Architect Build Specs
jsmastery-pro/skills
Runs a structured design conversation on a feature, tech stack or enhancement, recommends an answer and records it as a build spec in docs/specs.
Reviews a technical proposal before implementation through an independent subagent, returning findings, open questions and a verdict without rewriting it.
Install Architecture Review
$ npx skills add owainlewis/blueprint --skill architecture-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install owainlewis/blueprint architecture-review --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/owainlewis/blueprint.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/architecture-review .claude/skills/architecture-review && 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-review" agent skill from https://github.com/owainlewis/blueprint/tree/main/skills/architecture-review into .claude/skills/architecture-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-review", 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/owainlewis/blueprint/tree/main/skills/architecture-reviewType 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 owainlewis/blueprint --skill architecture-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install owainlewis/blueprint architecture-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/owainlewis/blueprint.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/architecture-review .agents/skills/architecture-review && 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-review" agent skill from https://github.com/owainlewis/blueprint/tree/main/skills/architecture-review into .agents/skills/architecture-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-review", 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 owainlewis/blueprint --skill architecture-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install owainlewis/blueprint architecture-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/owainlewis/blueprint.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/architecture-review .cursor/skills/architecture-review && 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-review" agent skill from https://github.com/owainlewis/blueprint/tree/main/skills/architecture-review into .cursor/skills/architecture-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-review", 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/owainlewis/blueprint.git --path skills/architecture-review--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 owainlewis/blueprint --skill architecture-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install owainlewis/blueprint architecture-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/owainlewis/blueprint.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/architecture-review .gemini/skills/architecture-review && 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-review" agent skill from https://github.com/owainlewis/blueprint/tree/main/skills/architecture-review into .gemini/skills/architecture-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-review", 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 owainlewis/blueprint architecture-reviewInstalls 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 owainlewis/blueprint --skill architecture-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/owainlewis/blueprint.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/architecture-review .github/skills/architecture-review && 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-review" agent skill from https://github.com/owainlewis/blueprint/tree/main/skills/architecture-review into .github/skills/architecture-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-review", 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 owainlewis/blueprint --skill architecture-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install owainlewis/blueprint architecture-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/owainlewis/blueprint.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/architecture-review .opencode/skills/architecture-review && 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-review" agent skill from https://github.com/owainlewis/blueprint/tree/main/skills/architecture-review into .opencode/skills/architecture-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-review", 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-review- GitHub stars
- 412
- Token cost
- ~1.2k tokens
- SKILL.md length
- 614 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reviews a technical proposal before implementation through an independent subagent, returning findings, open questions and a verdict without rewriting it.
- Works in 6 steps: Read the goal, proposal, requirements,… → State the problem, affected user,… → Trace one real case from input to… → …
- Reviewing an RFC or ADR before the team commits to it
- SKILL.md covers Process, Review focus, Material questions and Findings, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
RFCs, ADRs, feature specs, system designs and issues that describe a change are all fair targets, as long as no code has been written yet. The skill asks for one fresh subagent that did not write the proposal, handed the full context and told to work directly and stay read-only. If no fresh subagent is available it stops and reports that independent review is blocked, continuing only when you accept a documented self-review.
The process reads the goal, proposal, requirements and the relevant current code, tests, schemas and configuration, treating claims about the existing system as unverified until evidence backs them. It then states the problem, traces one real case from input to outcome, looks for a simpler design that reaches the same result, and surfaces open questions. The review focus covers requirements fit, ownership and interfaces, migration and rollback, partial failure and retries, scale and cost, and identity, authorization and sensitive data. It does not rewrite the proposal, plan the work or review implementation code.
When your agent uses it
- Reviewing an RFC or ADR before the team commits to it
- Checking a feature spec for ambiguity and missing failure handling
- Getting an independent second opinion on a system design
Example prompts
- “Review the RFC in docs/rfcs/queue-migration.md before we start building.”
- “Architecture-review this ADR for the new caching layer.”
- “Is the design in this GitHub issue sound enough to start implementing?”
Requirements
- An agent host that can start a fresh subagent
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read the goal, proposal, requirements, intended architecture, repository instructions, relevant current code,
- State the problem, affected user, intended outcome, success measure, scope,
- Trace one real case from input to observable outcome. Include ownership,
- Challenge the chosen design with the review focus below. Look for a simpler
- Surface material open questions. Recommend an answer when evidence supports
- Return findings, open questions, a short assessment, and one verdict.
