deep-assumptions

Files (1)

• SKILL.md

SKILL.md (first lines)

## Inputs (skill args)

| 인자 | 의미 |
|---|---|
| (없음) / `report` | Default — per-assumption confidence + Wilson Score + verdict + model-aware split |
| `report --verbose` | Per-signal per-session breakdown |
| `history` | ASCII confidence evolution timeline (requires 5+ sessions) |
| `export --format=badge` | shields.io 호환 JSON badge 출력 |
| `--rebuild` | Receipt 파일에서 JSONL 재생성 후 report 표시 |

빈 args / 매칭되지 않는 토큰 → 본문의 default 분기로 진입.

## Prerequisites

**Hub-spoke 관계**: 본 skill 은 `deep-status` hub 의 sub-page 입니다 — `/deep-status --<flag>` 가 본문 로직을 inline Read 하여 실행하는 것이 주 경로이며, 직접 호출도 동일하게 지원됩니다.


> **Internal** — `/deep-status --assumptions`가 이 파일의 로직을 `Read`하여 실행합니다. 자동 호출이 주 경로이며, 직접 호출도 지원됩니다.
> 참조처: `${CLAUDE_PLUGIN_ROOT}/skills/deep-status/SKILL.md` §9 (`Read ${CLAUDE_PLUGIN_ROOT}/skills/deep-assumptions/SKILL.md and follow its logic`).

# Assumption Health Report

Analyze deep-work's enforcement assumptions against session history to determine which rules are justified by evidence and which should be loosened.

## Language

Read(`${CLAUDE_PLUGIN_ROOT}/skills/shared/references/user-language.md`) and follow it.

## Usage

- `/deep-assumptions` — Show assumption health report (default: `report`)
- `/deep-assumptions report` — Per-assumption confidence with Wilson Score, verdict, model-aware split
- `/deep-assumptions report --verbose` — Per-signal per-session breakdown
- `/deep-assumptions history` — ASCII confidence evolution timeline (requires 5+ sessions)
- `/deep-assumptions export --format=badge` — shields.io JSON badge output
- `/deep-assumptions --rebuild` — Regenerate JSONL from receipts, then show report

## Runtime Setup

### 1. Read state and paths

Read(`${CLAUDE_PLUGIN_ROOT}/skills/deep-resume/references/session-detection.md`) and apply only its **Reusable session-state resolution** section to resolve `$STATE_FILE`; retain this skill's own no-session and standalone-mode behavior.

Read `$STATE_FILE` and extract `work_dir`. If the state file doesn't exist, default `work_dir` to `deep-work`.

Set paths:
```
PLUGIN_SCRIPTS = ${CLAUDE_PLUGIN_ROOT}/hooks/scripts
(plugin root 기준 절대 경로. 이 파일 위치에서 상대 유도하지 말 것 — 해석 기준이 target workspace로 넘어간다.)
REGISTRY_PATH = ${CLAUDE_PLUGIN_ROOT}/assumptions.json
WORK_DIR = $PROJECT_ROOT/<work_dir from state or "deep-work">
HISTORY_PATH = $WORK_DIR/harness-history/harness-sessions.jsonl
```

### 2. Parse subcommand

From `$ARGUMENTS`, determine the subcommand:

| Input | Action |
|-------|--------|
| (empty), `report` | Report (default) |
| `report --verbose` | Verbose report |
| `history` | Timeline |
| `export --format=badge` | Badge export |
| `--rebuild` | Rebuild JSONL, then report |

## Subcommand: `--rebuild`

Regenerate `harness-sessions.jsonl` from receipt files. This repairs corrupted or missing history.

Run via Bash:
```bash
echo '{"action":"rebuild","workDir":"<WORK_DIR>"}' | node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/assumption-engine.js"
```

Parse the JSON result. If `sessions` array is non-empty, write each session as a line to `$HISTORY_PATH` (creating `harness-history/` directory first with `mkdir -p`).

Display:
```
JSONL 재생성 완료
   소스: $WORK_DIR/receipts/
   세션 수: [N] entries rebuilt
   파일: $HISTORY_PATH
```

Then proceed to the default `report` subcommand.

## Subcommand: `report` (default)

### Step 1: Cold start / new model detection

Read `model_primary` from state file (or `"unknown"`).

Run via Bash:
```bash
echo '{"action":"detect-model","historyPath":"<HISTORY_PATH>","model":"<model_primary>"}' | node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/assumption-engine.js"
```

Parse JSON result. If `isNew` is true and `totalSessions` > 0:
```
⚠️ 새 모델 감지: <model_primary>
   이 모델의 세션 이력이 없습니다. 이전 모델(<totalSessions> sessions)의 데이터를 기반으로 보고합니다.
   해석 시 모델 차이를 고려하세요.
```

If `totalSessions` is 0:
```
ℹ️ 세션 이력이 없습니다.
   deep-work 세션을 실행하면 assumption 검증 데이터가 수집됩니다.
   최소 5회 세션 후 유의미한 분석이 가능합니다.
```
Stop here.

### Step 2: Generate report

Determine options based on arguments:
- Default: `{"splitByModel": true}`
- With `--verbose`: `{"splitByModel": true, "verbose": true}`

From Sungmin-Cho/deep-work, MIT.

More from Sungmin-Cho/deep-work