@willbooster/agent-skills 1.16.0 → 1.17.0

package/skills/review-fix-all/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: review-fix-all
+description: Run Codex, Claude Code, and Gemini CLI reviews against the current branch concurrently, deduplicate the findings, and fix only the review comments that are still valid for the current codebase.
+allowed-tools: Bash(bunx:*), Task
+---
+
+# Review workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest review --agent all`
+2. Treat the combined output as candidate comments generated by multiple agents running concurrently.
+3. Merge the review results into a single set of candidate comments, deduplicating those that address the same underlying issue.
+4. If there are no candidate comments, quit the workflow without modifying the code.
+5. Determine whether each candidate comment is still valid for the current codebase.
+6. Address valid review comments by updating the code. For invalid comments, add explanatory comments to the code detailing why the existing implementation is necessary.
+   - If there are valid review comments that are out of scope for the current PR, create new issues for them.
+7. If you made any code changes, commit and push them to the current branch.
+8. If you fixed any valid comments, return to step 1. Otherwise, quit the workflow.

package/skills/review-fix-claude/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: review-fix-claude
+description: Run Claude Code review against the current branch, fix only the review comments that are still valid for the current codebase, and leave invalid comments unchanged.
+allowed-tools: Bash(bunx:*)
+---
+
+# Review workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest review --agent claude`
+2. Treat the returned review results as the candidate comment set to process. If the command returns `There is no concern.`, quit without modifying code.
+3. Determine whether each candidate comment is still valid for the current codebase.
+4. Address valid review comments by updating the code. For invalid comments, add explanatory comments to the code detailing why the existing implementation is necessary.
+   - If there are valid review comments that are out of scope for the current PR, create new issues for them.
+5. If you made any code changes, commit and push them to the current branch.
+6. If you fixed any valid comments, return to step 1. Otherwise, quit the workflow.

package/skills/review-fix-codex/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: review-fix-codex
+description: Run Codex code review against the current branch, fix only the review comments that are still valid for the current codebase, and leave invalid comments unchanged.
+allowed-tools: Bash(bunx:*)
+---
+
+# Review workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest review --agent codex`
+2. Treat the returned review results as the candidate comment set to process. If the command returns `There is no concern.`, quit without modifying code.
+3. Determine whether each candidate comment is still valid for the current codebase.
+4. Address valid review comments by updating the code. For invalid comments, add explanatory comments to the code detailing why the existing implementation is necessary.
+   - If there are valid review comments that are out of scope for the current PR, create new issues for them.
+5. If you made any code changes, commit and push them to the current branch.
+6. If you fixed any valid comments, return to step 1. Otherwise, quit the workflow.

package/skills/review-fix-gemini/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: review-fix-gemini
+description: Run Gemini CLI review against the current branch, fix only the review comments that are still valid for the current codebase, and leave invalid comments unchanged.
+allowed-tools: Bash(bunx:*)
+---
+
+# Review workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest review --agent gemini`
+2. Treat the returned review results as the candidate comment set to process. If the command returns `There is no concern.`, quit without modifying code.
+3. Determine whether each candidate comment is still valid for the current codebase.
+4. Address valid review comments by updating the code. For invalid comments, add explanatory comments to the code detailing why the existing implementation is necessary.
+   - If there are valid review comments that are out of scope for the current PR, create new issues for them.
+5. If you made any code changes, commit and push them to the current branch.
+6. If you fixed any valid comments, return to step 1. Otherwise, quit the workflow.

package/skills/review-gemini/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: review-gemini
+description: Run Gemini CLI review against the current branch and report only the review comments that are still valid for the current codebase, without applying fixes.
+allowed-tools: Bash(bunx:*)
+---
+
+# Review workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest review --agent gemini`
+2. Report on the review results.

package/skills/screenshot-claude/SKILL.md

@@ -0,0 +1,13 @@
+---
+name: screenshot-claude
+description: Run Claude Code to take a screenshot for a specific page.
+allowed-tools: Bash(bunx:*)
+---
+
+# Screenshot workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest screenshot --agent claude <initial-url> <page-name> <description>`
+   - `<initial-url>`: Initial URL to open before navigating
+   - `<page-name>`: Page name to navigate to from the initial page
+   - `<description>`: Description of the part to capture in the screenshot
+2. Report the screenshot file path returned by the agent.

package/skills/screenshot-codex/SKILL.md

@@ -0,0 +1,13 @@
+---
+name: screenshot-codex
+description: Run Codex to take a screenshot for a specific page.
+allowed-tools: Bash(bunx:*)
+---
+
+# Screenshot workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest screenshot --agent codex <initial-url> <page-name> <description>`
+   - `<initial-url>`: Initial URL to open before navigating
+   - `<page-name>`: Page name to navigate to from the initial page
+   - `<description>`: Description of the part to capture in the screenshot
+2. Report the screenshot file path returned by the agent.