What it can do on your machine
Read from SKILL.md and the folder at commit 1d74745. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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 Review loads about 1.2k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 614 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 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 owainlewis/blueprint at commit 1d74745, republished under its MIT licence (© owainlewis). 614 words, ~1,226 tokens.
Download SKILL.mdSave it as
.claude/skills/architecture-review/SKILL.md (or your agent's skills folder).- name
- architecture-review
- description
- Reviews a technical proposal before implementation. Use for system architectures, feature specs, RFCs, ADRs, and issues that define how a system change should work. Finds material ambiguity and flaws in correctness, scalability, performance, security, operations, and proof.
- user-invocable
- true
- argument-hint
- [architecture, spec, RFC, ADR, or issue]
Architecture review
Find choices that could make a technical proposal wrong, unsafe, or impossible to prove. Review the proposed behavior and tradeoffs, not the document's size or format.
Use one fresh subagent that did not write the proposal. Give the reviewer the complete context. Tell the reviewer to work directly without delegating. If you are that reviewer, review directly. Stay read-only.
If fresh subagents are unavailable, stop and report that independent review is blocked. Continue only if the user explicitly accepts a documented self-review.
Process
- Read the goal, proposal, requirements, intended architecture, repository instructions, relevant current code, tests, schemas, configuration, and linked material. Treat claims about the current system as unverified until code, tests, schemas, configuration, infrastructure, or relevant runtime evidence supports them.
- State the problem, affected user, intended outcome, success measure, scope, constraints, and main tradeoff. Report any that the proposal leaves unclear.
- Trace one real case from input to observable outcome. Include ownership, validation, state changes, side effects, response timing, failure, retry, cleanup, and what the user sees where they matter.
- Challenge the chosen design with the review focus below. Look for a simpler choice that reaches the same outcome and proof with less state, coupling, duplication, or operational work.
- Surface material open questions. Recommend an answer when evidence supports one. Do not invent questions that cannot change the design.
- Return findings, open questions, a short assessment, and one verdict. Do not rewrite the proposal, plan the work, review implementation code, or implement changes.
Review focus
- Check fit with requirements and accepted architecture. Verify current-state claims without requiring a new system to have code.
- Check ownership, boundaries, interfaces, data, compatibility, migration, rollout, and rollback.
- Trace partial failure, retry, cancellation, concurrency, startup, shutdown, and recovery where they affect the proposal.
- Check claimed scale, limited resources, latency, throughput, storage, cost, dependency failure, and operator recovery only where they can change the choice.
- Check identity, authorization, untrusted input, credentials, destructive authority, and sensitive data handling.
- Require observable acceptance criteria and proof for important rules and failure paths. Do not let implementation invent user-visible behavior, interfaces, data rules, security policy, or failure behavior.
Show full SKILL.md (257 more words)Show less
Material questions
Report an open question only when two capable implementations could answer it differently in a way that affects users, data, interfaces, security, scale, performance, operations, cost, compatibility, or proof.
- Blocking: implementation should not start without the answer.
- Important: the proposal should record the answer, but the reviewer can recommend a safe default from available evidence.
Omit questions that are stylistic, safely local to implementation, outside the stated scope, or speculative beyond the scale the proposal claims to support.
Findings
Report only flaws that can change the design or its safety:
- Blocker: the choice is unsafe, contradicts the goal or current system, or cannot recover from an important failure.
- Important: the proposal permits materially different implementations or leaves a meaningful risk in behavior, scale, performance, security, operations, compatibility, or proof.
For each finding or open question include its location, concrete failure or ambiguity, impact, evidence, and the smallest correction or recommended answer. Report unclear wording when it prevents a new teammate from explaining, evaluating, or implementing the design. Omit other writing preferences.
Use plain words. State the exact condition, failure, and effect. Do not hide an
unknown behind vague language such as may have issues or could be risky.
Verdict
Approve: no blocker or important findings or open questions remain.Request changes: the proposal has a fixable blocker or important finding or open question.Blocked: the review lacks required context, repository evidence, specialist coverage, or an independent reviewer.
State what remains unverified. Do not approve because the document is detailed or because every template section exists.
© owainlewis, 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/architecture-review of owainlewis/blueprint.
