Agentbro Release
shirenchuang/agentbro
A skill your agent uses when releasing AgentBro from this repository: merging dev/main, bumping versions, updating release notes, tagging, pushing, monitoring GitHub Actions, Homebrew cask…
A skill your agent uses for GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro.
$ npx skills add oaslananka/kicad-mcp-pro --skill code-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install oaslananka/kicad-mcp-pro code-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/oaslananka/kicad-mcp-pro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/code-review .claude/skills/code-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 "code-review" agent skill from https://github.com/oaslananka/kicad-mcp-pro/tree/main/.github/skills/code-review into .claude/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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/oaslananka/kicad-mcp-pro/tree/main/.github/skills/code-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 oaslananka/kicad-mcp-pro --skill code-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install oaslananka/kicad-mcp-pro code-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/code-review .agents/skills/code-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 "code-review" agent skill from https://github.com/oaslananka/kicad-mcp-pro/tree/main/.github/skills/code-review into .agents/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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 oaslananka/kicad-mcp-pro --skill code-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install oaslananka/kicad-mcp-pro code-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/code-review .cursor/skills/code-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 "code-review" agent skill from https://github.com/oaslananka/kicad-mcp-pro/tree/main/.github/skills/code-review into .cursor/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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/oaslananka/kicad-mcp-pro.git --path .github/skills/code-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 oaslananka/kicad-mcp-pro --skill code-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install oaslananka/kicad-mcp-pro code-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/code-review .gemini/skills/code-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 "code-review" agent skill from https://github.com/oaslananka/kicad-mcp-pro/tree/main/.github/skills/code-review into .gemini/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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 oaslananka/kicad-mcp-pro code-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 oaslananka/kicad-mcp-pro --skill code-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/code-review .github/skills/code-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 "code-review" agent skill from https://github.com/oaslananka/kicad-mcp-pro/tree/main/.github/skills/code-review into .github/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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 oaslananka/kicad-mcp-pro --skill code-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 oaslananka/kicad-mcp-pro code-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/code-review .opencode/skills/code-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 "code-review" agent skill from https://github.com/oaslananka/kicad-mcp-pro/tree/main/.github/skills/code-review into .opencode/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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.
code-reviewA skill your agent uses for GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro.
Code Review is an agent skill from oaslananka/kicad-mcp-pro. Use this skill for GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro. Review Python MCP server changes, KiCad adapter and tool-contract changes, tests, npm/package wrappers, Tauri/Rust desktop code, GitHub Actions, security controls, documentation, generated metadata, and compatibility/release surfaces. Use it whenever reviewing a PR or diff in this repository, especially changes under src/, tests/, packages/, src-tauri/, .github/workflows/, or public MCP metadata/configuration.
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: GitHub Copilot code review for oaslananka/kicad-mcp-pro. Use GitHub MCP context when available. KiCad MCP Pro tools are optional and must remain read-only…
It sits in Development, covering MCP servers, Code review and Pull requests. It works with Model Context Protocol, GitHub Actions, Python and Tauri. The repository describes itself as: MCP server for KiCad, connecting AI agents to schematic and PCB workflows, ERC/DRC validation, DFM checks, BOM analysis, and manufacturing preparation—with controlled edits and… The licence is MIT.
11 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c7a464c. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
GitHub Copilot code review for oaslananka/kicad-mcp-pro. Use GitHub MCP context when available. KiCad MCP Pro tools are optional and must remain read-only during review.
From compatibility in the SKILL.md frontmatter.
Code Review loads about 3.9k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 1,749 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.
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.
The full file from oaslananka/kicad-mcp-pro at commit c7a464c, republished under its MIT licence (© oaslananka). 1,749 words, ~3,870 tokens.
.claude/skills/code-review/SKILL.md (or your agent's skills folder).Review pull requests for correctness, security, contract stability, compatibility, test coverage, and release safety. Prefer a small number of high-confidence, actionable findings over broad style feedback.
KiCad MCP Pro is a production MCP server that drives real KiCad projects. Treat unsafe mutations, incorrect tool contracts, path/subprocess mistakes, protocol regressions, and misleading engineering verdicts as high-risk.
Before writing findings:
ARCHITECTURE.mdCONTRIBUTING.mdSECURITY.mddocs/development/coding-standards.mddocs/development/testing-policy.mddocs/security/threat-model.md.github/PULL_REQUEST_TEMPLATE.mdUse GitHub MCP tools when they provide concrete review evidence, especially for linked issues, PR intent, CI/check state, or failed workflow details. Do not browse unrelated repository history just to increase context.
When changes affect the dashboard or desktop/web UI and the application can be run in the review environment, use Playwright MCP for focused user-visible verification.
Relevant areas include:
src/kicad_mcp/web/src-tauri/frontend/Do not report a browser regression unless you have code evidence or observed behavior. Lack of a runnable browser environment is not itself a defect.
