A skill your agent uses when 競合の伸びた側 / 伸びなかった側のサムネペアで人間が先にブラインド回答し、AI の封印分析と照合して観察眼を鍛える訓練セッションを行うとき。未完了の記録があれば自動で再開し、なければ新規ペアを提案する。「真実の目」「サムネ訓練」「観察眼を鍛える」「目を鍛える」「ブラインド分析」「訓練セッション」「サムネの答え合わせ」で発動。AI…

Custom licenceAuto-check passed

Install Truth Eye

skills CLI
$ npx skills add daiki-beppu/youtube-automation --skill truth-eye -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install daiki-beppu/youtube-automation truth-eye --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/daiki-beppu/youtube-automation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/truth-eye .claude/skills/truth-eye && rm -rf skills-src

Use ~/.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/

Facts

Skill name
truth-eye
GitHub stars
169
Token cost
~618 tokens
SKILL.md length
199 words
Files
6 (incl. references)
Skills in repo
21
Repo updated
First seen
Licence
Custom licence

At a glance

A skill your agent uses when 競合の伸びた側 / 伸びなかった側のサムネペアで人間が先にブラインド回答し、AI の封印分析と照合して観察眼を鍛える訓練セッションを行うとき。未完了の記録があれば自動で再開し、なければ新規ペアを提案する。「真実の目」「サムネ訓練」「観察眼を鍛える」「目を鍛える」「ブラインド分析」「訓練セッション」「サムネの答え合わせ」で発動。AI…

  • Works in 6 steps: 準備 → ブラインド回答 → grilling → …
  • SKILL.md covers 前後工程, 成果物, 前提ガード and 完了条件, plus 7 more sections
  • Calls uv

What it does

Truth Eye is an agent skill from daiki-beppu/youtube-automation. Use when 競合の伸びた側 / 伸びなかった側のサムネペアで人間が先にブラインド回答し、AI の封印分析と照合して観察眼を鍛える訓練セッションを行うとき。未完了の記録があれば自動で再開し、なければ新規ペアを提案する。「真実の目」「サムネ訓練」「観察眼を鍛える」「目を鍛える」「ブラインド分析」「訓練セッション」「サムネの答え合わせ」で発動。AI に競合サムネを分析させるなら channel-research の thumbnail mode、自チャンネルのサムネ生成・改善は /thumbnail を使う

Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/grilling.md`, `references/pair-selection.md` and `references/record-format.md`).

The repository describes itself as: YouTube チャンネル自動化 共有コア.

Example prompts

  • “/truth-eye”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 準備
  2. ブラインド回答
  3. grilling
  4. 出し切り宣言と促し
  5. 開示と照合
  6. 学び

What it can do on your machine

Read from SKILL.md and the folder at commit 4725876. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Truth Eye loads about 618 tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 199 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~618
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.9k

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.

Safety

Auto-check passed

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.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 199 words (~618 tokens).

“config/channel/ が存在し load_config() で読めることを確認する。満たさなければ /setup を案内して停止する。yt-truth-eye pair が旧 shape または benchmark JSON 不在で停止した場合は、そのメッセージをそのまま示して停止し、収集を代行しない。”

— opening of SKILL.md by daiki-beppu, Custom licence
name
truth-eye
purpose
振り返る

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (references) in .claude/skills/truth-eye of daiki-beppu/youtube-automation.

  • SKILL.md
  • references/grilling.md
  • references/pair-selection.md
  • references/record-format.md
  • references/sealed-analysis.md
  • references/viewpoints.md

Open the folder on GitHubat commit 4725876

Compare with similar skills

Truth Eye 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.

Truth Eye compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Truth Eye this skilldaiki-beppu/youtube-automation169—~618Automated safety check: PassCustom licence
Creative EyeLeoYeAI/openclaw-master-skills2.2k—~6kAutomated safety check: PassMIT
Designers EyeLeoYeAI/openclaw-master-skills2.2k—~5.6kAutomated safety check: PassMIT
Regulator Eyesmohitagw15856/pm-claude-skills1.4k—~1.1kAutomated safety check: PassMIT
Discovery Eyesmohitagw15856/pm-claude-skills1.4k—~1.2kAutomated safety check: PassMIT
Positioning Truth Traceraaron-he-zhu/aaron-marketing-skills2.9k—~3.5kAutomated safety check: PassApache-2.0

Similar skills

  • Creative Eye

    LeoYeAI/openclaw-master-skills

    Give AI agents creative judgment and design taste. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~6k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Designers Eye

    LeoYeAI/openclaw-master-skills

    Get honest design feedback. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~5.6k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • Regulator Eyes

    mohitagw15856/pm-claude-skills

    Read your marketing claims, landing page, or ad copy the way a consumer-protection investigator would (FTC/ASA framing) and draft the inquiry letter they could send.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Discovery Eyes

    mohitagw15856/pm-claude-skills

    Read your team's messages the way opposing counsel would in litigation discovery — prevention training that makes communication hygiene visceral.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Positioning Truth Tracer

    aaron-he-zhu/aaron-marketing-skills

    A skill your agent uses when the user asks to "check our positioning against what we can actually ship", "trace which differentiators we can defend", or "reconcile the positioning canvas with the…

