Devsly/>
NotebookLM Watermark Remover
Remove the NotebookLM watermark from PDF slide exports — free, unlimited, and 100% in your browser.
View
NotebookLM Video Watermark Remover
Remove the NotebookLM watermark from every frame of your MP4 and auto-trim the end card — free and unlimited.
View
Gemini Watermark Remover
Remove the Gemini (Veo) sparkle watermark from every frame of your AI-generated MP4 — free and unlimited.
View
MCP https://devsly.io/mcp MCP Tools Best Skills API Docs

Keyboard Shortcuts

Navigation

Quick Search
⌘ / Ctrl + K
Toggle Dark Mode
⌘ / Ctrl + D
Close Dialogs
Esc

Tool Actions

Execute / Process
⌘ / Ctrl + Enter
Clear Input
⌘ / Ctrl + Shift + C
Copy Output
⌘ / Ctrl + Shift + X

Editor

Select All
⌘ / Ctrl + A
Undo
⌘ / Ctrl + Z
Redo
⌘ / Ctrl + Shift + Z

Updated 3d ago

by FAIRY123456789

human-edge-agent-skills

18 portable Agent Skills for voice-native AI, human judgment, microbets, social tact, writing, life systems, and safe deployment.

  • Active — Updated in the last 14 days
Works with
  • Claude
  • Codex

107 GitHub stars (107)

+57 in 20 days

Stars gained per day · daily snapshots since Sep 26
Stars gained per day, Sep 26 to Oct 16: +57 in total; the busiest day was Sep 29 with +25 stars.Sep 27: +5 starsSep 28: +16 starsSep 29: +25 starsSep 30: 0 starsOct 1: 0 starsOct 2: +2 starsOct 3: 0 starsOct 4: 0 starsOct 5: +1 starsOct 6: +2 starsOct 7: +2 starsOct 8: 0 starsOct 9: 0 starsOct 10: 0 starsOct 11: 0 starsOct 12: 0 starsOct 13: 0 starsOct 14: 0 starsOct 15: 0 starsOct 16: +4 stars
Stars gained between daily snapshots
PeriodNew stars
Sep 27+5
Sep 28+16
Sep 29+25
Sep 300
Oct 10
Oct 2+2
Oct 30
Oct 40
Oct 5+1
Oct 6+2
Oct 7+2
Oct 80
Oct 90
Oct 100
Oct 110
Oct 120
Oct 130
Oct 140
Oct 150
Oct 16+4
  • 18 skills (18 skills found in its SKILL.md files)
  • 0 forks (0 forks)
  • 3d ago last update (Last updated 3d ago)

Install

Skills CLI

npx skills add FAIRY123456789/human-edge-agent-skills

Asks which skills and agents to install. Just one: npx skills add FAIRY123456789/human-edge-agent-skills --skill aliyun-fullstack-deploy — add -g for every project.

Claude Code

git clone https://github.com/FAIRY123456789/human-edge-agent-skillscp -r "human-edge-agent-skills/skills/aliyun-fullstack-deploy" ~/.claude/skills/

Copies the aliyun-fullstack-deploy skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.

Plugin

/plugin marketplace add FAIRY123456789/human-edge-agent-skills

Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.

Skills can run code on your machine — read the SKILL.md first.

What it does

In the author's own words, from each skill's SKILL.md.

  • aliyun-fullstack-deploy

    Deploy full-stack apps to user-authorized Alibaba Cloud ECS or comparable Linux VPS hosts with preflight, canary verification, and rollback. Use for production deployment and recovery; never purchase infrastructure or mutate an unauthorized host.

    skills/aliyun-fullstack-deploy/SKILL.md on GitHub (opens in a new tab)
  • anti-slop-personal-brand

    Audit a resume, GitHub profile, personal website, portfolio, bio, README, or project list for generic AI slop, stale student-project signals, unsupported grand claims, fragmented identity, weak proof, and outdated first-screen positioning. Use when the user wants a personal brand that feels current, specific, technically credible, and earned rather than over-designed or stuffed with fashionable k…

    skills/anti-slop-personal-brand/SKILL.md on GitHub (opens in a new tab)
  • build-in-public-launcher

    Turn a finished or nearly finished Skill, plugin, repository, micro-tool, research utility, or AI project into a credible public launch that can earn real users and feedback. Use when the work exists but nobody outside the creator has tried it, the README is weak, the launch has no demo or proof metric, or the user wants a GitHub-first build-in-public plan without fake traction or vanity metrics.

    skills/build-in-public-launcher/SKILL.md on GitHub (opens in a new tab)
  • cross-domain-translator

    Translate a problem, workflow, or project from one professional domain into another while preserving the real structure. Use when someone needs to connect domain expertise with software, AI, product, research, data, policy, operations, or another field. Rebuild actors, objects, states, events, constraints, evidence, metrics, and failure modes instead of merely replacing vocabulary.

    skills/cross-domain-translator/SKILL.md on GitHub (opens in a new tab)
  • csdn-technical-writing

    Draft, rewrite, or audit Chinese CSDN-style technical articles using a specific long-form teaching structure: a plain-text overall title, Markdown headings for section levels, dense natural paragraphs, beginner-first progression, commented code examples, and splitting when an article becomes too long. Use for technical tutorials, AI and backend articles, engineering practice notes, and beginner-f…

    skills/csdn-technical-writing/SKILL.md on GitHub (opens in a new tab)
  • deep-talk-to-podcast

