Agent skill

Vibe Decision Journal

by ash1794 in ash1794/vibe-engineering

Extracts and records architectural decisions from diffs, conversation context, and explicit choices.

MITAuto-check passedDevelopment

Install Vibe Decision Journal

skills CLI
$ npx skills add ash1794/vibe-engineering --skill vibe-decision-journal -a claude-code

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

GitHub CLI
$ gh skill install ash1794/vibe-engineering vibe-decision-journal --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/ash1794/vibe-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/vibe-engineering/skills/vibe-decision-journal .claude/skills/vibe-decision-journal && 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
vibe-decision-journal
GitHub stars
163
Token cost
~1.4k tokens
SKILL.md length
511 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

Extracts and records architectural decisions from diffs, conversation context, and explicit choices.

  • Works in 5 steps: Read the staged diff → Analyze for implicit decisions — Look… → Filter out non-decisions → …
  • Tasks that involve Data cleaning
  • SKILL.md covers When to Use This Skill, When NOT to Use This Skill, Modes and Decision Format, plus 3 more sections
  • Calls git

What it does

Vibe Decision Journal is an agent skill from ash1794/vibe-engineering. Extracts and records architectural decisions from diffs, conversation context, and explicit choices. Supports automatic extraction from staged changes, deduplication against prior decisions, and persistent ADR-format logging with spec traceability. Use after a significant design or architecture choice, before committing a diff that embeds implicit decisions, or when the same question keeps resurfacing.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Data cleaning and Architecture decision records. The repository describes itself as: 33 engineering discipline skills for Claude Code, OpenAI Codex & Gemini CLI + a CLI for CI/CD enforcement. Extracted from real-world multi-agent system development. Born from… The licence is MIT.

When your agent uses it

  • Tasks that involve Data cleaning
  • Tasks that involve Architecture decision records

Example prompts

  • “Use the vibe-decision-journal skill to extract and records architectural decisions from diffs, conversation context, and explicit choices”
  • “/vibe-decision-journal”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read the staged diff
  2. Analyze for implicit decisions — Look for changes that represent choices
  3. Filter out non-decisions
  4. Deduplicate against existing decisions
  5. Present each extracted decision to the user for review (use the harness's structured question tool if it has one; otherwise ask in plain…

What it can do on your machine

Read from SKILL.md and the folder at commit 8f1d71b. 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:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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

Vibe Decision Journal loads about 1.4k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 511 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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

The full file from ash1794/vibe-engineering at commit 8f1d71b, republished under its MIT licence (© ash1794). 511 words, ~1,386 tokens.

Download SKILL.mdSave it as .claude/skills/vibe-decision-journal/SKILL.md (or your agent's skills folder).
name
vibe-decision-journal
description
Extracts and records architectural decisions from diffs, conversation context, and explicit choices. Supports automatic extraction from staged changes, deduplication against prior decisions, and persistent ADR-format logging with spec traceability. Use after a significant design or architecture choice, before committing a diff that embeds implicit decisions, or when the same question keeps resurfacing.
user-invocable
true

vibe-decision-journal

Decisions happen whether you document them or not. This skill makes sure they don't vanish into git history.

When to Use This Skill

  • After making any significant design, architecture, or behavioral choice
  • Before committing — extract implicit decisions from staged diffs
  • When you realize "we keep coming back to this question"
  • After a session where multiple design choices were made without explicit recording

When NOT to Use This Skill

  • Trivial implementation choices (variable naming, formatting, import order)
  • Decisions already captured and reviewed
  • Temporary/reversible choices (which test to run first)

Modes

Mode 1: Automatic Extraction (from staged diffs)

Use when committing or when the user says "what decisions did we make?"

  1. Read the staged diff:

    git diff --cached
  2. Analyze for implicit decisions — Look for changes that represent choices:

    • New abstractions, patterns, or data structures introduced
    • API contracts defined or changed
    • Caching/storage/retry strategies chosen
    • Error handling approaches selected
    • Behavioral changes (not just refactors)
    • Configuration or default values set
  3. Filter out non-decisions:

    • Process/workflow choices ("commit now", "run tests")
    • Tooling setup ("install package X")
    • Pure refactors with no behavioral change
    • Diagnostic observations ("X causes Y")
    • Trivial changes (formatting, imports, variable renames)
  4. Deduplicate against existing decisions:

    • Read existing decisions from docs/decisions/ or project decision log
    • Skip exact matches (same question + same decision)
    • Flag potential conflicts (same topic, different conclusion) — present both to user
    • If a new decision countermands an old one, mark the old one as Superseded by: [new decision]
  5. Present each extracted decision to the user for review (use the harness's structured question tool if it has one; otherwise ask in plain text):

    • Accept — record as-is
    • Accept with edits — user refines the wording
    • Not a decision — discard (it was a refactor, not a choice)
    • Already captured — skip
Mode 2: Explicit Recording (manual)

Use when the user explicitly states a decision.

