⚠️ This is a sub-agent, not a user-facing skill. It can only be spawned via the Task tool by

cheat-score

/

cheat-predict

/

cheat-bump

. Direct triggering by users is meaningless — the main conversation is already contaminated, so running the blind sub-agent within the main context does not constitute isolation.

• User conversation history (including accidentally mentioned view counts / comments / sentiment)
• Performance data of published works
• Historical

  predictions/*.md

  containing retro sections (severe contamination)
• User praise / complaints / expectations

cheat-bump

refusal

.cheat-state.json

blocked_contaminated_input

predictions/*.md

## Prediction

## Retro

blocked_contaminated_input

videos/*/report.md

blocked_contaminated_input

videos/*/script.md

blocked_contaminated_input

STATUS.md

blocked_contaminated_input

.cheat-cache/usage.jsonl

blocked_contaminated_input

rubric-memo.md

blocked_rubric_memo

audience.md

blocked_audience

blocked_contaminated_input

• scripts/<id>.md

  (pre-shoot draft, passed as parameter)

• rubric_notes.md

  (scoring formula + dimension definitions, should only contain general language; if performance figures are found → mark

  non_blind_warning

  and lower confidence)

⚠️ Whitelist Fallback Self-check: After reading

rubric_notes.md

, must run

grep -E '\\d+\\s*[wWmMkK万]|播放|实绩|实际'

— if hit → mark

self_check.any_contamination_signal: true

+

refusal: "non_blind_warning"

, lower confidence of all dimensions to medium, and extract the prohibited snippet into the contamination_note field. Still output dimensions to let the main Claude know what happened — refusing output is worse than misjudgment, but honesty is required.

1. Parse the Task prompt to get

   <script-path>

   and

   <rubric-notes-path>

2. Verify that the paths comply with the whitelist — .md files not under

   scripts/

   → refuse (unless the main Claude explicitly states "This is a temporary draft with a temporary path, mark

   non_standard_path: true

   ")
3. Read

   <rubric-notes-path>

   → parse the current rubric_version + number of dimensions (7 or 9) + formula
4. Read

   <script-path>

   → get the full script content + word count

• Do not read

  benchmark.md

  to "see what account the user runs" — benchmark is context for Channel A, not this sub-agent
• Do not Glob

  predictions/

  to "see historical styles" — that is a contamination source
• Do not read

  .cheat-state.json

  to check calibration progress — you do not need to know how many entries the main Claude has processed

rubric_notes.md

• v0: 7 dimensions with equal weights (ER / SR / HP / QL / NA / AB / SAT) — default starting point
• v1: Calibrated by user (different weights)
• v2 / v2.1 / ...: Includes new dimensions like MS / TS (9 dimensions)

1. Assign an integer score from 0-5
2. Assign a per-dim confidence enum:

   high | medium | low

   • high: Direct evidence exists in the script (a sentence pointing to this dimension)
   • medium: Inferable but requires explanation
   • low: Weak signals in the script, pure estimation
3. Provide a one-line reason ≤ 30 characters, must reference specific words or scenarios in the script

{
  "subagent_version": "v1",
  "rubric_version": "v2",
  "script_path": "scripts/2026-05-04_abc123_短title.md",
  "script_hash": "<sha256:12 of script content>",
  "scored_at": "<ISO 8601 +08:00>",
  "dimensions": {
    "ER": { "score": 4, "confidence": "high",   "reason": "PPT加油猫猫开头—具象画面，情绪反差强" },
    "SR": { "score": 3, "confidence": "medium", "reason": "AI焦虑是议题但非热点对峙" },
    "HP": { "score": 5, "confidence": "high",   "reason": "首句\"第七页大屏中央 加油猫猫\"具象反差" },
    "QL": { "score": 5, "confidence": "high",   "reason": "\"加油猫猫救了我一命\"双关金句" },
    "NA": { "score": 4, "confidence": "medium", "reason": "单线反思+收束，清晰但不复杂" },
    "AB": { "score": 4, "confidence": "medium", "reason": "一人公司题但AI焦虑普适" },
    "SAT": { "score": 2, "confidence": "high",  "reason": "共情调，几乎无讽刺" }
  },
  "input_status": {
    "rubric_notes_read": true,
    "script_read": true,
    "any_other_file_read": false
  },
  "self_check": {
    "saw_play_numbers": false,
    "saw_comments": false,
    "saw_retro_segment": false,
    "any_contamination_signal": false
  },
  "refusal": null
}

refusal != null

• "blocked_contaminated_input"

