@willbooster/agent-skills 1.21.6 → 1.21.8

package/README.md

@@ -45,3 +45,11 @@ bunx skills@latest add WillBooster/agent-skills --agent claude-code --agent code
 ## CLI
 
 This repository also ships a Bun-powered CLI package for skill-specific commands.
+
+## Recommended Other Skills
+
+```
+bunx skills@latest add https://cli.sentry.dev --agent claude-code --agent codex
+bunx skills@latest add railwayapp/railway-skills --agent claude-code --agent codex
+bunx skills@latest add https://github.com/cloudflare/skills --skill wrangler --agent claude-code --agent codex
+```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@willbooster/agent-skills",
-  "version": "1.21.6",
+  "version": "1.21.8",
   "description": "A collection of agent skills for WillBooster Inc.",
   "repository": {
     "type": "git",
@@ -45,16 +45,16 @@
     "@semantic-release/release-notes-generator": "14.1.0",
     "@tsconfig/bun": "1.0.10",
     "@types/bun": "1.3.12",
-    "@typescript/native-preview": "7.0.0-dev.20260419.1",
-    "@willbooster/oxfmt-config": "1.2.1",
-    "@willbooster/oxlint-config": "1.4.4",
-    "@willbooster/wb": "13.11.8",
-    "build-ts": "17.1.6",
+    "@typescript/native-preview": "7.0.0-dev.20260421.2",
+    "@willbooster/oxfmt-config": "1.2.2",
+    "@willbooster/oxlint-config": "1.4.6",
+    "@willbooster/wb": "13.11.11",
+    "build-ts": "17.1.8",
     "conventional-changelog-conventionalcommits": "9.3.1",
-    "lefthook": "2.1.5",
-    "oxfmt": "0.45.0",
-    "oxlint": "1.60.0",
-    "oxlint-tsgolint": "0.21.0",
+    "lefthook": "2.1.6",
+    "oxfmt": "0.47.0",
+    "oxlint": "1.62.0",
+    "oxlint-tsgolint": "0.22.1",
     "semantic-release": "25.0.3",
     "sort-package-json": "3.6.1"
   },

package/skills/complete-pr/SKILL.md

@@ -6,26 +6,5 @@ description: Complete GitHub pull requests by iterating on CI and review feedbac
 Use the `fetch-pr` skill to read the PR body and its messages.
 Fetch the latest changes from the remote. If the remote default branch has new commits, merge it into the current branch, resolve any conflicts, and push the changes.
 Next, fetch the current repository owner using the command `gh repo view --json owner --jq '.owner.login'`.
-If the owner is `WillBooster` or `WillBoosterLab`, follow the first workflow below; otherwise, follow the second workflow.
-
-## Workflow for `WillBooster` or `WillBoosterLab` repositories
-
-1. Check the CI (GitHub Actions) results using the `check-pr-ci` skill.
-2. If any workflow fails, pull the latest remote changes, resolve the issues, commit, push, and return to step 1. Otherwise, proceed to the next step.
-3. Fetch unresolved review threads using the `manage-pr-review-threads` skill.
-4. Review each unresolved thread to determine if it requires code or documentation changes. Validate each claim against the current codebase first, and reproduce issues or consult official documentation when necessary instead of relying on memory.
-5. 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.
-6. Reply to all review threads using the `manage-pr-review-threads` skill.
-7. If you made changes in step 5, commit and push them, post `/gemini review` on the PR, wait for 5 minutes (`sleep 5m`), and return to step 1.
-8. Update the PR title and body using the `update-pr` skill to reflect all changes.
-
-## Workflow for the other repositories
-
-1. Check the CI (GitHub Actions) results using the `check-pr-ci` skill.
-2. If any workflow fails, pull the latest remote changes, resolve the issues, commit, push, and return to step 1. Otherwise, proceed to the next step.
-3. Fetch unresolved review threads using the `manage-pr-review-threads` skill.
-4. Review each unresolved thread and decide whether it requires a code or documentation change. Validate each claim against the current codebase first, and reproduce it or check official documentation when needed instead of relying on memory. Ignore only comments that are clearly outdated, incorrect, or intentionally declined with solid reasoning.
-5. If there are valid review comments to address, make only the changes supported by the validation from step 4, commit, push, and then return to step 1.
-   - Do not post any message like review replies on non-WillBooster repositories.
-6. Update the PR title and body using the `update-pr` skill to reflect all changes.
+If the owner is `WillBooster` or `WillBoosterLab`, follow `references/willbooster-workflow.md`.
+Otherwise, follow `references/other-repositories-workflow.md`.

package/skills/complete-pr/references/other-repositories-workflow.md

@@ -0,0 +1,7 @@
+1. Check the CI (GitHub Actions) results using the `check-pr-ci` skill.
+2. If any workflow fails, pull the latest remote changes, resolve the issues, commit, push, and return to step 1. Otherwise, proceed to the next step.
+3. Fetch unresolved review threads using the `manage-pr-review-threads` skill.
+4. Review each unresolved thread and decide whether it requires a code or documentation change. Validate each claim against the current codebase first, and reproduce it or check official documentation when needed instead of relying on memory. Ignore only comments that are clearly outdated, incorrect, or intentionally declined with solid reasoning.
+5. If there are valid review comments to address, make only the changes supported by the validation from step 4, commit, push, and then return to step 1.
+   - Do not post any message like review replies on non-WillBooster repositories.
+6. Update the PR title and body using the `update-pr` skill to reflect all changes.

package/skills/complete-pr/references/willbooster-workflow.md

@@ -0,0 +1,9 @@
+1. Check the CI (GitHub Actions) results using the `check-pr-ci` skill.
+2. If any workflow fails, pull the latest remote changes, resolve the issues, commit, push, and return to step 1. Otherwise, proceed to the next step.
+3. Fetch unresolved review threads using the `manage-pr-review-threads` skill.
+4. Review each unresolved thread to determine if it requires code or documentation changes. Validate each claim against the current codebase first, and reproduce issues or consult official documentation when necessary instead of relying on memory.
+5. 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.
+6. Reply to all review threads using the `manage-pr-review-threads` skill.
+7. If you made changes in step 5, commit and push them, post `/gemini review` on the PR, wait for 5 minutes (`sleep 5m`), and return to step 1.
+8. Update the PR title and body using the `update-pr` skill to reflect all changes.

package/skills/fetch-issue/SKILL.md

@@ -4,4 +4,4 @@ description: Fetch a GitHub issue body and its messages for the current reposito
 allowed-tools: Bash(bun:*), Bash(gh:*)
 ---
 
-Run the following command to fetch the issue body and its messages: `bunx @willbooster/agent-skills@latest fetch-issue <issue-number-or-url>`
+Run the following command in the local repository to fetch the issue body and its messages: `bunx @willbooster/agent-skills@latest fetch-issue <issue-number-or-url>`

package/skills/fetch-pr/SKILL.md

@@ -4,4 +4,4 @@ description: Fetch a GitHub pull request body and its messages for the current r
 allowed-tools: Bash(bun:*), Bash(gh:*)
 ---
 
-Run the following command to fetch the pull request body and messages, excluding inline review comments: `bunx @willbooster/agent-skills@latest fetch-pr <pr-number-or-url>`
+Run the following command in the local repository to fetch the pull request body and messages (excluding inline review comments): `bunx @willbooster/agent-skills@latest fetch-pr <pr-number-or-url>`