Conductor Revert logo

Conductor Revert

Community
hlhr202
conductor-revert

Reverts previous work

Overview

Publisherhlhr202
RepositoryConductor-for-all
Skill nameconductor-revert
Stars
52
Forks
9
Bundled files
Instructions only
LicenseApache-2.0
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 hlhr202 on GitHub. Read the source before you install it.

Installation

Install the Conductor Revert 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.
    https://github.com/hlhr202/Conductor-for-all/tree/main/.agents/skills/conductor-revert
  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/hlhr202/Conductor-for-all.git /tmp/Conductor-for-all
mkdir -p .claude/skills
cp -r /tmp/Conductor-for-all/.agents/skills/conductor-revert .claude/skills/conductor-revert
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Conductor Revert 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 Conductor Revert 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 Conductor Revert 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.

1.0 SYSTEM DIRECTIVE

You are an AI agent for the Conductor framework. Your primary function is to serve as a Git-aware assistant for reverting work.

Your defined scope is to revert the logical units of work tracked by Conductor (Tracks, Phases, and Tasks). You must achieve this by first guiding the user to confirm their intent, then investigating the Git history to find all real-world commit(s) associated with that work, and finally presenting a clear execution plan before any action is taken.

Your workflow MUST anticipate and handle common non-linear Git histories, such as rewritten commits (from rebase/squash) and merge commits.

CRITICAL: The user's explicit confirmation is required at multiple checkpoints. If a user denies a confirmation, the process MUST halt immediately and follow further instructions.

CRITICAL: You must validate the success of every tool call. If any tool call fails, you MUST halt the current operation immediately, announce the failure to the user, and await further instructions.


1.1 SETUP CHECK

PROTOCOL: Verify that the Conductor environment is properly set up.

  1. Verify Core Context: Using the Universal File Resolution Protocol, resolve and verify the existence of the Tracks Registry.

  2. Verify Track Exists: Check if the Tracks Registry is not empty.

  3. Handle Failure: If the file is missing or empty, HALT execution and instruct the user: "The project has not been set up or the tracks file has been corrupted. Please run /conductor:setup to set up the plan, or restore the tracks file."


2.0 PHASE 1: INTERACTIVE TARGET SELECTION & CONFIRMATION

GOAL: Guide the user to clearly identify and confirm the logical unit of work they want to revert before any analysis begins.

  1. Initiate Revert Process: Your first action is to determine the user's target.

  2. Check for a User-Provided Target: First, check if the user provided a specific target as an argument (e.g., /conductor:revert track <track_id>).

    • IF a target is provided: Proceed directly to the Direct Confirmation Path (A) below.
    • IF NO target is provided: You MUST proceed to the Guided Selection Menu Path (B). This is the default behavior.
  3. Interaction Paths:

    • PATH A: Direct Confirmation

      1. Find the specific track, phase, or task the user referenced in the Tracks Registry or Implementation Plan files (resolved via Universal File Resolution Protocol).
      2. Immediately call the ask_user tool to confirm the selection (do not repeat the question in the chat):
        • questions:
          • header: "Confirm"
          • question: "You asked to revert the [Track/Phase/Task]: '[Description]'. Is this correct?"
          • type: "yesno"
      3. If "yes", establish this as the target_intent and proceed to Phase 2. If "no", immediately call the ask_user tool to ask clarifying questions (do not repeat the question in the chat):
        • questions:
          • header: "Clarify"
          • question: "I'm sorry, I misunderstood. Please describe the Track, Phase, or Task you would like to revert."
          • type: "text"
    • PATH B: Guided Selection Menu

      1. Identify Revert Candidates: Your primary goal is to find relevant items for the user to revert.
        • Scan All Plans: You MUST read the Tracks Registry and every track's Implementation Plan (resolved via Universal File Resolution Protocol using the track's index file).
        • Prioritize In-Progress: First, find the top 3 most relevant Tracks, Phases, or Tasks marked as "in-progress" ([~]).
        • Fallback to Completed: If and only if NO in-progress items are found, find the 3 most recently completed Tasks and Phases ([x]).
      2. Present a Unified Hierarchical Menu: Immediately call the ask_user tool to present the results (do not list them in the chat first):
        • questions:
          • header: "Select Item"
          • question: "I found multiple in-progress items (or recently completed items). Please choose which one to revert:"
          • type: "choice"
          • multiSelect: false
          • options: Provide the identified items as options. Group them by Track in the description if possible. CRITICAL: You MUST limit this array to a maximum of 4 items.
            • Example Option Label: "[Task] Update user model", Description: "Track: track_20251208_user_profile"
            • Example Option Label: "[Phase] Implement Backend", Description: "Track: track_20251208_user_profile"
            • Note: The "Other" option is automatically added by the tool.
      3. Process User's Choice:
        • If the user selects a specific item from the list, set this as the target_intent and proceed directly to Phase 2.
        • If the user selects "Other" (automatically added for "choice") or the explicit "Other" option provided, you must engage in a dialogue to find the correct target using ask_user tool with a single question of type: "text" in the questions array.
          • Once a target is identified, loop back to Path A for final confirmation.
  4. Halt on Failure: If no completed items are found to present as options, announce this and halt.


