PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Audits codebase for architectural friction, shallow modules; proposes RFCs.
Apache-2.0Auto-check: notes
Install Architecture Audit
$ npx skills add softspark/ai-toolkit --skill architecture-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install softspark/ai-toolkit architecture-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/architecture-audit .claude/skills/architecture-audit && rm -rf skills-srcUse ~/.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/
Install the "architecture-audit" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/architecture-audit into .claude/skills/architecture-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/softspark/ai-toolkit/tree/main/app/skills/architecture-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add softspark/ai-toolkit --skill architecture-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install softspark/ai-toolkit architecture-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/app/skills/architecture-audit .agents/skills/architecture-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "architecture-audit" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/architecture-audit into .agents/skills/architecture-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add softspark/ai-toolkit --skill architecture-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install softspark/ai-toolkit architecture-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/app/skills/architecture-audit .cursor/skills/architecture-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "architecture-audit" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/architecture-audit into .cursor/skills/architecture-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/softspark/ai-toolkit.git --path app/skills/architecture-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add softspark/ai-toolkit --skill architecture-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install softspark/ai-toolkit architecture-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/app/skills/architecture-audit .gemini/skills/architecture-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "architecture-audit" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/architecture-audit into .gemini/skills/architecture-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install softspark/ai-toolkit architecture-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add softspark/ai-toolkit --skill architecture-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/app/skills/architecture-audit .github/skills/architecture-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "architecture-audit" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/architecture-audit into .github/skills/architecture-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add softspark/ai-toolkit --skill architecture-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install softspark/ai-toolkit architecture-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/app/skills/architecture-audit .opencode/skills/architecture-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "architecture-audit" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/architecture-audit into .opencode/skills/architecture-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
architecture-audit- GitHub stars
- 179
- Token cost
- ~1.7k tokens
- SKILL.md length
- 841 words
- Files
- 1
- Skills in repo
- 112
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Audits codebase for architectural friction, shallow modules; proposes RFCs.
- Works in 5 steps: Organic Exploration → Present Candidates → Frame the Problem Space → …
- SKILL.md covers Usage, What This Command Does, Key Concept and Process, plus 11 more sections
- Calls gh
What it does
Architecture Audit is an agent skill from softspark/ai-toolkit. Audits codebase for architectural friction, shallow modules; proposes RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with GitHub. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.
Example prompts
- “Use the architecture-audit skill to audit codebase for architectural friction, shallow modules; proposes RFCs”
- “/architecture-audit”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash, Agent
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit d64db2b. 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:
ReadGrepGlobBashAgent
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
gh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, 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
Architecture Audit loads about 1.7k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 841 words of instructions outside code blocks.
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, Agent
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 softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 841 words, ~1,722 tokens.
Download SKILL.mdSave it as
.claude/skills/architecture-audit/SKILL.md (or your agent's skills folder).- name
- architecture-audit
- description
- Audits codebase for architectural friction, shallow modules; proposes RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling.
- allowed-tools
- Read, Grep, Glob, Bash, Agent
- user-invocable
- true
- effort
- high
- argument-hint
- [area to audit or 'full codebase']
Architecture Audit
$ARGUMENTS
Explore a codebase organically, surface architectural friction, and propose module-deepening refactors as GitHub issue RFCs.
Usage
/architecture-audit [area to audit or 'full codebase']What This Command Does
- Explores codebase organically — friction IS the signal
- Presents deepening candidates to user
- Frames problem space for chosen candidate
- Spawns 3+ parallel sub-agents for radically different interface designs
- Compares and recommends
- Files RFC as GitHub issue
Key Concept
A deep module (Ousterhout) has a small interface hiding a large implementation. Deep modules enhance testability, AI navigation, and enable boundary testing.
A shallow module has a large interface with thin implementation — avoid.
Process
1. Organic Exploration
Use Agent (subagent_type=Explore) to navigate the codebase naturally. Note friction:
- Where does understanding one concept require bouncing between many small files?
