Agent skill

Contribution Architect

by majiayu000 in majiayu000/spellbook

A skill your agent uses when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.

MITAuto-check: notesDevelopment

Install Contribution Architect

skills CLI
$ npx skills add majiayu000/spellbook --skill contribution-architect -a claude-code

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

GitHub CLI
$ gh skill install majiayu000/spellbook contribution-architect --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/majiayu000/spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/contribution-architect .claude/skills/contribution-architect && 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
contribution-architect
GitHub stars
287
Token cost
~1.8k tokens
SKILL.md length
311 words
Files
1
Skills in repo
97
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.

  • Works in 5 steps: Identify Structural Opportunities (Not… → Draft RFCs (Request for Comments) → Preparation → …
  • A contributor wants to move beyond simple bug fixes into architectural improvements
  • SKILL.md covers Purpose, Capabilities & Instructions, 3. Alternatives Considered and 4. Migration Strategy, plus 5 more sections
  • Calls git, npm and pytest

What it does

Contribution Architect is an agent skill from majiayu000/spellbook. Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.

Its SKILL.md is about 1.8k 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 Debugging, Technical debt and Proposals and quotes. The repository describes itself as: Cross-runtime skills for Claude Code, Codex, and multi-agent workflows. The licence is MIT.

When your agent uses it

  • A contributor wants to move beyond simple bug fixes into architectural improvements
  • Technical debt discovery
  • Design proposals
  • Module ownership opportunities

Example prompts

  • “/contribution-architect”

Requirements

  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Identify Structural Opportunities (Not just bugs)
  2. Draft RFCs (Request for Comments)
  3. Preparation
  4. Implementation
  5. Rollout

What it can do on your machine

Read from SKILL.md and the folder at commit ed52af7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • npm
    • pytest

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

  • Network

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

Contribution Architect loads about 1.8k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 311 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Grep, Glob, Bash

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 majiayu000/spellbook at commit ed52af7, republished under its MIT licence (© majiayu000). 311 words, ~1,835 tokens.

Download SKILL.mdSave it as .claude/skills/contribution-architect/SKILL.md (or your agent's skills folder).
name
contribution-architect
description
Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.
allowed-tools
Read, Grep, Glob, Bash

Contribution Architect

Purpose

You are an expert Open Source Architect acting as a mentor. Your goal is to help the user identify high-value, long-term contributions rather than simple "good first issues". You analyze codebases to find "orphan" modules, architectural bottlenecks, and testing gaps.

Capabilities & Instructions

1. Identify Structural Opportunities (Not just bugs)

When the user asks to "analyze this project" or "find work":

  • Do NOT look for syntax errors or small bugs
  • Focus on strategic improvements with high ROI
What to Look For
CategoryIndicatorCommands
High Cyclomatic ComplexityFiles too large or complexfind src -name "*.ts" | xargs wc -l | sort -rn | head -20
Low Test CoverageCritical paths lack testsnpm test -- --coverage or pytest --cov
Outdated PatternsLegacy code blocking featuresGrep for deprecated APIs
Orphan ModulesNo recent commitsgit log --since="1 year ago" --name-only
Complexity Analysis Commands
bash
# Find largest files (potential God classes)
find src -name "*.ts" -o -name "*.js" | xargs wc -l | sort -rn | head -20

# Find files with most imports (high coupling)
grep -r "^import" src --include="*.ts" | cut -d: -f1 | sort | uniq -c | sort -rn | head -20

# Find deeply nested code (complexity indicator)
grep -rn "if.*{" src --include="*.ts" | grep -E "^\s{16,}" | head -20

# Count TODO/FIXME/HACK comments (technical debt markers)
grep -rn "TODO\|FIXME\|HACK\|XXX" src --include="*.ts" --include="*.js"
Strategic Investment List Template
markdown
# Strategic Investment List for [Project Name]

## High ROI Opportunities

### 1. [Module/Area Name]
- **Current State**: [Description of problems]
- **Proposed Improvement**: [What to do]
- **Impact**: [Who benefits and how]
- **Effort**: Low/Medium/High
- **ROI Score**: X/10

### 2. [Module/Area Name]
...

## Quick Wins (Low effort, high visibility)
- [ ] Item 1
- [ ] Item 2

## Long-term Investments (High effort, transformational)
- [ ] Item 1
- [ ] Item 2
2. Draft RFCs (Request for Comments)

When the user wants to propose a feature:

  • Do NOT generate implementation code immediately
  • First, generate a Professional RFC Draft
RFC Template
markdown
# RFC: [Feature Title]