If a KiCad MCP Pro server is configured in repository Copilot settings and the PR
changes KiCad-facing behavior, .kicad_* fixtures, validation logic, or project
inspection behavior, use it only when it adds concrete evidence.
Prefer the bounded read-only/default review surface and inspection/validation tools such as:
kicad_get_project_infokicad_get_versionproject_quality_gateschematic_quality_gatepcb_quality_gaterun_ercrun_drcpcb_get_board_summarysch_get_symbolsDuring code review, do not invoke write, destructive, manufacturing, export, or mutation tools. Never change a user's board or schematic as part of review.
KiCad MCP Pro has a five-layer design. Preserve the boundaries described in
ARCHITECTURE.md.
Flag changes that bypass the KiCad adapter seam or spread KiCad-version fragility into pure domain code.
KiCad-facing behavior belongs behind the established seams, including:
src/kicad_mcp/kicad/src/kicad_mcp/connection.pysrc/kicad_mcp/ipc/src/kicad_mcp/discovery.pyPure deterministic logic should remain testable without KiCad and should not import KiCad-specific runtime internals unnecessarily.
For tool registration and validation composition:
register() and _register_* helpers focused on wiring;The server must not invent board, schematic, DRC/ERC, manufacturing, or KiCad state. Behavior should be based on real KiCad engines, real project files, or explicitly documented deterministic/heuristic calculations.
If a calculation is approximate, heuristic, partial, or first-pass, ensure the API, docstring, docs, and verdict communicate that limitation. Do not allow code or docs to present first-order estimates as formal engineering sign-off.
Treat the MCP surface as a public compatibility contract.
When a tool is added, removed, renamed, reclassified, or its schema/behavior changes, check the relevant contract surfaces:
TOOL_CATEGORIES and profile membership in src/kicad_mcp/tools/router.py;src/kicad_mcp/tools/metadata.py;Flag any change that silently exposes mutating or destructive behavior through a read-only/default review surface.
Preserve stable error behavior. Agent-visible failures should use the repository's typed error model and stable error codes rather than leaking raw implementation exceptions or ambiguous strings.
For transport/protocol changes, review:
stdio and Streamable HTTP behavior;Security findings take priority over style or convenience.
Flag:
shell=True;os.system, os.popen, or equivalent shell execution in production paths;KiCad CLI calls should use discrete argv elements with shell=False.
Treat MCP/tool arguments, project paths, filenames, output paths, and imported artifact names as attacker-controlled.
Check for:
.. traversal;Security-sensitive filesystem/subprocess changes need negative tests for hostile inputs and failure paths.
For Streamable HTTP, dashboard, bridge, or auth changes, verify the intended local and authentication boundaries are preserved, including:
Flag code, tests, logs, fixtures, screenshots, or workflow artifacts that can expose:
Any destructive or KiCad-mutating operation must be explicit, policy-gated, test-covered, and documented. A convenience path must not bypass operating-mode or human-approval boundaries.
For .github/workflows/**, check:
env: before shell use;If a public PR introduces a sensitive vulnerability, explain the fix-relevant risk
without publishing weaponized exploit details, secrets, or private data. Follow
SECURITY.md for disclosure handling.
Behavior changes require evidence at the narrowest useful layer.
Check the repository's testing policy:
For tests that create or mutate Git repositories, verify test-owned temporary directories and isolated Git configuration are used so contributor/system hooks and configuration cannot leak into fixtures.
Do not demand live KiCad execution for logic that is deliberately unit-testable without KiCad. Conversely, do not accept mocked-only evidence when the change specifically depends on a live KiCad integration contract and the repository has a dedicated KiCad-enabled CI path for it.
Identify the source of truth before commenting on generated surfaces.
Important repository rules include:
pyproject.toml is a canonical package metadata/version source;compatibility.yaml is a canonical KiCad/MCP support-policy source;server.json and several public surfaces are generated/synchronized;Flag generated drift, but do not ask contributors to hand-edit generated files when the repository generator is authoritative.
For Python/npm/container/release changes, check:
compatibility.yaml;For Tauri/desktop changes, also review:
Prefer the smallest relevant validation set. Use CI evidence instead of re-running a check only when the reviewed head commit already ran the same check successfully.
corepack pnpm run format:check
corepack pnpm run lint
corepack pnpm run typecheck
corepack pnpm run test:unitcorepack pnpm run metadata:check
corepack pnpm run docs:tools:check
corepack pnpm run tool-contracts:check
corepack pnpm run architecture:check
corepack pnpm run profiles:check
corepack pnpm run adapter-matrix:check
corepack pnpm run compat:checkcorepack pnpm run workflows:lint
corepack pnpm run workflows:securitycorepack pnpm run package:check
corepack pnpm run release:dry-runtask test:webUse Playwright-backed tests when the environment supports them and the change is user-visible.
