← Back to Skills Marketplace
harrylabsj

Decision Recorder

by haidong · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
333
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install decision-recorder
Description
Record, review, search, and analyze decisions from technical work, product work, team discussions, and personal planning. Use when the user wants to capture...
README (SKILL.md)

Decision Recorder

Record decisions in a structured format so they can be searched, reviewed, and improved over time.

Core capabilities

  • Detect decision-oriented text
  • Create structured decision records
  • Search and filter past decisions
  • Review decision details
  • Analyze decision patterns
  • Update or delete stored decisions

Commands

Record a decision

decision-recorder record
decision-recorder r

List decisions

decision-recorder list
decision-recorder ls

Search decisions

decision-recorder search \x3Ckeyword>
decision-recorder s \x3Ckeyword>

Analyze patterns

decision-recorder analyze
decision-recorder a

View a specific decision

decision-recorder view \x3Cid>
decision-recorder v \x3Cid>

Update or delete a decision

decision-recorder update \x3Cid>
decision-recorder u \x3Cid>

decision-recorder delete \x3Cid>
decision-recorder d \x3Cid>

Detect decision keywords

decision-recorder detect "We decided to use Node.js"
decision-recorder keywords

Common filters

# Filter by tag
decision-recorder list --tag=important

# Filter by date range
decision-recorder list --from=2024-01-01 --to=2024-12-31

Programmatic usage

const dr = require('decision-recorder');

const record = dr.createDecision({
  question: 'Which backend stack should we use?',
  options: ['Node.js', 'Python', 'Go'],
  reasoning: 'Node.js has the best fit for fast iteration and ecosystem support.',
  result: 'Node.js',
  context: 'New product launch',
  tags: ['architecture', 'backend']
});

const matches = dr.searchDecisions('architecture');
const analysis = dr.analyzeDecisions();

Decision record format

{
  "id": "unique-id",
  "timestamp": "ISO-8601 timestamp",
  "question": "Decision question",
  "options": ["Option A", "Option B"],
  "reasoning": "Why this choice was made",
  "result": "Final choice",
  "context": "Background",
  "tags": ["tag-a", "tag-b"]
}

Data location

Decision records are stored under:

~/.decision-recorder/

Each decision is stored as a JSON file.

Recommended use cases

  • Architecture and technology choices
  • Product tradeoff decisions
  • Team decisions after discussion
  • Operational decisions and retrospectives
  • Personal planning and career decisions

Good practice

  1. Record decisions soon after they are made.
  2. Capture reasoning, not just outcomes.
  3. Use tags consistently.
  4. Review decisions periodically.
  5. Compare similar decisions over time.

Notes

  • Requires Node.js 14 or later.
  • Uses local JSON files for storage.
  • Works best when reasoning and context are written clearly.

License

MIT

Usage Guidance
This skill appears to do what it says (local decision recording and analysis) and does not request secrets or network access, but the packaged code/metadata contain multiple inconsistencies (incorrect package.json entries, mismatched file paths, possible broken require() calls). Before installing or running globally: 1) Inspect the files locally and verify or fix package.json 'main' and 'bin' fields to point to the correct files; 2) Run the CLI in a sandbox or throwaway account and test create/list/search operations; 3) Confirm the CLI’s require paths (bin/cli.js expecting './index') and ensure src/index.js is importable (or add a root index.js); 4) Backup any existing ~/.decision-recorder data and check file permissions; 5) If you cannot or do not want to edit code, avoid installing globally and prefer running the scripts directly from a controlled directory. The inconsistencies look like sloppy packaging rather than malicious intent, but treat the package as untrusted until you validate and, if necessary, correct it.
Capability Analysis
Type: OpenClaw Skill Name: decision-recorder Version: 1.0.1 The decision-recorder skill is a legitimate utility for capturing and analyzing decision-making processes. It stores data locally in JSON format within the user's home directory (~/.decision-recorder/) and lacks any network communication, sensitive data access (e.g., SSH/AWS keys), or suspicious execution patterns. The code in src/index.js and bin/cli.js strictly follows the functionality described in SKILL.md without any hidden or malicious behaviors.
Capability Assessment
Purpose & Capability
Name/description (record, search, analyze decisions) align with the code and SKILL.md: data is stored locally under ~/.decision-recorder and operations are local CRUD and analysis. No unexpected services, credentials, or network calls are requested.
Instruction Scope
SKILL.md instructions restrict operations to local JSON files and to Node.js usage; they do not instruct reading unrelated system files, sending data externally, or requiring extra credentials. Programmatic and CLI usages described match the intended local scope.
Install Mechanism
There is no explicit install spec (instruction-only), but a package.json and code files are included. The package metadata and file layout are inconsistent: package.json 'bin' entry points to './bin/decision-recorder' which does not exist (actual file is bin/cli.js), 'main' is 'index.js' but the project places index at src/index.js, and registry metadata version differs from package.json version. Several require() paths in the code also appear mismatched (bin/cli.js requires './index' relative to bin/, but index lives in src/). These inconsistencies mean the package may be nonfunctional as distributed and could require manual fixes to run.
Credentials
The skill requests no environment variables, binaries, or credentials. Data is stored in the user's home directory (~/.decision-recorder), which is proportionate to the claimed function. There are no unexpected requests for secrets or unrelated service tokens.
Persistence & Privilege
The skill does not declare always:true and does not request elevated system privileges. It stores its own data under ~/.decision-recorder only. There is no evidence it tries to modify other skills or system-wide configurations.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install decision-recorder
  3. After installation, invoke the skill by name or use /decision-recorder
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Update documentation to English.
v1.0.0
- Initial release of Decision Recorder CLI tool - Record, list, update, delete, and search decisions with structured fields (question, options, reasoning, result, tags) - Analyze decision patterns and trends - Detect decision keywords in both Chinese and English - JSON file storage per decision in user directory - Includes command-line usage and Node.js API support
Metadata
Slug decision-recorder
Version 1.0.1
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is Decision Recorder?

Record, review, search, and analyze decisions from technical work, product work, team discussions, and personal planning. Use when the user wants to capture... It is an AI Agent Skill for Claude Code / OpenClaw, with 333 downloads so far.

How do I install Decision Recorder?

Run "/install decision-recorder" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Decision Recorder free?

Yes, Decision Recorder is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Decision Recorder support?

Decision Recorder is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Decision Recorder?

It is built and maintained by haidong (@harrylabsj); the current version is v1.0.1.

💬 Comments