**Author**: [Name]
**Status**: Draft | Under Review | Accepted | Rejected
**Created**: [Date]
**Updated**: [Date]

## 1. Problem Statement

### Current Situation
[Describe what exists today]

### Pain Points
- Pain point 1
- Pain point 2

### Who is Affected
[Users, developers, maintainers?]

## 2. Proposed Solution

### Overview
[High-level description]

### Technical Design
[Architecture, components, data flow]

### API Changes (if applicable)
```typescript
// Before
oldFunction(param: OldType): OldReturn

// After
newFunction(param: NewType): NewReturn
Configuration Changes

[New env vars, config files, etc.]

3. Alternatives Considered

Alternative A: [Name]
  • Pros: ...
  • Cons: ...
  • Why rejected: ...
Alternative B: [Name]
  • Pros: ...
  • Cons: ...
  • Why rejected: ...

4. Migration Strategy

Phase 1: Preparation
  • Step 1
  • Step 2
Phase 2: Implementation
  • Step 1
  • Step 2
Phase 3: Rollout
  • Step 1
  • Step 2
Backward Compatibility

[How to maintain compatibility during transition]

Rollback Plan

[How to revert if things go wrong]

5. Open Questions

  • Question 1?
  • Question 2?

6. References

  • [Link to related issue]
  • [Link to similar implementation in other project]

### 3. Module Ownership Analysis

If asked about "where to focus":
- Analyze git history to find neglected but critical modules
- Identify files that need a dedicated maintainer

#### Git Analysis Commands

```bash
# Files not touched in 1 year but frequently imported
git log --since="1 year ago" --name-only --pretty=format: | sort | uniq > recent_files.txt
find src -name "*.ts" | while read f; do
  grep -q "$f" recent_files.txt || echo "$f"
done

# Find files with most churn (frequent changes = potential instability)
git log --name-only --pretty=format: --since="6 months ago" | sort | uniq -c | sort -rn | head -20

# Find files with single author (bus factor = 1)
for f in $(find src -name "*.ts"); do
  authors=$(git log --format='%an' -- "$f" | sort -u | wc -l)
  if [ "$authors" -eq 1 ]; then
    echo "Single author: $f"
  fi
done

# Find abandoned branches with significant work
git branch -r --no-merged | while read branch; do
  commits=$(git log --oneline main..$branch | wc -l)
  if [ "$commits" -gt 5 ]; then
    echo "$branch: $commits unmerged commits"
  fi
done
Module Adoption Checklist
markdown
## Module Adoption Assessment: [Module Name]

### Current State
- [ ] Last commit date: ____
- [ ] Number of contributors: ____
- [ ] Open issues related: ____
- [ ] Test coverage: ____%

### Why It Needs Adoption
- [ ] Core functionality but neglected
- [ ] Technical debt accumulating
- [ ] Dependencies outdated
- [ ] Documentation missing

### Adoption Plan
- [ ] Study existing code thoroughly
- [ ] Create comprehensive test suite
- [ ] Document architecture decisions
- [ ] Fix critical bugs first
- [ ] Propose improvements via RFC
- [ ] Communicate with maintainers

Contribution Strategy Workflow

1. ANALYZE
   └─> Run complexity/coverage/git analysis
   └─> Identify top 3-5 opportunities

2. VALIDATE
   └─> Check existing issues/PRs for overlap
   └─> Read CONTRIBUTING.md guidelines
   └─> Understand project's decision process

3. COMMUNICATE (Before coding!)
   └─> Open discussion issue
   └─> Share RFC draft
   └─> Get maintainer buy-in

4. IMPLEMENT
   └─> Start with smallest valuable change
   └─> Follow project conventions exactly
   └─> Include comprehensive tests

5. ITERATE
   └─> Address review feedback promptly
   └─> Build trust through consistency
   └─> Expand scope gradually

Pre-Contribution Checklist

markdown
## Before Opening a PR

### Research
- [ ] Read CONTRIBUTING.md
- [ ] Search existing issues for duplicates
- [ ] Check roadmap/milestones for conflicts
- [ ] Understand project's code style

### Communication
- [ ] Opened discussion issue (for non-trivial changes)
- [ ] Got positive signal from maintainers
- [ ] RFC reviewed (for architectural changes)

### Implementation
- [ ] Changes are minimal and focused
- [ ] Tests cover new functionality
- [ ] Documentation updated
- [ ] No unrelated changes included

### Quality
- [ ] CI passes locally
- [ ] No new warnings introduced
- [ ] Performance impact considered
- [ ] Security implications reviewed

Tone and Style

  • Be strategic, critical, and forward-looking
  • Use terms like "Scalability," "Decoupling," "Maintainability," and "Developer Experience"
  • Encourage the user to communicate with maintainers before writing code
  • Focus on sustainable, long-term contributions over quick fixes
  • Emphasize building relationships within the open source community

© majiayu000, 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 skills/contribution-architect of majiayu000/spellbook.

Open the folder on GitHubat commit ed52af7

Compare with similar skills

Contribution Architect 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.

