Builds or refreshes an account's audience profile from the comments in its post retrospectives and writes it to audience.md for later topic and script work.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add XBuilderLAB/cheat-on-content --skill cheat-persona -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-persona --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/XBuilderLAB/cheat-on-content.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cheat-persona .claude/skills/cheat-persona && 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 "cheat-persona" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main/skills/cheat-persona into .claude/skills/cheat-persona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-persona", 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/XBuilderLAB/cheat-on-content/tree/main/skills/cheat-personaType 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 XBuilderLAB/cheat-on-content --skill cheat-persona -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-persona --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XBuilderLAB/cheat-on-content.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cheat-persona .agents/skills/cheat-persona && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cheat-persona" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main/skills/cheat-persona into .agents/skills/cheat-persona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-persona", 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 XBuilderLAB/cheat-on-content --skill cheat-persona -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-persona --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XBuilderLAB/cheat-on-content.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cheat-persona .cursor/skills/cheat-persona && 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 "cheat-persona" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main/skills/cheat-persona into .cursor/skills/cheat-persona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-persona", 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/XBuilderLAB/cheat-on-content.git --path skills/cheat-persona--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 XBuilderLAB/cheat-on-content --skill cheat-persona -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-persona --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XBuilderLAB/cheat-on-content.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cheat-persona .gemini/skills/cheat-persona && 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 "cheat-persona" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main/skills/cheat-persona into .gemini/skills/cheat-persona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-persona", 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 XBuilderLAB/cheat-on-content cheat-personaInstalls 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 XBuilderLAB/cheat-on-content --skill cheat-persona -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/XBuilderLAB/cheat-on-content.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cheat-persona .github/skills/cheat-persona && 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 "cheat-persona" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main/skills/cheat-persona into .github/skills/cheat-persona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-persona", 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 XBuilderLAB/cheat-on-content --skill cheat-persona -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install XBuilderLAB/cheat-on-content cheat-persona --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/XBuilderLAB/cheat-on-content.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cheat-persona .opencode/skills/cheat-persona && 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 "cheat-persona" agent skill from https://github.com/XBuilderLAB/cheat-on-content/tree/main/skills/cheat-persona into .opencode/skills/cheat-persona/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cheat-persona", 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.
cheat-personaBuilds or refreshes an account's audience profile from the comments in its post retrospectives and writes it to audience.md for later topic and script work.
Top comments with their like counts are pulled from the retrospective section of each file in predictions/, along with completion and follower-conversion figures from videos/*/report.md when those exist. The comments are grouped into a profile of who actually watches and engages, saved as audience.md and compared with the previous version if one is there.
How firm the profile is depends on how many retrospectives exist. With none and no benchmark file it refuses to invent one and tells you to run a few retros first; with only a benchmark it seeds a profile marked unverified; three or more retros count as well grounded. A trait needs at least three supporting comments to be listed as verified, otherwise it is filed as a hypothesis.
The profile is deliberately kept apart from scoring. It shapes what the cheat-seed step writes about, but audience.md is on the blind scorer's refusal list, so the prediction step never reads it. The SKILL.md is written in Chinese.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 2d8211e. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
Bash(*)ReadWriteEditGlobGrepFrom 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.
Audience Persona Builder loads about 1.5k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 456 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 noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Bash(*), Read, Write, Edit, Glob, GrepAutomated 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 XBuilderLAB/cheat-on-content at commit 2d8211e, republished under its MIT licence (© XBuilderLAB). 456 words, ~1,509 tokens.