  1. Capture the decision directly from the conversation.
Show full SKILL.md (205 more words)Show less
Mode 3: Session Sweep

Use at end of session or when user says "what did we decide this session?"

  1. Review the work done this session — files changed, features built, bugs fixed
  2. Extract decisions from the pattern of changes (not just the latest diff)
  3. Present consolidated list for review

Decision Format

markdown
## DEC-[NNNN]: [Short title]
**Date**: [Today]
**Status**: Accepted | Superseded | Rejected
**Supersedes**: DEC-[NNNN] (if applicable)

### Context
[1-2 sentences: what situation prompted this decision]

### Decision
[What was decided. Be specific enough to reconstruct the choice.]

### Alternatives Considered
1. [Alternative A] — Rejected because [reason]

### Consequences
- [What this enables or constrains going forward]

### Affected Files
- [path/to/file.ext]

### Spec Sections (if applicable)
- [Which spec sections this decision affects]

Storage

Decisions are stored in docs/decisions/decisions.jsonl (append-only, one JSON object per line):

json
{
  "id": "DEC-0001",
  "title": "Use Redis for session caching",
  "status": "accepted",
  "date": "2026-03-07",
  "context": "Need sub-10ms session lookups at 10k req/s",
  "decision": "Use Redis with 24h TTL for session data",
  "alternatives": ["In-memory dict (no persistence)", "DynamoDB (too expensive at scale)"],
  "consequences": ["Adds Redis as infrastructure dependency", "Enables horizontal scaling"],
  "affected_files": ["src/cache.py", "config/redis.yml"],
  "spec_sections": ["## Session Management"],
  "supersedes": null,
  "extracted_from": "diff"
}

Also render a human-readable markdown version in docs/decisions/ as DEC-NNNN-[slug].md.

ID assignment: Read existing decisions, find the highest DEC-NNNN, increment by 1.

Deduplication Rules

When extracting decisions automatically:

  1. Exact match: Same question/topic AND same conclusion → skip
  2. Same topic, different conclusion: Present both to user — ask if this supersedes the prior decision
  3. Semantic overlap: If two extracted decisions from the same diff describe the same choice in different words, merge into one and present the clearer version

Output Format

Decisions Extracted: [N]
#DecisionSourceStatus
1Use Redis for session cachingdiff: src/cache.pyAccepted
224h TTL for all cached datadiff: config/redis.ymlAccepted
3Retry with exponential backoffexplicitAlready captured (DEC-0012)
New Decisions Recorded
  • DEC-0045: Use Redis for session caching
  • DEC-0046: 24h TTL for all cached data
Superseded Decisions
  • DEC-0008: "Use in-memory caching" → Superseded by DEC-0045

© ash1794, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/vibe-engineering/skills/vibe-decision-journal of ash1794/vibe-engineering.

Open the folder on GitHubat commit 8f1d71b

Compare with similar skills

Vibe Decision Journal 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.

Vibe Decision Journal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vibe Decision Journal this skillash1794/vibe-engineering163—~1.4kAutomated safety check: PassMIT
Find Similar Functionsmillionco/react-doctor15k—~1.2kAutomated safety check: PassCustom licence
Lead Enrichmenttech-leads-club/agent-skills7k—~5.3kAutomated safety check: PassCustom licence
Monte Carlo Remediationsickn33/agentic-awesome-skills47k1 repos~4kAutomated safety check: PassApache-2.0
Data Cleanbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~1.1kAutomated safety check: PassCustom licence
PR Design DocOpenHands/OpenHands91k—~2.4kAutomated safety check: PassMIT

Similar skills

  • Find Similar Functions

    millionco/react-doctor

    Use truffler to find similar or pre-existing JavaScript/TypeScript symbols before implementing new code, especially helpers, utilities, parsers, formatters, scanners, fuzzy matchers, and other…

    15k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Lead Enrichment

    tech-leads-club/agent-skills

    When the user wants to build data enrichment workflows, score leads against ICP, set up Clay waterfalls, or improve contact data quality.

