Workflow Fix logo

Workflow Fix

Organization
bitwarden
workflow-fix

Apply fixes for workflow linter findings identified by the workflow-audit skill. Applies mechanical fixes automatically, pauses for judgment calls, verifies with a re-lint, and creates draft PRs. Run the workflow-audit skill first to identify findings before using this skill. <example> User: Go ahead and fix the linter findings from the audit Action: Trigger workflow-fix to apply fixes and create PRs </example> <example> User: Fix the workflow linter issues in server and clients Action: Trigger workflow-fix for those repos </example>

Overview

Publisherbitwarden
Repositoryai-plugins
Skill nameworkflow-fix
Stars
149
Forks
19
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bitwarden on GitHub. Read the source before you install it.

Installation

Install the Workflow Fix AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bitwarden/ai-plugins.git /tmp/ai-plugins
mkdir -p .claude/skills
cp -r /tmp/ai-plugins/plugins/bitwarden-devops-engineer/skills/workflow-fix .claude/skills/workflow-fix
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Workflow Fix in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Workflow Fix on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Workflow Fix is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Rules

  • No mutating API calls without confirmation. gh api GET requests are allowed freely. Any call using -X POST, -X PUT, -X PATCH, or -X DELETE must be shown to the user and approved before execution.
  • Never force-push, delete branches, or delete repositories.
  • Only modify files under .github/. Do not touch application code, scripts, or configuration outside of workflow files.
  • Show a diff and get confirmation before handing off for commit.
  • All PRs must be created as drafts.
  • Flag uncertainty. If a finding is ambiguous or a fix could break a workflow, stop and ask rather than guessing.

Step 1: Verify Prerequisites

Check if bwwl is available:

bash
bwwl --version

If the command is not found, stop and inform the user that bwwl must be installed before continuing. Do not attempt to install it.

Step 2: Determine Scope

Parse the user's request to determine what to fix:

  • Single file or directory: Operate on the current repo only.
  • Multiple repos (e.g., "server, clients, android"): Operate on each repo sequentially. Ask the user for the base directory where their repos are cloned. For each repo, look for its local clone at <base-dir>/<repo>. If a clone is not found, inform the user and skip that repo.
  • No specific target: Fix all findings in .github/workflows/ of the current directory.

If the user has not run the workflow-audit skill first, run the linter now to identify findings before proceeding.

Step 3: For Each Repo in Scope

Repeat Steps 4–7 for each repo. Announce which repo is being worked on.

Step 4: Create a Fix Branch

Only create the fix branch if there are findings to fix:

bash
git checkout -b fix/workflow-linter-findings

Step 5: Apply Fixes

Consult the bitwarden-workflow-linter-rules skill for the correct fix for each rule.

For mechanical findings: Apply all fixes without prompting.

Exception — step_pinned: Before applying each hash pin, follow the step_pinned fix procedure from the bitwarden-workflow-linter-rules skill (resolve SHA via gh api, show verification link, wait for user confirmation).

For judgment findings: For each one, pause and present the finding clearly. Ask the user which option they want (per the bitwarden-workflow-linter-rules skill), then apply their choice.

Step 6: Verify Fixes

Re-run the linter to confirm all findings are resolved:

bash
bwwl lint -f .github/workflows/

If errors remain, analyze and fix them. Repeat until clean.

Step 7: Review and Create PR

After all fixes are applied:

  1. Show a git diff of all changes made.
  2. Ask the user to confirm they want to proceed with a PR.
  3. Do not run the staging, commit, or push commands yourself. Present the block below for the user to run manually as a suggestion:
bash
git add .github/workflows/
git commit -m "Fix workflow linter findings"
git push -u origin fix/workflow-linter-findings
  1. Once the user confirms the push, create the draft PR:
bash
gh pr create \
  --title "Fix workflow linter findings" \
  --body "Automated fixes for findings from the Bitwarden workflow linter (bwwl)." \
  --draft

Step 8: Summary

After processing all repos, output a summary table:

RepoFindings FixedPRs CreatedSkipped / Notes
............

Frequently asked questions

What does the Workflow Fix AI skill do?

Apply fixes for workflow linter findings identified by the workflow-audit skill. Applies mechanical fixes automatically, pauses for judgment calls, verifies with a re-lint, and creates draft PRs. Run the workflow-audit skill first to identify findings before using this skill. <example> User: Go ahead and fix the linter findings from the audit Action: Trigger workflow-fix to apply fixes and create PRs </example> <example> User: Fix the workflow linter issues in server and clients Action: Trigger workflow-fix for those repos </example>

Why use Workflow Fix on TypingMind?

Because you install it once and use it with any model. Workflow Fix is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Workflow Fix in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwarden/ai-plugins/tree/main/plugins/bitwarden-devops-engineer/skills/workflow-fix. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Workflow Fix?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Workflow Fix?

As many as you like. As long as a model supports skills, you can use Workflow Fix with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Workflow Fix AI skill free?

It is published on GitHub by bitwarden. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