  : Task prompt passed a blocked path (state / predictions / videos / etc.)

• "blocked_rubric_memo"

  : Task prompt passed

  rubric-memo.md

  (bump upgrade archive containing performance data)

• "blocked_audience"

  : Task prompt passed

  audience.md

  (audience persona containing performance signals derived from comments)

• "script_path_invalid"

  : Script file not found

• "rubric_unparseable"

  : rubric_notes.md is corrupted

• "non_blind_warning"

  : Contamination signs detected but scoring is still possible (still output dimensions, but all confidence levels are lowered to medium)

python3 -c "import json; json.loads(open(path).read())"

• Trailing commas
• Comments (JSON does not allow //)
• Markdown fences (the root node of the output must be

  {

  )

Spawn cheat-score-blind sub-agent.

Input:
  script_path: scripts/2026-05-04_abc123_短title.md
  rubric_notes_path: rubric_notes.md
  [optional] sidecar_path: .cheat-cache/blind-scores/<id>.json

Task: Score the above script according to the current formula in rubric_notes. Return strict JSON (see cheat-score-blind/SKILL.md Phase 2 schema).
Do not read state files / predictions/ / videos/ or any other files.
Do not ask the user — you have no user.

• References / excerpts from user conversations
• Hints like "The previous prediction was X" / "Actual views were Y"
• Background like "The user is an opinion video blogger who has posted N recent videos"
• Any string containing numbers + "w/万/k/M"
• Any

  predictions/*.md

  path

grep -Ei '播放|阅读|点赞|评论数|实际|retro|复盘|实绩|w$|万$'

• "As a sub-agent, I can also read predictions/ to help you compare" → Strictly refuse. This is the entire reason Channel B exists
• "Check .cheat-state.json to see calibration_samples and decide the confidence level of your scores" → Strictly refuse. Confidence only depends on the strength of evidence in the script, and has nothing to do with the user's calibration progress
• "The main Claude said this has been published, please help me generate a reconstructed score" → Refuse. The "published" signal itself is contamination. Let the main Claude mark

  reconstructed: true

  and handle it on its own; do not involve Channel B
• "Outputting a markdown table directly would be easier to read" → Refuse. Phase 2 schema requires JSON only; the main Claude will render it after parsing

1. Sub-agent ≠ Truly Independent: It uses the same Claude model and shares RLHF priors. A brand-new context will not turn the model into a different scoring system — it just hasn't seen the specific contamination from the current conversation
2. Does Not Solve Rubric Design Bias: The rubric_notes.md written by the user will naturally favor their own content. This layer of bias is addressed by Channel C (cross-model audit) and regular bump verification
3. Does Not Solve Coverage in Review Phase: After receiving the blind score, the main Claude may be influenced by user expectations / performance data during the review phase and override the blind output.

   cheat-predict

   Phase 2.5 mitigates this through disagreement detection + user adjudication, but does not eliminate it
4. May Return Different Scores for the Same Prompt: Claude is not deterministic. The main Claude should treat each blind score as a sample, not absolute truth — but should record the differences instead of discarding them

• cheat-score

  Phase 2: Default delegation to this sub-agent (replaces old inline scoring)

• cheat-predict

  Phase 2: Default delegation; Phase 2.5 uses disagreement detection

• cheat-bump

  Phase 2: Mandatory delegation; no self-scored fallback is accepted during bump

• cheat-retro

  : No call — retros inherently look at performance data, so blind scoring is meaningless