    7k GitHub stars~5.3k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Monte Carlo Remediation

    sickn33/agentic-awesome-skills

    Investigate and remediate data quality alerts using Monte Carlo MCP tools.

    47k GitHub starsUsed in 1 repo~4k tokens
    DevelopmentAuto-check passed
  • Data Clean

    brycewang-stanford/Auto-Empirical-Research-Skills

    Produce documented data cleaning scripts that log every transformation with N before/after each step, generate a CONSORT-style exclusion flow diagram, create decision log entries for every…

    4.6k GitHub stars~1.1k tokensUpdated 5 days ago
    Data & AnalyticsAuto-check passed
  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    91k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Cto Advisor

    Ibrahim-3d/orchestrator-supaconductor

    Technical leadership guidance for engineering teams, architecture decisions, and technology strategy.

    381 GitHub starsUsed in 4 repos~2.4k tokens
    DevelopmentAuto-check passed

More from ash1794/vibe-engineering

All 33 skills in this repo
  • Vibe Concurrent Test Safety

    ash1794/vibe-engineering

    Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering.

    163 GitHub stars~665 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Fuzz Parser Inputs

    ash1794/vibe-engineering

    Generates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input).

    163 GitHub stars~722 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Golden File Testing

    ash1794/vibe-engineering

    Implements snapshot/golden file tests with temporal normalization so tests don't break daily.

    163 GitHub stars~669 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Parallel Task Decomposition

    ash1794/vibe-engineering

    Analyzes large tasks for independent subtasks that can be safely parallelized.

    163 GitHub stars~717 tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Slop Filter

    ash1794/vibe-engineering

    Strips AI-generation "smell" from prose before it ships (READMEs, docs, release notes, PR descriptions, posts, emails).

    163 GitHub stars~2.3k tokensUpdated 3 days ago
    Auto-check passed
  • Vibe Spec Sync

    ash1794/vibe-engineering

    Keeps specification documents and code in agreement. An agent skill from ash1794/vibe-engineering.

    163 GitHub stars~2.2k tokensUpdated 3 days ago
    Auto-check passed

Questions about Vibe Decision Journal

What does Vibe Decision Journal do?

Extracts and records architectural decisions from diffs, conversation context, and explicit choices. Vibe Decision Journal is an agent skill from ash1794/vibe-engineering. Extracts and records architectural decisions from diffs, conversation context, and explicit choices.

When should I use Vibe Decision Journal?

Vibe Decision Journal fits situations like: tasks that involve Data cleaning; tasks that involve Architecture decision records.

How do I install Vibe Decision Journal in Claude Code?

Run `npx skills add ash1794/vibe-engineering --skill vibe-decision-journal -a claude-code`. Or copy the skill folder (plugins/vibe-engineering/skills/vibe-decision-journal in ash1794/vibe-engineering) into .claude/skills/vibe-decision-journal in your project. Claude Code loads it when a task matches its description.

How do I install Vibe Decision Journal in Codex?

Run `npx skills add ash1794/vibe-engineering --skill vibe-decision-journal -a codex`. Or copy the skill folder (plugins/vibe-engineering/skills/vibe-decision-journal in ash1794/vibe-engineering) into .agents/skills/vibe-decision-journal in your project. Codex loads it when a task matches its description.

Can I use Vibe Decision Journal 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 ash1794/vibe-engineering --skill vibe-decision-journal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vibe-decision-journal, .gemini/skills/vibe-decision-journal, .github/skills/vibe-decision-journal and .opencode/skills/vibe-decision-journal in your project.

What does Vibe Decision Journal need to run?

Going by SKILL.md and its folder, Vibe Decision Journal needs the command-line tools its instructions call (git).

Does Vibe Decision Journal access the network?

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

Is Vibe Decision Journal 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 Vibe Decision Journal use?

Vibe Decision Journal is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vibe Decision Journal use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vibe Decision Journal?

Skills that share tags, products or a category with Vibe Decision Journal: Find Similar Functions (millionco/react-doctor, 15k stars), Lead Enrichment (tech-leads-club/agent-skills, 7k stars), Monte Carlo Remediation (sickn33/agentic-awesome-skills, 47k stars) and Data Clean (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vibe Decision Journal?

ash1794 (a GitHub user) maintains it in ash1794/vibe-engineering, which has 163 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 7, 2026.

Source: ash1794/vibe-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.