    2.9k GitHub stars~3.5k tokensUpdated today
    Marketing & SEOAuto-check passed
  • Ripwire Fresh Eyes

    redhat-et/ripwire

    Maintenance risk in code you did NOT write — inheriting a module, planning a refactor, a suspected god object, 'what's gnarly / where's the rot / safe to touch?': hotspots, dead or inactive code…

    2.4k GitHub stars~10k tokensUpdated today
    DevelopmentAuto-check: notes

More from daiki-beppu/youtube-automation

All 21 skills in this repo
  • Analytics

    daiki-beppu/youtube-automation

    A skill your agent uses when YouTube Analytics の収集・分析・レポート表示を一括実行または一段だけ実行するとき。フラグなしは収集→分析→表示を状態判定付きで進める。公開済み動画の失速分析は --flop と videoid / collection / --since <N、登録者・再生回数など YouTube 統計の表示は --status…

    169 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed
  • Audit

    daiki-beppu/youtube-automation

    A skill your agent uses when 整合性・動画本体・公開後メタデータ・価値ループの監査を一括実行または一段だけ実行するとき。フラグなしは4監査を状態判定付きで進め、音楽ムード × サムネ × タイトルは --alignment、動画解析は --video、ローカルと YouTube のメタデータ整合は --metadata、価値ループは --value-loop…

    169 GitHub stars~975 tokensUpdated 2 days ago
    Auto-check passed
  • Channel Research

    daiki-beppu/youtube-automation

    A skill your agent uses when チャンネル調査を状態判定付きで一括実行または一段だけ実行するとき。競合データ収集は --benchmark、追加競合候補の発掘は --discover、TTP・ニッチ仮説の比較または収集済みデータ分析は --market、競合コメントからの視聴者インサイト抽出は --voice、競合サムネイルの上位群・下位群比較は…

    169 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Channel Strategy

    daiki-beppu/youtube-automation

    A skill your agent uses when チャンネル戦略を状態判定付きで一括実行または一段だけ実行するとき。第一ペルソナは --persona、視聴シーンは --scene、制作制約への翻訳は --constraints、開設後の方向性・ポジショニング・差別化の再検討は --direction…

    169 GitHub stars~897 tokensUpdated 2 days ago
    Auto-check passed
  • Distrokid Helper

    daiki-beppu/youtube-automation

    A skill your agent uses when コレクションの楽曲を DistroKid 配信用に準備し、distrokid-helper Chrome 拡張へ渡すローカルサーバーを起動したいとき(30-distrokid 生成 / disc 分割 / metadata.md / ジャケット 3000×3000 新規生成 / uv run yt-collection-serve…

    169 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed
  • Extension

    daiki-beppu/youtube-automation

    A skill your agent uses when Chrome 拡張(suno-helper / distrokid-helper / community-helper)の導入・更新、または拡張向け collection server の起動・停止を行うとき。「拡張入れて」「extension 更新」「サーバー起動」で発動。排他的な --install / --update /…

    169 GitHub stars~520 tokensUpdated 2 days ago
    Auto-check passed

Questions about Truth Eye

What does Truth Eye do?

A skill your agent uses when 競合の伸びた側 / 伸びなかった側のサムネペアで人間が先にブラインド回答し、AI の封印分析と照合して観察眼を鍛える訓練セッションを行うとき。未完了の記録があれば自動で再開し、なければ新規ペアを提案する。「真実の目」「サムネ訓練」「観察眼を鍛える」「目を鍛える」「ブラインド分析」「訓練セッション」「サムネの答え合わせ」で発動。AI…. Truth Eye is an agent skill from daiki-beppu/youtube-automation.

How do I install Truth Eye in Claude Code?

Run `npx skills add daiki-beppu/youtube-automation --skill truth-eye -a claude-code`. Or copy the skill folder (.claude/skills/truth-eye in daiki-beppu/youtube-automation) into .claude/skills/truth-eye in your project. Claude Code loads it when a task matches its description.

How do I install Truth Eye in Codex?

Run `npx skills add daiki-beppu/youtube-automation --skill truth-eye -a codex`. Or copy the skill folder (.claude/skills/truth-eye in daiki-beppu/youtube-automation) into .agents/skills/truth-eye in your project. Codex loads it when a task matches its description.

Can I use Truth Eye in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add daiki-beppu/youtube-automation --skill truth-eye -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/truth-eye, .gemini/skills/truth-eye, .github/skills/truth-eye and .opencode/skills/truth-eye in your project.

What does Truth Eye need to run?

Going by SKILL.md and its folder, Truth Eye needs the command-line tools its instructions call (uv).

Does Truth Eye access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Truth Eye safe to install?

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.

What licence does Truth Eye use?

Truth Eye has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Truth Eye use?

About 618 tokens (SKILL.md is roughly 2.5k 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 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Truth Eye?

Skills that share tags, products or a category with Truth Eye: Creative Eye (LeoYeAI/openclaw-master-skills, 2.2k stars), Designers Eye (LeoYeAI/openclaw-master-skills, 2.2k stars), Regulator Eyes (mohitagw15856/pm-claude-skills, 1.4k stars) and Discovery Eyes (mohitagw15856/pm-claude-skills, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Truth Eye?

daiki-beppu (a GitHub user) maintains it in daiki-beppu/youtube-automation, which has 169 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 7, 2026.

Source: daiki-beppu/youtube-automation on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.