package/skills/screenshot-gemini/SKILL.md

@@ -0,0 +1,13 @@
+---
+name: screenshot-gemini
+description: Run Gemini CLI to take a screenshot for a specific page.
+allowed-tools: Bash(bunx:*)
+---
+
+# Screenshot workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest screenshot --agent gemini <initial-url> <page-name> <description>`
+   - `<initial-url>`: Initial URL to open before navigating
+   - `<page-name>`: Page name to navigate to from the initial page
+   - `<description>`: Description of the part to capture in the screenshot
+2. Report the screenshot file path returned by the agent.

package/skills/simplify-pr-claude/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: simplify-pr-claude
+description: Use Claude Code to simplify the current pull request by safely reducing unnecessary scope, complexity, and noise while preserving the intended outcome.
+allowed-tools: Bash(bunx:*)
+---
+
+# PR simplification workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest simplify --agent claude`
+2. Report on the simplification results.

package/skills/simplify-pr-codex/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: simplify-pr-codex
+description: Use Codex to simplify the current pull request by safely reducing unnecessary scope, complexity, and noise while preserving the intended outcome.
+allowed-tools: Bash(bunx:*)
+---
+
+# PR simplification workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest simplify --agent codex`
+2. Report on the simplification results.

package/skills/simplify-pr-gemini/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: simplify-pr-gemini
+description: Use Gemini CLI to simplify the current pull request by safely reducing unnecessary scope, complexity, and noise while preserving the intended outcome.
+allowed-tools: Bash(bunx:*)
+---
+
+# PR simplification workflow
+
+1. Run the following command with a 1-hour timeout (DO NOT STOP THE COMMAND BEFORE 1 HOUR ELAPSES): `bunx @willbooster/agent-skills@latest simplify --agent gemini`
+2. Report on the simplification results.

package/skills/update-pr/SKILL.md

@@ -0,0 +1,60 @@
+---
+name: update-pr
+description: Update the pull request title and body for the current branch in the current repository.
+allowed-tools: Bash(bun:*), Bash(gh:*), Bash(git:*)
+---
+
+# Update PR workflow
+
+Write the full replacement pull request title and the complete replacement PR body so they reflect the current scope, motivation, and validation.
+Run `update-pr-title` first, then run `update-pr-body`.
+Finally, report the pull request URL.
+
+## Update the PR title
+
+```bash
+bunx @willbooster/agent-skills@latest update-pr-title <<'EOF'
+feat: concise PR title
+EOF
+```
+
+Note that the prefix of the PR title must follow the Conventional Commits specification:
+
+- feat: A new feature for the user or API.
+- fix: A bug fix for the user or API.
+- build: Changes that affect the build system or external dependencies (e.g., npm, webpack, typescript).
+- chore: Routine tasks, maintenance, or tooling changes that don't modify source or test files.
+- ci: Changes to CI/CD configuration files and scripts.
+- docs: Documentation-only changes.
+- perf: A code change that improves performance.
+- refactor: A code change that neither fixes a bug nor adds a feature, but improves code structure or readability.
+- style: Changes that do not affect the meaning of the code (e.g., formatting).
+- test: Adding missing tests or correcting existing tests.
+
+## Update the PR body
+
+```bash
+bunx @willbooster/agent-skills@latest update-pr-body <<'EOF'
+Close #<issue>
+
+## Summary
+
+- What changed
+- Key scope or affected area
+- Any notable tradeoff or limitation
+
+## Why
+
+- Problem being solved
+- Reason this approach was chosen
+
+## Testing
+
+- Exact commands run
+- Manual verification steps if relevant
+
+## Notes (if needed)
+
+- Breaking changes, rollout concerns, screenshots, or follow-up work
+EOF
+```

package/skills/wbfy/SKILL.md

@@ -0,0 +1,17 @@
+---
+name: wbfy
+description: Apply `wbfy` to the current repository.
+allowed-tools: Bash(bun:*), Bash(gh:*), Bash(git:*), Bash(yarn:*)
+---
+
+# wbfy application workflow
+
+1. If the current branch is `main`, create and switch to a new branch from the latest remote `main` branch.
+   - Make sure the branch is derived from the latest remote `main` branch to avoid merge conflicts when opening a PR.
+2. Run `yarn start <directory_path_of_target_repo>` in `~/ghq/github.com/WillBooster/wbfy`.
+3. Run `yarn check-for-ai` or `bun check-for-ai` in the target repository (do not run this in `wbfy`).
+4. If any checks fail, do one of the following:
+   - Fix the issues in the target repository, then return to step 2.
+   - If the failure originates from `wbfy`, fix `~/ghq/github.com/WillBooster/wbfy`, commit and push the changes, open a PR in the `wbfy` repository, then return to step 1.
+5. Commit and push any changes in the target repository, then open a PR.
+   - `wbfy` creates, modifies, and deletes many files in the target repository, so be sure to include all of them in the commit.