Humanizer
Azure-Samples/interview-coach-agent-framework
Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.
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…
$ npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install FAIRY123456789/human-edge-agent-skills social-signal-and-tact --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/FAIRY123456789/human-edge-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/social-signal-and-tact .claude/skills/social-signal-and-tact && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "social-signal-and-tact" agent skill from https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/skills/social-signal-and-tact into .claude/skills/social-signal-and-tact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "social-signal-and-tact", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/skills/social-signal-and-tactType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install FAIRY123456789/human-edge-agent-skills social-signal-and-tact --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FAIRY123456789/human-edge-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/social-signal-and-tact .agents/skills/social-signal-and-tact && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "social-signal-and-tact" agent skill from https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/skills/social-signal-and-tact into .agents/skills/social-signal-and-tact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "social-signal-and-tact", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install FAIRY123456789/human-edge-agent-skills social-signal-and-tact --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FAIRY123456789/human-edge-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/social-signal-and-tact .cursor/skills/social-signal-and-tact && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "social-signal-and-tact" agent skill from https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/skills/social-signal-and-tact into .cursor/skills/social-signal-and-tact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "social-signal-and-tact", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/FAIRY123456789/human-edge-agent-skills.git --path skills/social-signal-and-tact--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install FAIRY123456789/human-edge-agent-skills social-signal-and-tact --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FAIRY123456789/human-edge-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/social-signal-and-tact .gemini/skills/social-signal-and-tact && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "social-signal-and-tact" agent skill from https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/skills/social-signal-and-tact into .gemini/skills/social-signal-and-tact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "social-signal-and-tact", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install FAIRY123456789/human-edge-agent-skills social-signal-and-tactInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/FAIRY123456789/human-edge-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/social-signal-and-tact .github/skills/social-signal-and-tact && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "social-signal-and-tact" agent skill from https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/skills/social-signal-and-tact into .github/skills/social-signal-and-tact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "social-signal-and-tact", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install FAIRY123456789/human-edge-agent-skills social-signal-and-tact --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FAIRY123456789/human-edge-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/social-signal-and-tact .opencode/skills/social-signal-and-tact && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "social-signal-and-tact" agent skill from https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/skills/social-signal-and-tact into .opencode/skills/social-signal-and-tact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "social-signal-and-tact", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
social-signal-and-tactRead 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…
Social Signal And Tact is an agent skill from FAIRY123456789/human-edge-agent-skills. 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, apologies, disagreement, gift and courtesy messages, proxy greetings, holiday wishes, warm friend-like chat…
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/message-patterns.md`).
It sits in Writing & Content, covering Humanizing AI text. The repository describes itself as: 18 portable Agent Skills for voice-native AI, human judgment, microbets, social tact, writing, life systems, and safe deployment. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 31a0a16. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Social Signal And Tact loads about 3.8k tokens when it runs, and up to ~7.3k if it reads all its reference files. Until then it costs about 166 tokens; SKILL.md has 2,089 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from FAIRY123456789/human-edge-agent-skills at commit 31a0a16, republished under its MIT licence (© FAIRY123456789). 2,089 words, ~3,800 tokens.
.claude/skills/social-signal-and-tact/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Read the relationship before writing the sentence.
Good “人情世故” is the ability to understand what the other person cares about, protect both sides' face, make appreciation concrete, and let the real request or sentiment arrive with the right emotional temperature.
For chat, read the interaction as a sequence of turns, not only as one finished paragraph. Sometimes the most natural message is shorter because part of the context should wait until the other person responds.
The skill should solve two tasks in order: first determine what the other person's words changed in the relationship; then decide how much of that change to acknowledge in the next message. Do not draft before the signal reading is clear.
For any conversation with meaningful relationship stakes, silently reconstruct the interaction using these fields:
Use cumulative evidence. Repeated specific praise is stronger than one compliment. Public advocacy in front of relevant third parties is stronger than private praise. An invitation into private or family space usually signals more relational warmth than a generic “有空联系”. A concrete introduction, meeting arrangement, document request, or work assignment is stronger evidence of resource intent than encouragement alone.
Do not collapse different signal types into one conclusion. Personal warmth can coexist with professional uncertainty. Praise can be sincere without implying a job, internship, introduction, or future commitment.