    Transform a long private conversation, voice transcript, mentor chat, interview, or two-person deep talk into a privacy-aware podcast package: the real turning points, a natural two-host or interview-style script, show notes, title options, short clips, and a current AI-audio platform recommendation. Use when a normal summary would lose the chemistry and reasoning, or when the user wants to turn…

    skills/deep-talk-to-podcast/SKILL.md on GitHub (opens in a new tab)
  • deployment-proof

    Convert deployment logs, validation reports, Git history, and comparison notes into a redacted GitHub case study, portfolio entry, interview story, and evidence-backed resume bullets. Use after a software deployment, migration, recovery, or automation project when the user wants to demonstrate learning ability or impact without leaking host identities, credentials, private paths, customer data, o…

    skills/deployment-proof/SKILL.md on GitHub (opens in a new tab)
  • fitness-recovery-coach

    Build practical training, recovery, and habit plans from a user's goal, training age, schedule, equipment, sleep, fatigue, pain signals, and current routine. Use for beginner fitness planning, strength or hypertrophy routines, fat-loss habits, recovery-day adjustments, low-risk return-to-training decisions, and training logs. Do not diagnose injuries or replace medical care.

    skills/fitness-recovery-coach/SKILL.md on GitHub (opens in a new tab)
  • one-week-founder-mode

    Compress an overloaded week of startup, research, job-search, creator, or side-project work into one main bet, up to two microbets, essential maintenance, and an explicit kill list. Use when the user has too many parallel ideas, keeps adding tasks, needs a founder-like weekly operating rhythm, or wants every week to end with real external proof instead of a long completed-task list.

    skills/one-week-founder-mode/SKILL.md on GitHub (opens in a new tab)
  • personal-boardroom

    Stress-test a difficult career, startup, study, money, product, or life decision through a small board of explicit decision lenses, then synthesize one evidence-weighted recommendation. Use when the user is torn between options, has several identities or goals in conflict, keeps receiving contradictory advice, or wants more than a generic trade-off list.

    skills/personal-boardroom/SKILL.md on GitHub (opens in a new tab)
  • skill-from-scars

    Mine repeated pain from transcripts, project retrospectives, debugging logs, failed prompts, deployment notes, or work history and decide whether it deserves to become a reusable Agent Skill. Use when the user wants to turn hard-earned experience into open-source knowledge, avoid publishing generic prompts, generate a SKILL.md package with references and evaluations, or identify which repeated mi…

    skills/skill-from-scars/SKILL.md on GitHub (opens in a new tab)
  • small-server-fit

    Assess whether a web application and its build and runtime plan fit a low-cost Linux VPS or Alibaba Cloud ECS before purchase, implementation, or deployment. Use when choosing an OS image, Python, Node.js, or Java versions, build location, worker count, swap strategy, or minimum CPU, RAM, and disk for a repository. Produce evidence-backed FIT, FIT WITH CHANGES, NOT FIT, or NOT MEASURED decisions;…

    skills/small-server-fit/SKILL.md on GitHub (opens in a new tab)
  • social-signal-and-tact

    Read relationship signals across a conversation, infer what changed between turns, then turn awkward, overly formal, blunt, or AI-sounding messages to teachers, leaders, mentors, senior colleagues, partners, acquaintances, or potential professional contacts into short, natural, relationship-aware communication. Use for tactful praise, upward communication, progress updates, favors, reminders, apo…

    skills/social-signal-and-tact/SKILL.md on GitHub (opens in a new tab)
  • student-money-four-buckets

    Help university students allocate a common monthly living allowance into four practical layers: essentials, uncertainty buffer, long-term reserve and growth, and deliberate non-essential enjoyment. Use for budgeting, overspending diagnosis, monthly allowance planning, saving goals, or deciding how much can be safely spent on entertainment without pretending student life should contain zero fun. D…

    skills/student-money-four-buckets/SKILL.md on GitHub (opens in a new tab)
  • trend-to-microbet

    Turn a fast-moving AI, product, creator, career, or technology trend into a small evidence-producing bet instead of a vague FOMO reaction. Use when the user says something is suddenly hot, wonders whether to chase a new model, platform, agent, Skill, or plugin, or wants a 48-hour to 7-day experiment with a clear upside, effort cap, proof metric, and stop rule.

    skills/trend-to-microbet/SKILL.md on GitHub (opens in a new tab)
  • vibe-to-spec

    Convert messy voice input, imperfect speech recognition, half-formed product ideas, and iterative corrections into an implementation-ready software specification for Codex, Claude Code, Copilot, Cursor, or another coding agent. Use when the user speaks faster than they structure requirements, named entities are misrecognized, context or memory can safely resolve recurring terms, and the final out…

    skills/vibe-to-spec/SKILL.md on GitHub (opens in a new tab)
  • voice-dump-to-todo

    Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list. Use when the user speaks tasks in inaccurate ASR language, changes priorities mid-sentence, mixes ideas with actions, or wants a downloadable standalone interactive HTML to-do that can be saved or dragged to the desktop. Use context-aware named-entity repair when a recurring term is clearly…

    skills/voice-dump-to-todo/SKILL.md on GitHub (opens in a new tab)
  • voice-with-temperature

    Rewrite, edit, or draft prose so it becomes clearer while retaining the writer's lived detail, emotional temperature, uncertainty, rhythm, specificity, and intellectual character. Use for reflections, personal essays, technical writing, speeches, bios, posts, or formal prose when normal AI polishing makes the text generic, over-smoothed, slogan-like, or emotionally fake.

    skills/voice-with-temperature/SKILL.md on GitHub (opens in a new tab)

Review before you install

A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.