.claude/skills/cheat-persona/SKILL.md (or your agent's skills folder).从 predictions/*.md 复盘段的评论数据，聚类出账号真实受众画像，写入 audience.md。
persona 是和 rubric 平行的第二个派生物，不是 rubric 的一部分：
复盘数据（评论 + 完播 + 转粉）
├──→ rubric 进化（cheat-bump） —— "怎么打分"
└──→ 受众画像（cheat-persona） —— "谁在看"
两者都喂给 cheat-seed，但用途不同绝不混：persona 不进打分公式。rubric 的 AB 维度（受众广度）可以参考 persona，但那是 cheat-bump 的事，不是这里。
audience.md 从复盘评论派生 = 含已发布作品的实绩信号。因此：
audience.md 在 cheat-score-blind 的 hard refusal list 里，refusal_code blocked_audience[用户：构造受众画像 / 更新 persona]
↓
[Phase 0: 收集数据 — 扫 predictions/*.md 复盘段评论 + benchmark.md]
↓
[Phase 1: 数据量判定 → 派生 Confidence 等级]
↓
[Phase 2: 评论聚类 — 自我认同 / 情绪寄存 / 反驳点 / 语言]
↓
[Phase 3: persona × rubric 交叉检验]
↓
[Phase 4: 写 audience.md（覆盖式重建，header 记 version + last_rebuilt）]
↓
[Phase 5: 控制台报告 + 跟上次画像的 diff]💡 调用覆盖：
/cheat-persona — seed-from-benchmark（强制用 benchmark seed）/— rebuild（即使数据没变也重建）
| 来源 | 用途 |
|---|---|
predictions/*.md 的 ## 复盘 段 | 主数据源——top 评论（带赞数）。persona 的金矿 |
videos/*/report.md | 完播 / 转粉率——薄信号，推"留得住 vs 留不住" |
benchmark.md | 冷启动 seed——"看对标的人 ≈ 你想要的人" |
rubric_notes.md | Phase 3 交叉检验用——persona 食欲 vs rubric 校准现实 |
audience.md（如已存在） | 上一版画像，用于 Phase 5 diff |
predictions/*.md，对每个文件读 ## 复盘 段（只读复盘段——这是 channel A，本来就看实绩）N_retros、评论总数 N_commentsbenchmark.md（如存在）audience.md（如已存在）→ 留作 Phase 5 diff| 情况 | Confidence | 行为 |
|---|---|---|
N_retros == 0 且无 benchmark | 🔴 无数据 | 不强行造——告诉用户"persona 需要复盘数据。先跑几篇 cheat-retro，或导 benchmark"，退出 |
N_retros == 0 但有 benchmark | 🟠 benchmark-seed 未验证 | seed 一份 aspirational persona，全文标"未验证" |
N_retros 1-2 | 🟡 早期信号 | 能产出但特征多落"假设"段 |
N_retros 3-5 | 🟢 数据扎实 | 正常产出 |
N_retros ≥6 | 🔵 稳健 | 正常产出 + 可做更细的食欲分层 |
Confidence 等级写进 audience.md header。
对收集到的所有评论，按四个维度聚类：
聚类纪律：
MIN_COMMENTS_PER_TRAIT（3）条评论证据。不够 → 降到"假设特征"段读 rubric_notes.md 当前 rubric + 校准历史。检查：
诚实要求：两个派生物矛盾时不要强行调和。明确写"persona 说 A，rubric 校准说 B，待下次复盘澄清"——矛盾本身是信号。
覆盖式重建（不是 append）——persona 是活文档，每次 rebuild 重写全文。但：
Persona 版本 +1（v0 → v1 → v2）Last rebuilt 日期 + 数据基础（N 篇复盘 / M 条评论）+ ConfidencevN — 基于 M 篇复盘 / K 条评论，主要变化：...（这是唯一保留的历史；不搞 memo 累积——persona 是活文档不是公式）用 templates/audience.template.md 的结构。
⚠️ 不走版本 memo / 不调跨模型审——persona 不是高风险不可逆动作（写错了重跑一次就好），过度工程没必要。
✅ 受众画像已更新：audience.md（v2，🟢 数据扎实）
数据基础：4 篇复盘 / 87 条评论
核心画像：25-35 岁职场人，来找情绪共鸣不来找信息……
跟 v1 的主要变化：
- 新验证："深夜刷手机" 场景共鸣强（v1 是假设，本次 17 条评论验证）
- 新反画像：原以为"学生党"是受众，但评论里学生占比 <5% → 移到反画像
- ⚠️ 交叉检验 flag：persona 说受众爱"职场吐槽"，但 rubric 校准显示职场类 composite 偏低——下次复盘留意
下一步：
- cheat-seed 选题 / 写稿时会自动参考这份画像
- 再跑 3 篇复盘后建议再 /cheat-persona 刷新user-asserted（未经数据验证）user-asserted 放"假设特征"段，不放"验证特征"。persona 的价值在于数据 vs 你的幻想之间的 gapcheat-retro 每完成一篇复盘 → flag "已累计 N 篇复盘，可跑 /cheat-persona 刷新画像"cheat-init 创建空 audience.md 骨架；如导了 benchmark → 提示可 /cheat-persona — seed-from-benchmarkcheat-seed Mode A/B/C 读 audience.md 作为"这个 persona 会在乎吗"的镜子cheat-recommend persona-fit 排序；cheat-status persona 新鲜度 nagcheat-score-blind 硬禁读 audience.md（refusal_code blocked_audience）© XBuilderLAB, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/cheat-persona of XBuilderLAB/cheat-on-content.