Open the folder on GitHubat commit 1d74745
Compare with similar skills
Architecture Review 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 Review this skillowainlewis/blueprint | 412 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Architect Build Specsjsmastery-pro/skills | 1.5k | — | ~7k | Automated safety check: Notes | MIT | |
| Create Vibe Featuremistralai/mistral-vibe | 5.1k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Ontology-Driven System Buildersharptoolbox/ontology-driven-dev | 433 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Task Workflowikarenkov/Modo | 343 | — | ~2.4k | Automated safety check: Pass | None | |
| Architecture Decisions and ADRsfirst-fluke/oh-my-agent | 1.3k | — | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
- Official
Create Vibe Feature
mistralai/mistral-vibe
Guides feature work in the Mistral Vibe Python CLI so each change lands in the right module and matches the project's architecture decision records.
Ontology-Driven System Builder
sharptoolbox/ontology-driven-dev
Runs a three-step pipeline, requirement exploration, seven-model ontology YAML, then app build, on a Flask, SQLite, and React stack with sign-off gates.
Task Workflow
ikarenkov/Modo
Spec-driven workflow for non-trivial work. An agent skill from ikarenkov/Modo.
Architecture Decisions and ADRs
first-fluke/oh-my-agent
Evaluates system boundaries and tradeoffs and writes architecture recommendations, option comparisons or ADRs, with a Mermaid diagram when structure changes.
MVP Technical Design
KhazP/vibe-coding-prompt-template
Writes an MVP technical design from agreed requirements, covering architecture, data ownership, integration contracts, deployment and tradeoffs, then hands off to the next stage.
More from owainlewis/blueprint
All 11 skills in this repoMarkdown PRD to HTML Renderer
owainlewis/blueprint
Converts a complete Markdown PRD or technical design into one verified, static HTML reading page without changing what it says.
Codex Issue Coordinator
owainlewis/blueprint
Lets one Codex thread run a batch of GitHub issues through separate worker threads, each with its own worktree, branch, tested pull request and gated merge.
Vertical-Slice Task Planner
owainlewis/blueprint
Breaks a reviewed spec into ordered, vertical-slice tasks that each fit one agent run and one pull request, grouped into milestones when useful.
Independent Implementation Review
owainlewis/blueprint
Has a separate agent review a code change without editing it, checking behavior, security, regressions, complexity, tests and docs before merge.
Architecture
owainlewis/blueprint
Designs and maintains root ARCHITECTURE.md for the intended system, including its data model and shared technical rules.
Product Requirements Document
owainlewis/blueprint
Creates or updates a long-running REQUIREMENTS.md that defines a system's users, outcomes, capabilities, business rules, scope and acceptance conditions.
Related
Categories
Questions about Architecture Review
What does Architecture Review do?
Reviews a technical proposal before implementation through an independent subagent, returning findings, open questions and a verdict without rewriting it. RFCs, ADRs, feature specs, system designs and issues that describe a change are all fair targets, as long as no code has been written yet. The skill asks for one fresh subagent that did not write the proposal, handed the full context and told to work directly and stay read-only.
When should I use Architecture Review?
Architecture Review fits situations like: reviewing an RFC or ADR before the team commits to it; checking a feature spec for ambiguity and missing failure handling; getting an independent second opinion on a system design.
How do I install Architecture Review in Claude Code?
Run `npx skills add owainlewis/blueprint --skill architecture-review -a claude-code`. Or copy the skill folder (skills/architecture-review in owainlewis/blueprint) into .claude/skills/architecture-review in your project. Claude Code loads it when a task matches its description.
How do I install Architecture Review in Codex?
Run `npx skills add owainlewis/blueprint --skill architecture-review -a codex`. Or copy the skill folder (skills/architecture-review in owainlewis/blueprint) into .agents/skills/architecture-review in your project. Codex loads it when a task matches its description.
Can I use Architecture Review 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 owainlewis/blueprint --skill architecture-review -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-review, .gemini/skills/architecture-review, .github/skills/architecture-review and .opencode/skills/architecture-review in your project.
What does Architecture Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Architecture Review is instructions for the agent only. Our summary lists: An agent host that can start a fresh subagent.
Does Architecture Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Architecture Review 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 Architecture Review use?
Architecture Review 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 Architecture Review use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Review?
Skills that share tags, products or a category with Architecture Review: Architect Build Specs (jsmastery-pro/skills, 1.5k stars), Create Vibe Feature (mistralai/mistral-vibe, 5.1k stars), Ontology-Driven System Builder (sharptoolbox/ontology-driven-dev, 433 stars) and Task Workflow (ikarenkov/Modo, 343 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Architecture Review?
owainlewis (a GitHub user) maintains it in owainlewis/blueprint, which has 412 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 10, 2026.
Source: owainlewis/blueprint on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.