Actualize logo

Actualize

OrganizationPopular
NeoLabHQ
actualize

Reconcile the project's FPF state with recent repository changes

Overview

PublisherNeoLabHQ
Repositorycontext-engineering-kit
Skill nameactualize
Stars
1.7K
Forks
159
Bundled files
Instructions only
LicenseGPL-3.0
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 NeoLabHQ on GitHub. Read the source before you install it.

Installation

Install the Actualize 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/NeoLabHQ/context-engineering-kit.git /tmp/context-engineering-kit
mkdir -p .claude/skills
cp -r /tmp/context-engineering-kit/antigravity/skills/actualize .claude/skills/actualize
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Actualize 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 Actualize 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 Actualize 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.

Actualize Knowledge Base

This command is a core part of maintaining a living assurance case. It keeps your FPF knowledge base (.fpf/) in sync with the evolving reality of your project's codebase.

The command performs a three-part audit against recent git changes to surface potential context drift, stale evidence, and outdated decisions. This aligns with the Observe phase of the FPF Canonical Evolution Loop (B.4) and helps manage Epistemic Debt (B.3.4).

Action (Run-Time)

Step 1: Check Git Changes

Run git commands to identify changes since last actualization:

bash
# Get current commit hash
git rev-parse HEAD

# Check for changes since last known baseline
# (Read .fpf/.baseline file if it exists, otherwise use initial commit)
git diff --name-only <baseline_commit> HEAD

# List all changed files
git diff --stat <baseline_commit> HEAD

Step 2: Analyze Report for Context Drift

  1. Review changed files for core project configuration:

    • package.json, go.mod, Cargo.toml, requirements.txt
    • Dockerfile, docker-compose.yml
    • .env.example, config files
  2. If configuration files changed:

    • Re-read project structure (README, config files)
    • Compare detected context with .fpf/context.md
    • Present diff to user
  3. Ask user if they want to update context.md

Step 3: Analyze Report for Evidence Staleness (Epistemic Debt)

  1. Read all evidence files in .fpf/evidence/
  2. Check carrier_ref field in each evidence file
  3. Cross-reference with changed files from git diff
  4. If a referenced file changed:
    • Flag the evidence as STALE
    • Note which hypothesis is affected

Step 4: Analyze Report for Decision Relevance

  1. Read all DRR files in .fpf/decisions/
  2. Trace back to source evidence and hypothesis files
  3. If foundational files changed:
    • Flag the DRR as POTENTIALLY OUTDATED

Step 5: Update Baseline

Create/update .fpf/.baseline file:

# FPF Actualization Baseline
# Last actualized: 2025-01-15T16:00:00Z
commit: abc123def456

Step 6: Present Findings

Output a structured report:

markdown
## Actualization Report

**Baseline**: abc123 (2025-01-10)
**Current**: def456 (2025-01-15)
**Files Changed**: 42

### Context Drift

The following configuration files have changed:
- package.json (+5 dependencies)
- Dockerfile (base image updated)

**Action Required**: Review and update `.fpf/context.md` if constraints have changed.

### Stale Evidence (3 items)

| Evidence | Hypothesis | Changed File |
|----------|------------|--------------|
| ev-benchmark-api | api-optimization | src/api/handler.ts |
| ev-test-auth | auth-module | src/auth/login.ts |
| ev-perf-db | db-indexing | migrations/002.sql |

**Action Required**: Re-validate to refresh evidence for affected hypotheses.

### Decisions to Review (1 item)

| DRR | Affected By |
|-----|-------------|
| DRR-2025-01-10-api-design | src/api/handler.ts changed |

**Action Required**: Consider re-evaluating decision via `/fpf:propose-hypotheses`.

### Summary

- Context drift detected: YES
- Stale evidence: 3 items
- Decisions to review: 1 item

Run `/fpf:decay` for detailed freshness management.

File: .fpf/.baseline

Track the last actualization point:

yaml
# FPF Actualization Baseline
last_actualized: 2025-01-15T16:00:00Z
commit: abc123def456789
branch: main

When to Run

  • Before starting new work: Ensure knowledge base is current
  • After major changes: Sync evidence with code changes
  • Weekly maintenance: Part of regular hygiene
  • Before decisions: Ensure evidence is still valid

Frequently asked questions

What does the Actualize AI skill do?

Reconcile the project's FPF state with recent repository changes

Why use Actualize on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NeoLabHQ/context-engineering-kit/tree/master/antigravity/skills/actualize. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Actualize?

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 Actualize?

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

Is the Actualize AI skill free?

Yes. It is published on GitHub by NeoLabHQ under the GPL-3.0 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 👇