- Where are modules so shallow the interface is nearly as complex as the implementation?
- Where have pure functions been extracted just for testability but real bugs hide in how they're called?
- Where do tightly-coupled modules create integration risk in the seams?
- What is untested or hard to test?
2. Present Candidates
Numbered list. For each candidate show:
| Field | Content |
|---|---|
| Cluster | Which modules/concepts are involved |
| Why coupled | Shared types, call patterns, co-ownership |
| Dependency category | In-process, Local-substitutable, Ports & Adapters, or True external (see reference/) |
| Test impact | What existing tests would be replaced by boundary tests |
Do NOT propose interfaces yet. Ask: "Which would you like to explore?"
3. Frame the Problem Space
For the chosen candidate, write a user-facing explanation:
- Constraints any new interface would satisfy
- Dependencies it would rely on
- Rough illustrative code sketch (not a proposal — just grounding)
Show to user, then immediately proceed to step 4.
4. Design Multiple Interfaces
Spawn 3+ sub-agents in parallel via Agent tool. Each gets a different constraint:
| Agent | Constraint |
|---|---|
| Agent 1 | Minimize interface — 1-3 entry points max |
| Agent 2 | Maximize flexibility — many use cases and extension |
| Agent 3 | Optimize for most common caller — default case trivial |
| Agent 4 | Ports & adapters pattern (if cross-boundary) |
Each outputs: interface signature, usage example, what it hides, dependency strategy, trade-offs.
Present sequentially, compare in prose, give opinionated recommendation.
5. Create GitHub Issue RFC
Use gh issue create with template below. Don't ask for review.
Issue Template
<issue-template>Problem
Architectural friction:
- Which modules are shallow and tightly coupled
- Integration risk in the seams
- Why this makes the codebase harder to navigate/maintain
Proposed Interface
- Interface signature (types, methods, params)
- Usage example
- What complexity it hides
Dependency Strategy
- In-process: merged directly
- Local-substitutable: tested with [specific stand-in]
- Ports & adapters: port definition, production adapter, test adapter
- Mock: mock boundary for external services
Testing Strategy
- New boundary tests to write
- Old shallow tests to delete
- Test environment needs
Implementation Recommendations
Durable guidance NOT coupled to file paths:
- What the module should own
- What it should hide
- What it should expose
- How callers migrate
</issue-template>Dependency Categories
| Category | Description | Deepenable? |
|---|---|---|
| In-process | Pure computation, no I/O | Always |
| Local-substitutable | Has local test stand-ins (PGLite, in-memory FS) | If stand-in exists |
| Remote but owned | Your services across network (Ports & Adapters) | Via port injection |
| True external | Third-party (Stripe, Twilio) — mock at boundary | Via mock injection |
Show full SKILL.md (332 more words)Show less
Testing Principle
Replace, don't layer. Old unit tests on shallow modules are waste once boundary tests exist — delete them. Tests assert on observable outcomes through public interface, not internal state.
Rules
- MUST explore the codebase organically (Explore sub-agent) before proposing deepening targets — do not anchor on what you already know
- MUST present numbered candidates to the user and wait for selection before step 3 — auto-picking skips the product decision
- NEVER design interfaces in step 2; interface work only happens in step 4 after the problem space is framed
- CRITICAL: step 4 spawns parallel sub-agents with genuinely different constraints (minimize / maximize-flexibility / optimize-common / ports-adapters). Sequential variations of the same idea defeat the purpose.
- MANDATORY: deliverable is a GitHub issue RFC created via
gh issue create. Never open a PR from this skill.
Gotchas
- "Depth" is measured against actual call patterns, not the method count. A module exporting 20 functions where callers only use 2 is effectively 2-deep — the other 18 are dead interface, not richness.
- Shared TypeScript types and Python protocols count as coupling. A "just types" file imported by 30 modules creates a deep blast radius; deleting or renaming it is structurally significant even though no runtime code moves.