A useful internal scale is:
Treat the scale as evidence discipline, not a rigid social ranking. The next message usually matches the observed level or stays slightly below it. Move higher only when the other person has opened that layer first or when a concrete reciprocal gesture is natural.
When the message is Chinese, draft from Chinese conversational logic rather than building an English outline and translating it sentence by sentence. This matters most in WeChat messages to teachers, mentors, leaders, founders, elders, and other senior people.
Prefer person → event → action → feeling over abstract concepts → grouped points → summary judgment. A Chinese message should usually move through what the person said, what happened, and what the user genuinely felt. Do not force several ideas into an English-style list and then close with a generic evaluation such as 这几个点给我很大启发.
Treat connective words such as 也 / 还 / 还是 / 又 as a review trigger when they function like automatic translations of also / too / still / again. Keep them only when they carry real meaning. Do not use them merely to manufacture progression, for example 今天又想了想,还是想专门跟您说声感谢 when a direct 非常感谢您昨晚愿意和我聊这么久 is more natural.
Do not manufacture reflection time. If the conversation happened the previous night, avoid phrases such as 今天静下来以后重新想了一遍, 到今天还一直记着, or other wording that makes one night's interval sound like long-term沉淀. Start from the actual interaction and gratitude unless the user explicitly describes a later reflection process.
Keep the speaker's causal order exact. If a senior's business advice was 先确定自己的预期 → 再看客户需求 → 以预期为尺度调整产品和定价 → 找到平衡, preserve that order. Do not rewrite it into a more familiar framework such as 先看客户需求,再结合自己的预期 merely because it sounds smoother.
Show humility through position and experience, not ceremonial self-deprecation. Natural forms include 您愿意跟我这样一个晚辈聊这么久 and 以我现在的经历,很多话可能还理解不到您真正想表达的深度. Avoid turning humility into a polished speech about how shallow, immature, or ignorant the user used to be unless the user genuinely wants to say that.
Use the user's own syntax as the first reference. Preserve natural repetition, emphasis, and slightly uneven human rhythm when it sounds like the user. Polish only enough to improve clarity, respect, and tact. Do not replace the user's Chinese with generic AI gratitude language.
One idea should normally appear once. If 想通 / 认知提升 / 运动让人静下来 express one connected insight, merge them into one compact passage instead of explaining the same realization across several paragraphs.
When a senior person gives the user a higher-status role over a peer, protect both relationships. For example, if a parent says “please help him become more disciplined,” do not accept a supervisory posture too literally. Reframe it as 互相督促 / 一起进步 / 能帮上的尽力 unless the user truly has formal responsibility. This receives the elder's trust while preserving the peer's dignity.
When praise becomes identity-level—such as maturity, judgment, execution, or future potential—receive it with modesty and one grounded sentence. Do not argue with the praise, amplify it into self-promotion, or immediately attach a request.
When the other person opens a private or family layer, deepen only with true specifics. A reciprocal invitation can be more natural when it names a real place, food, activity, or shared interest. Specificity turns a ceremonial “欢迎来玩” into a believable future social scene. Use this only when the warmth has already been opened by the other person.
Do not cash out goodwill too early. A compliment, public endorsement, or invitation can increase trust without yet becoming a professional resource. Preserve the relationship until there is an L4 trigger or a separate, naturally justified reason to ask. This is especially important when the same network may later contain internships, introductions, collaboration, or hiring opportunities.
When the other person's message reveals two identity anchors, respond to the one that matters most to them. A senior may care about professional expertise and family responsibility at the same time. A short, specific acknowledgement of both can show that the user actually listened. Avoid inventing emotional depth that the conversation did not support.