Open the folder on GitHubat commit 2d8211e
Audience Persona Builder 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 |
|---|---|---|---|---|---|---|
| Audience Persona Builder this skillXBuilderLAB/cheat-on-content | 7.2k | — | ~1.5k | Automated safety check: Notes | MIT | |
| 15 Social Listening Globalminhnv0807/ai-business-skills | 608 | — | ~4.8k | Automated safety check: Pass | MIT | |
| Twitter Searchsundial-org/awesome-openclaw-skills | 663 | — | ~2.3k | Automated safety check: Pass | None | |
| Getxapi ConnectLeoYeAI/openclaw-marketing-skills | 1k | 1 repos | ~715 | Automated safety check: Pass | Custom licence | |
| Content Traffic and Value Diagnosisdontbesilent2025/dbskill | 10k | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| Xiaohongshu Title Formula Matcherdontbesilent2025/dbskill | 10k | 1 repos | ~3.4k | Automated safety check: Pass | Custom licence |
minhnv0807/ai-business-skills
A skill your agent uses when the user wants to monitor what is being said about the brand, competitors, and the category — channels and keywords to track, sentiment scoring, weekly and monthly…
sundial-org/awesome-openclaw-skills
Advanced Twitter search and social media data analysis. An agent skill from sundial-org/awesome-openclaw-skills.
LeoYeAI/openclaw-marketing-skills
Connect GetXAPI to pull public X/Twitter marketing signals into OpenClaw workflows.
dontbesilent2025/dbskill
Judges unpublished or underperforming content: who it will attract, whether the opening keeps viewers, how they may engage and what commercial value the traffic has.
dontbesilent2025/dbskill
Matches a Xiaohongshu post topic to the best-fitting formulas from a library of 75 proven title patterns, rather than freely generating a title from scratch.
JasonColapietro/suede-creator-skills
Turns a video clip, interview moment or transcript into a package that bridges viewers to a long-form guide, with rights, claim and approval gates along the way.
XBuilderLAB/cheat-on-content
Proposes and applies upgrades to a content-scoring rubric: a full formula bump with blind re-scoring and a cross-model audit, or a lighter bucket-boundary recalibration.
XBuilderLAB/cheat-on-content
Onboards a new user to the cheat-on-content workflow with a short question flow, creating the project scaffolding and optionally importing past video history.
XBuilderLAB/cheat-on-content
Imports scripts and engagement numbers from an account you want to emulate, then extracts content patterns and starting scoring signals from them.
XBuilderLAB/cheat-on-content
Upgrades an older .cheat-state.json to the current schema version by applying migration files in order, with dry-run, backup and stop-on-failure behavior.
XBuilderLAB/cheat-on-content
Turns content creation into a calibrated loop of scoring, blind prediction, post-publish review and rubric evolution, with a built-in rubric for opinion videos.
XBuilderLAB/cheat-on-content
Writes an immutable blind prediction log for a finished content draft: a seven-dimension score, bucket, probability distribution and counterfactuals, scored blind by a sub-agent.
Categories
Builds or refreshes an account's audience profile from the comments in its post retrospectives and writes it to audience.md for later topic and script work. md when those exist.md and compared with the previous version if one is there.
Audience Persona Builder fits situations like: building an audience profile for the first time from post retrospectives; refreshing the profile after new retros add more comments; checking who actually engages with an account before planning the next topics.
Run `npx skills add XBuilderLAB/cheat-on-content --skill cheat-persona -a claude-code`. Or copy the skill folder (skills/cheat-persona in XBuilderLAB/cheat-on-content) into .claude/skills/cheat-persona in your project. Claude Code loads it when a task matches its description.
Run `npx skills add XBuilderLAB/cheat-on-content --skill cheat-persona -a codex`. Or copy the skill folder (skills/cheat-persona in XBuilderLAB/cheat-on-content) into .agents/skills/cheat-persona 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 XBuilderLAB/cheat-on-content --skill cheat-persona -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cheat-persona, .gemini/skills/cheat-persona, .github/skills/cheat-persona and .opencode/skills/cheat-persona in your project.
SKILL.md names no scripts, command-line tools or credentials: Audience Persona Builder is instructions for the agent only. Our summary lists: A project with predictions/ retrospective files that contain comments; Optionally a benchmark.md to seed a first, unverified profile. Its frontmatter pre-approves these tools: Bash(*), Read, Write, Edit, Glob, Grep.
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 notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Audience Persona Builder is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Audience Persona Builder: 15 Social Listening Global (minhnv0807/ai-business-skills, 608 stars), Twitter Search (sundial-org/awesome-openclaw-skills, 663 stars), Getxapi Connect (LeoYeAI/openclaw-marketing-skills, 1k stars) and Content Traffic and Value Diagnosis (dontbesilent2025/dbskill, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
XBuilderLAB (a GitHub organization) maintains it in XBuilderLAB/cheat-on-content, which has 7,225 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 5, 2026.
Source: XBuilderLAB/cheat-on-content on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
