openclaw 网盘下载
OpenClaw

技能详情(站内镜像,无评论)

首页 > 技能库 > Decision Logger

Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions aft...

开发与 DevOps

作者:Alireza Rezvani @alirezarezvani

许可证:MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本:v2.1.1

统计:⭐ 0 · 238 · 2 current installs · 2 all-time installs

0

安装量(当前) 2

🛡 VirusTotal :良性 · OpenClaw :良性

Package:alirezarezvani/decision-logger

安全扫描(ClawHub)

  • VirusTotal :良性
  • OpenClaw :良性

OpenClaw 评估

The skill is internally consistent with a local, file-based decision-logging utility (parser + CLI reporter) and requests no credentials or installs, but there is a small mismatch between the SKILL.md's claimed write-workflow and the included script (which appears to be a read/parse/report tool); review the remaining code to confirm it does not write or network-exfiltrate before use.

目的

Name/description and included files line up: a decision-logging memory architecture plus a Python CLI (scripts/decision_tracker.py) and a template. However, SKILL.md describes a logging workflow that includes writing raw transcripts and appending founder-approved entries to decisions.md, while the visible portion of scripts/decision_tracker.py is a parser/reporter (reads decisions.md and produces reports). This is a capability mismatch (docume…

说明范围

Runtime instructions operate on local project paths under memory/board-meetings/ (decisions.md, YYYY-MM-DD-raw.md, archive/). SKILL.md explicitly forbids auto-loading raw transcripts and defines DO_NOT_RESURFACE rules. There are no instructions to read unrelated system files, environment variables, or to transmit data to external endpoints.

安装机制

No install spec is provided and the Python script claims to use only the standard library. That minimizes installation risk — nothing downloaded or extracted by the skill itself.

证书

The skill requires no environment variables, no credentials, and no config paths. All declared I/O is local files under memory/board-meetings/, which is proportionate to a decision-logging tool.

持久

The skill is not marked always:true and uses the platform default for invocation. It does not request elevated/system-wide persistence. SKILL.md notes Layer 2 is loaded automatically by the board-meeting skill in Phase 1, which is a behavioral detail but not a privilege escalation in this package alone.

综合结论

This appears to be a local, file-based decision logger and report generator that does not request secrets or install software. Before installing or enabling it for autonomous use: (1) Inspect the remainder of scripts/decision_tracker.py (search for open(..., 'w'/'a'), os.system/subprocess, socket or requests usage) to confirm it does not write files unexpectedly or make network calls. (2) If you intend to keep raw transcripts private, confirm …

安装(复制给龙虾 AI)

将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「Decision Logger」。简介:Two-layer memory architecture for board meeting decisions. Manages raw transcri…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/alirezarezvani/decision-logger/SKILL.md
(来源:yingzhi8.cn 技能库)

SKILL.md

打开原始 SKILL.md(GitHub raw)

---
name: "decision-logger"
description: "Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval."
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: c-level
  domain: decision-memory
  updated: 2026-03-05
  python-tools: scripts/decision_tracker.py
---

# Decision Logger

Two-layer memory system. Layer 1 stores everything. Layer 2 stores only what the founder approved. Future meetings read Layer 2 only — this prevents hallucinated consensus from past debates bleeding into new deliberations.

## Keywords
decision log, memory, approved decisions, action items, board minutes, /cs:decisions, /cs:review, conflict detection, DO_NOT_RESURFACE

## Quick Start

```bash
python scripts/decision_tracker.py --demo             # See sample output
python scripts/decision_tracker.py --summary          # Overview + overdue
python scripts/decision_tracker.py --overdue          # Past-deadline actions
python scripts/decision_tracker.py --conflicts        # Contradiction detection
python scripts/decision_tracker.py --owner "CTO"      # Filter by owner
python scripts/decision_tracker.py --search "pricing" # Search decisions
```

---

## Commands

| Command | Effect |
|---------|--------|
| `/cs:decisions` | Last 10 approved decisions |
| `/cs:decisions --all` | Full history |
| `/cs:decisions --owner CMO` | Filter by owner |
| `/cs:decisions --topic pricing` | Search by keyword |
| `/cs:review` | Action items due within 7 days |
| `/cs:review --overdue` | Items past deadline |

---

## Two-Layer Architecture

### Layer 1 — Raw Transcripts
**Location:** `memory/board-meetings/YYYY-MM-DD-raw.md`
- Full Phase 2 agent contributions, Phase 3 critique, Phase 4 synthesis
- All debates, including rejected arguments
- **NEVER auto-loaded.** Only on explicit founder request.
- Archive after 90 days → `memory/board-meetings/archive/YYYY/`

### Layer 2 — Approved Decisions
**Location:** `memory/board-meetings/decisions.md`
- ONLY founder-approved decisions, action items, user corrections
- **Loaded automatically in Phase 1 of every board meeting**
- Append-only. Decisions are never deleted — only superseded.
- Managed by Chief of Staff after Phase 5. Never written by agents directly.

---

## Decision Entry Format

```markdown
## [YYYY-MM-DD] — [AGENDA ITEM TITLE]

**Decision:** [One clear statement of what was decided.]
**Owner:** [One person or role — accountable for execution.]
**Deadline:** [YYYY-MM-DD]
**Review:** [YYYY-MM-DD]
**Rationale:** [Why this over alternatives. 1-2 sentences.]

**User Override:** [If founder changed agent recommendation — what and why. Blank if not applicable.]

**Rejected:**
- [Proposal] — [reason] [DO_NOT_RESURFACE]

**Action Items:**
- [ ] [Action] — Owner: [name] — Due: [YYYY-MM-DD] — Review: [YYYY-MM-DD]

**Supersedes:** [DATE of previous decision on same topic, if any]
**Superseded by:** [Filled in retroactively if overridden later]
**Raw transcript:** memory/board-meetings/[DATE]-raw.md
```

---

## Conflict Detection

Before logging, Chief of Staff checks for:
1. **DO_NOT_RESURFACE violations** — new decision matches a rejected proposal
2. **Topic contradictions** — two active decisions on same topic with different conclusions
3. **Owner conflicts** — same action assigned to different people in different decisions

When a conflict is found:
```
⚠️ DECISION CONFLICT
New: [text]
Conflicts with: [DATE] — [existing text]

Options: (1) Supersede old  (2) Merge  (3) Defer to founder
```

**DO_NOT_RESURFACE enforcement:**
```
🚫 BLOCKED: "[Proposal]" was rejected on [DATE]. Reason: [reason].
To reopen: founder must explicitly say "reopen [topic] from [DATE]".
```

---

## Logging Workflow (Post Phase 5)

1. Founder approves synthesis
2. Write Layer 1 raw transcript → `YYYY-MM-DD-raw.md`
3. Check conflicts against `decisions.md`
4. Surface conflicts → wait for founder resolution
5. Append approved entries to `decisions.md`
6. Confirm: decisions logged, actions tracked, DO_NOT_RESURFACE flags added

---

## Marking Actions Complete

```markdown
- [x] [Action] — Owner: [name] — Completed: [DATE] — Result: [one sentence]
```

Never delete completed items. The history is the record.

---

## File Structure

```
memory/board-meetings/
├── decisions.md       # Layer 2: append-only, founder-approved
├── YYYY-MM-DD-raw.md  # Layer 1: full transcript per meeting
└── archive/YYYY/      # Raw files after 90 days
```

---

## References
- `templates/decision-entry.md` — single entry template with field rules
- `scripts/decision_tracker.py` — CLI parser, overdue tracker, conflict detector