references/message-patterns.md. Use multiple techniques only when the message still feels natural. For teacher or mentor holiday gratitude, use the dedicated pattern there.有些过意不去 and 让我代他向您问好 are often proportionate. Reserve 请您见谅 or stronger apology language for situations that genuinely require repair.您回办公室后可以尝尝呀,希望您吃着喜欢 over commands such as 记得拿一下 when the context is a gift.很久没联系了, 正好借教师节向您问个好, 顺便跟您问候一下, or 刚好想到您. Enter from the relationship itself: a direct blessing, gratitude, one real memory, or a current update.A、B、C,这几个点给我很大启发, mechanical 也 / 还 / 还是 / 又 progression, and ornamental parallel endings such as 把 A,把 B or 做好 A,走稳 B. Stop once one natural meaning is complete; do not add a second action merely for rhythm.很久没联系了, 正好借教师节问个好, or 顺便问候一下.也 / 还 / 还是 / 又, and artificial reflection-time phrases.想通, 认知, and 静下来?The user may ask for one of these:
克制礼貌熟一点但不冒犯自然拍一下马屁汇报中顺手归功请教式轻松朋友感有分寸地反对送礼/代问候节日感谢潜在人脉关系维护关系信号拆解先养关系,暂不提资源Friend-like naturalness is allowed when the wording fits the real relationship. Fabricated intimacy is not.
Do not invent shared memories, private closeness, endorsements, affection, resource commitments, or facts. Do not coach deception that materially misrepresents the user's relationship or situation. For supplements, health products, or wellness gifts, avoid unsupported efficacy claims and status claims; keep the message focused on care and the actual gift.
© FAIRY123456789, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (references) in skills/social-signal-and-tact of FAIRY123456789/human-edge-agent-skills.
Open the folder on GitHubat commit 31a0a16
Social Signal And Tact next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Social Signal And Tact this skillFAIRY123456789/human-edge-agent-skills | 103 | — | ~3.8k | Automated safety check: Pass | MIT | |
| HumanizerAzure-Samples/interview-coach-agent-framework | 173 | 38 repos | ~5.8k | Automated safety check: Pass | MIT | |
| Avoid AI Writingconorbronsdon/avoid-ai-writing | 4.9k | 3 repos | ~8.1k | Automated safety check: Pass | MIT | |
| User-Facing Text Cleanupguillaumemeyer/watermarks-remover | 24k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Install Anti Sloptrycompai/crm | 11k | 1 repos | ~881 | Automated safety check: Pass | MIT | |
| Stop SlopXe/site | 732 | 8 repos | ~423 | Automated safety check: Pass | MIT |
Azure-Samples/interview-coach-agent-framework
Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.
conorbronsdon/avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms").
guillaumemeyer/watermarks-remover
Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.
trycompai/crm
Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.
Xe/site
Remove AI writing patterns from prose. An agent skill from Xe/site.
op7418/Humanizer-zh
Edits Chinese articles, comments and documents to remove filler, repetition and template phrasing while keeping the facts, the level of certainty and the author's voice.
FAIRY123456789/human-edge-agent-skills
Deploy full-stack apps to user-authorized Alibaba Cloud ECS or comparable Linux VPS hosts with preflight, canary verification, and rollback.
FAIRY123456789/human-edge-agent-skills
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.
FAIRY123456789/human-edge-agent-skills
Convert a long, messy, repetitive, speech-recognition-heavy task dump into a precise executable to-do list.
FAIRY123456789/human-edge-agent-skills
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.
FAIRY123456789/human-edge-agent-skills
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…
FAIRY123456789/human-edge-agent-skills
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.
Categories
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…. Social Signal And Tact is an agent skill from FAIRY123456789/human-edge-agent-skills. 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.
Social Signal And Tact fits situations like: upward communication; progress updates; gift and courtesy messages; proxy greetings.
Run `npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a claude-code`. Or copy the skill folder (skills/social-signal-and-tact in FAIRY123456789/human-edge-agent-skills) into .claude/skills/social-signal-and-tact in your project. Claude Code loads it when a task matches its description.
Run `npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a codex`. Or copy the skill folder (skills/social-signal-and-tact in FAIRY123456789/human-edge-agent-skills) into .agents/skills/social-signal-and-tact in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FAIRY123456789/human-edge-agent-skills --skill social-signal-and-tact -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/social-signal-and-tact, .gemini/skills/social-signal-and-tact, .github/skills/social-signal-and-tact and .opencode/skills/social-signal-and-tact in your project.
SKILL.md names no scripts, command-line tools or credentials: Social Signal And Tact is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Social Signal And Tact is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Social Signal And Tact: Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 24k stars) and Install Anti Slop (trycompai/crm, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
FAIRY123456789 (a GitHub user) maintains it in FAIRY123456789/human-edge-agent-skills, which has 103 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 10, 2026.
Source: FAIRY123456789/human-edge-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.