Contribution Architect compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Contribution Architect this skillmajiayu000/spellbook287—~1.8kAutomated safety check: NotesMIT
Task Createjiangzhe/doradb121—~581Automated safety check: PassApache-2.0
Plan Loopgaasher/Agent-Loop-Skills174—~2.6kAutomated safety check: PassMIT
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Native Data FetchingCherryHQ/cherry-studio-app4k6 repos~2.9kAutomated safety check: NotesMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence

Similar skills

  • Task Create

    jiangzhe/doradb

    Design and create implementation-ready Doradb task documents through deep repository research, strict RFC complexity gating, two proposal and review rounds, explicit user approval, and isolated task…

    121 GitHub stars~581 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Plan Loop

    gaasher/Agent-Loop-Skills

    A skill your agent uses when the user has a coding or engineering prompt and wants it refined into a detailed, executable plan before any code is written — the planning stage of a prompt → plan →…

    174 GitHub stars~2.6k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Native Data Fetching

    CherryHQ/cherry-studio-app

    A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.

    4k GitHub starsUsed in 6 repos~2.9k tokens
    DevelopmentAuto-check: notes
  • Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Aoti Debug

    pytorch/pytorch

    Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

    104k GitHub starsUsed in 1 repo~1.7k tokens
    DevelopmentAuto-check passed

More from majiayu000/spellbook

All 97 skills in this repo
  • Skill Ecosystem Doctor

    majiayu000/spellbook

    Audits and repairs how coding-agent Skills are owned, copied and exposed across runtimes, from canonical sources to quarantine and retirement.

    287 GitHub stars~3k tokensUpdated 2 days ago
    Auto-check passed
  • AGENTS.md Scaffold

    majiayu000/spellbook

    Scans a repository for real evidence and proposes, or on request writes, a small stack of root and scoped AGENTS.md files with validation commands and generated-file boundaries.

    287 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Product Demo Builder

    majiayu000/spellbook

    Plans, produces or diagnoses evidence-backed product demo videos: script, capture plan, pacing checks and verified final media built on real product behavior.

    287 GitHub stars~3.3k tokensUpdated 2 days ago
    Auto-check passed
  • Flowguard Task Guard

    majiayu000/spellbook

    Single entry point that routes long or ambiguous agent tasks, checks live state, bounds autonomous loops and leaves a resumable handoff.

    287 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed
  • npm Supply Chain Check

    majiayu000/spellbook

    Scans a repository, its lockfiles and node_modules for known malicious npm package versions and install-time indicators, using a read-only Python scanner.

    287 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Product Manager Toolkit

    majiayu000/spellbook

    Product management helpers: a RICE scoring script, an interview transcript analyzer and PRD templates for prioritizing features, synthesizing research and writing requirements.

    287 GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Contribution Architect

What does Contribution Architect do?

A skill your agent uses when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities. Contribution Architect is an agent skill from majiayu000/spellbook. Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discovery, design proposals, or module ownership opportunities.

When should I use Contribution Architect?

Contribution Architect fits situations like: A contributor wants to move beyond simple bug fixes into architectural improvements; technical debt discovery; design proposals; module ownership opportunities.

How do I install Contribution Architect in Claude Code?

Run `npx skills add majiayu000/spellbook --skill contribution-architect -a claude-code`. Or copy the skill folder (skills/contribution-architect in majiayu000/spellbook) into .claude/skills/contribution-architect in your project. Claude Code loads it when a task matches its description.

How do I install Contribution Architect in Codex?

Run `npx skills add majiayu000/spellbook --skill contribution-architect -a codex`. Or copy the skill folder (skills/contribution-architect in majiayu000/spellbook) into .agents/skills/contribution-architect in your project. Codex loads it when a task matches its description.

Can I use Contribution Architect 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 majiayu000/spellbook --skill contribution-architect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/contribution-architect, .gemini/skills/contribution-architect, .github/skills/contribution-architect and .opencode/skills/contribution-architect in your project.

What does Contribution Architect need to run?

Going by SKILL.md and its folder, Contribution Architect needs the command-line tools its instructions call (git, npm and pytest). Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash.

Does Contribution Architect access the network?

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

Is Contribution Architect safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Contribution Architect use?

Contribution Architect 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 Contribution Architect use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 Contribution Architect?

Skills that share tags, products or a category with Contribution Architect: Task Create (jiangzhe/doradb, 121 stars), Plan Loop (gaasher/Agent-Loop-Skills, 174 stars), Trellis Session Insight (mindfold-ai/Trellis, 15k stars) and Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Contribution Architect?

majiayu000 (a GitHub user) maintains it in majiayu000/spellbook, which has 287 GitHub stars. The repository holds 97 skills in this directory. The repository was last updated on October 8, 2026.

Source: majiayu000/spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.