Use task verify for the repository's local quality gate. Use task ci only when the
change crosses enough package, compatibility, workflow, security, or release boundaries
to justify the full local CI equivalent.
Do not make "run the entire suite" the only review recommendation when a specific, smaller regression test would prove the issue.
Write a review finding only when all of the following are true:
For each finding:
Use severity proportional to impact:
Avoid duplicate comments for the same root cause. Prefer one precise finding that covers the causal defect.
Do not create review comments solely because:
task ci run is absent but the relevant focused checks passed;ARCHITECTURE.md;The goal is a review that maintainers can trust: few comments, high confidence, clear impact, and repository-specific evidence.
© oaslananka, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .github/skills/code-review of oaslananka/kicad-mcp-pro.
Open the folder on GitHubat commit c7a464c
Code 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 |
|---|---|---|---|---|---|---|
| Code Review this skilloaslananka/kicad-mcp-pro | 119 | — | ~3.9k | Automated safety check: Pass | MIT | |
| Agentbro Releaseshirenchuang/agentbro | 203 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| ReleaseWebMCP-org/npm-packages | 103 | — | ~1.6k | Automated safety check: Notes | MIT | |
| Preflightopenfootmanager/openfootmanager | 1.1k | — | ~1.3k | Automated safety check: Pass | GPL-3.0 | |
| MCP Server Trello Releasedelorenj/mcp-server-trello | 446 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Code ReviewAzure/sap-automation | 145 | — | ~7k | Automated safety check: Pass | MIT |
shirenchuang/agentbro
A skill your agent uses when releasing AgentBro from this repository: merging dev/main, bumping versions, updating release notes, tagging, pushing, monitoring GitHub Actions, Homebrew cask…
WebMCP-org/npm-packages
Release the @mcp-b monorepo with Changesets and pnpm, using npm trusted publishing in GitHub Actions.
openfootmanager/openfootmanager
Verify a pull request with the frontend scripts, default and MCP backend tests and clippy, formatting, architecture checks and review evidence.
delorenj/mcp-server-trello
Canonical build → release → tag → publish procedure for the @delorenj/mcp-server-trello repo.
Azure/sap-automation
Review pull requests in the SAP Deployment Automation Framework.
langchain-ai/docs
Document new or changed docs-team tooling on the Notion tooling pages.
oaslananka/kicad-mcp-pro
A skill your agent uses when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.
oaslananka/kicad-mcp-pro
Comprehensive KiCad design review skill covering schematic, PCB, DFM, manufacturing, high-speed, and simulation review workflows.
oaslananka/kicad-mcp-pro
A skill your agent uses for maintainer-requested pull request repairs in kicad-mcp-pro; maps changes to repository-native validation gates and safety constraints.
oaslananka/kicad-mcp-pro
KiCad MCP workflow for ERC/DRC execution, issue triage, waiver review, and revalidation.
oaslananka/kicad-mcp-pro
KiCad MCP manufacturing release workflow for Gerbers, drill files, BOM, pick-and-place, DFM, release evidence, and final human review.
oaslananka/kicad-mcp-pro
Safe KiCad PCB design assistance workflow using KiCad MCP board inspection, placement, routing, stackup, and quality-gate tools.
Categories
A skill your agent uses for GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro. Code Review is an agent skill from oaslananka/kicad-mcp-pro. Use this skill for GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro.
Code Review fits situations like: GitHub Copilot pull request and code reviews in oaslananka/kicad-mcp-pro; diff in this repository; especially changes under src/; .github/workflows/.
Run `npx skills add oaslananka/kicad-mcp-pro --skill code-review -a claude-code`. Or copy the skill folder (.github/skills/code-review in oaslananka/kicad-mcp-pro) into .claude/skills/code-review in your project. Claude Code loads it when a task matches its description.
Run `npx skills add oaslananka/kicad-mcp-pro --skill code-review -a codex`. Or copy the skill folder (.github/skills/code-review in oaslananka/kicad-mcp-pro) into .agents/skills/code-review in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oaslananka/kicad-mcp-pro --skill code-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/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.
SKILL.md names no scripts, command-line tools or credentials: Code Review is instructions for the agent only. Our summary lists: Python 3. Compatibility (from SKILL.md): GitHub Copilot code review for oaslananka/kicad-mcp-pro. Use GitHub MCP context when available. KiCad MCP Pro tools are optional and must remain read-only during review..
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.
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.
Code Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Code Review: Agentbro Release (shirenchuang/agentbro, 203 stars), Release (WebMCP-org/npm-packages, 103 stars), Preflight (openfootmanager/openfootmanager, 1.1k stars) and MCP Server Trello Release (delorenj/mcp-server-trello, 446 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
oaslananka (a GitHub user) maintains it in oaslananka/kicad-mcp-pro, which has 119 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.
Source: oaslananka/kicad-mcp-pro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.