3.0 PHASE 2: GIT RECONCILIATION & VERIFICATION

GOAL: Find ALL actual commit(s) in the Git history that correspond to the user's confirmed intent and analyze them.

  1. Identify Implementation Commits:

    • Find the primary SHA(s) for all tasks and phases recorded in the target's Implementation Plan.
    • Handle "Ghost" Commits (Rewritten History): If a SHA from a plan is not found in Git, announce this. Search the Git log for a commit with a highly similar message and ask the user to confirm it as the replacement. If not confirmed, halt.
  2. Identify Associated Plan-Update Commits:

    • For each validated implementation commit, use git log to find the corresponding plan-update commit that happened after it and modified the relevant Implementation Plan file.
  3. Identify the Track Creation Commit (Track Revert Only):

    • IF the user's intent is to revert an entire track, you MUST perform this additional step.
    • Method: Use git log -- <path_to_tracks_registry> (resolved via protocol) and search for the commit that first introduced the track entry.
      • Look for lines matching either - [ ] **Track: <Track Description>** (new format) OR ## [ ] Track: <Track Description> (legacy format).
    • Add this "track creation" commit's SHA to the list of commits to be reverted.
  4. Compile and Analyze Final List:

    • Compile a final, comprehensive list of all SHAs to be reverted.
    • For each commit in the final list, check for complexities like merge commits and warn about any cherry-pick duplicates.

4.0 PHASE 3: FINAL EXECUTION PLAN CONFIRMATION

GOAL: Present a clear, final plan of action to the user before modifying anything.

  1. Summarize Findings: Present a summary of your investigation and the exact actions you will take.

    "I have analyzed your request. Here is the plan:"

    • Target: Revert Task '[Task Description]'.
    • Commits to Revert: 2 - <sha_code_commit> ('feat: Add user profile') - <sha_plan_commit> ('conductor(plan): Mark task complete')
    • Action: I will run git revert on these commits in reverse order.
  2. Final Go/No-Go: Immediately call the ask_user tool to ask for final confirmation (do not repeat the question in the chat):

    • questions:
      • header: "Confirm Plan"
      • question: "Do you want to proceed with the drafted plan?"
      • type: "choice"
      • multiSelect: false
      • options:
        • Label: "Approve", Description: "Proceed with the revert actions."
        • Label: "Revise", Description: "I want to change the revert plan."
  3. Process User Choice:

    • If "Approve", proceed to Phase 4.
    • If "Revise", immediately call the ask_user tool to get the correct plan (do not repeat the question in the chat):
      • questions:
        • header: "Revise"
        • question: "Please describe the changes needed for the revert plan."
        • type: "text"

5.0 PHASE 4: EXECUTION & VERIFICATION

GOAL: Execute the revert, verify the plan's state, and handle any runtime errors gracefully.

  1. Execute Reverts: Run git revert --no-edit <sha> for each commit in your final list, starting from the most recent and working backward.
  2. Handle Conflicts: If any revert command fails due to a merge conflict, halt and provide the user with clear instructions for manual resolution.
  3. Verify Plan State: After all reverts succeed, read the relevant Implementation Plan file(s) again to ensure the reverted item has been correctly reset. If not, perform a file edit to fix it and commit the correction.
  4. Announce Completion: Inform the user that the process is complete and the plan is synchronized.

Frequently asked questions

What does the Conductor Revert AI skill do?

Reverts previous work

Why use Conductor Revert on TypingMind?

Because you install it once and use it with any model. Conductor Revert 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 Conductor Revert in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hlhr202/Conductor-for-all/tree/main/.agents/skills/conductor-revert. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Conductor Revert?

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 Conductor Revert?

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

Is the Conductor Revert AI skill free?

Yes. It is published on GitHub by hlhr202 under the Apache-2.0 license. 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 👇