- Parallel sub-agents collapse into echo chambers when their constraints are not sharply different. Spell out the opposing tensions ("minimize interface" vs "maximize flexibility") — soft variations produce near-identical designs.
gh issue createwithout--bodyor--body-fileopens$EDITOR. In automated flows this hangs the skill indefinitely. Always pass the body explicitly.- Ports & Adapters introduces indirection that IDE "find references" and static analysis sometimes miss (dynamic dispatch via interface). Count on broken tooling during the transition period and compensate with runtime smoke tests.
When NOT to Use
- For executing a known refactor plan — use
/refactor(direct edits) or/refactor-plan(incremental) - For designing a single module's interface from scratch — use
/design-an-interface - For deciding between 2-3 named architectural options — use
/architecture-decision - For code-quality metrics (complexity, duplication, coverage) — use
/analyze - For understanding a codebase without proposing changes — use
/explore
© softspark, Apache-2.0. 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 app/skills/architecture-audit of softspark/ai-toolkit.
Open the folder on GitHubat commit d64db2b
Compare with similar skills
Architecture Audit 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Architecture Audit this skillsoftspark/ai-toolkit | 179 | — | ~1.7k | Automated safety check: Notes | Apache-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Diagnosing Superpowers Sessionsobra/superpowers | 296k | 3 repos | ~1.7k | Automated safety check: Pass | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 83k | 5 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Greplooponyx-dot-app/onyx | 32k | 4 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Update V8 Versionopeninterpreter/openinterpreter | 69k | 2 repos | ~845 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Diagnosing Superpowers Sessions
obra/superpowers
Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.
GitHub Deep Research
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
Update V8 Version
openinterpreter/openinterpreter
Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.
Last30days
mvanhorn/last30days-skill
Research what people actually say about any topic in the last 30 days.
More from softspark/ai-toolkit
All 112 skills in this repoPrepare Test Env
softspark/ai-toolkit
Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.
A11y Validate
softspark/ai-toolkit
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.
Analyze
softspark/ai-toolkit
Analyzes code quality, complexity, patterns across codebase.
Autonomous Dev
softspark/ai-toolkit
Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.
Brand Voice
softspark/ai-toolkit
Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.
CI
softspark/ai-toolkit
Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).
Related
Works with
Questions about Architecture Audit
What does Architecture Audit do?
Audits codebase for architectural friction, shallow modules; proposes RFCs. Architecture Audit is an agent skill from softspark/ai-toolkit. Audits codebase for architectural friction, shallow modules; proposes RFCs.
How do I install Architecture Audit in Claude Code?
Run `npx skills add softspark/ai-toolkit --skill architecture-audit -a claude-code`. Or copy the skill folder (app/skills/architecture-audit in softspark/ai-toolkit) into .claude/skills/architecture-audit in your project. Claude Code loads it when a task matches its description.
How do I install Architecture Audit in Codex?
Run `npx skills add softspark/ai-toolkit --skill architecture-audit -a codex`. Or copy the skill folder (app/skills/architecture-audit in softspark/ai-toolkit) into .agents/skills/architecture-audit in your project. Codex loads it when a task matches its description.
Can I use Architecture Audit 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 softspark/ai-toolkit --skill architecture-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-audit, .gemini/skills/architecture-audit, .github/skills/architecture-audit and .opencode/skills/architecture-audit in your project.
What does Architecture Audit need to run?
Going by SKILL.md and its folder, Architecture Audit needs the command-line tools its instructions call (gh). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash, Agent.
Does Architecture Audit access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Architecture Audit 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 Architecture Audit use?
Architecture Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Architecture Audit use?
About 1.7k tokens (SKILL.md is roughly 6.9k 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 Architecture Audit?
Skills that share tags, products or a category with Architecture Audit: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 296k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars) and Greploop (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Architecture Audit?
softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.
Source: softspark/ai-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.