KS
Killer-Skills

parametric-scribe — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for Claude, Codex, and Claude Code agents requiring secure and audited parametric history management for coding projects. Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

aiskillstore aiskillstore
[0]
[0]
Updated: 2/20/2026

Quality Score

Top 5%
45
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add aiskillstore/marketplace/parametric-scribe

Agent Capability Analysis

The parametric-scribe MCP Server by aiskillstore is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Ideal for Claude, Codex, and Claude Code agents requiring secure and audited parametric history management for coding projects.

Core Value

Empowers agents to maintain a parametric history of projects in YAML format, ensuring transparent and version-controlled coding processes with features like sequential step IDs, ISO date timestamps, and intent summaries, all stored in a `docs/recipe.yaml` file.

Capabilities Granted for parametric-scribe MCP Server

Automating parametric history updates after coding tasks
Generating detailed project timelines with step IDs and timestamps
Debugging coding projects through intent summaries and output file tracking

! Prerequisites & Limits

  • Requires security auditing for integration
  • Specifically designed for Claude, Codex, and Claude Code agents
  • Dependent on YAML file format for parametric history storage
Project
SKILL.md
1.5 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Parametric Scribe

Overview

You are the Keeper of the Recipe. Unlike normal coding where "what's done is done," you maintain a Parametric History of the project in docs/recipe.yaml.

Mode 1: Recording (The default)

When: After completing any coding task. Action: Append a new entry to docs/recipe.yaml.

yaml
1 - step_id: "<sequential-id>" 2 timestamp: "<iso-date>" 3 intent: "<short-summary>" 4 prompt: "<the-exact-prompt-used>" 5 output_files: ["<list-of-modified-files>"] 6 git_sha: "<current-head-sha>"

Mode 2: Time Travel (Replay)

When: The user says "Change Step X" or "Replay from Step X".

The Protocol:

  1. Read docs/recipe.yaml.
  2. Identify the Target Step (Step X).
  3. Hard Reset: git checkout <Step X-1 SHA> (Go back to the state before Step X).
  4. Execute Target: Run the New Prompt provided by the user.
  5. Intelligent Rebase (The Magic):
    • For each Subsequent Step (Step X+1, X+2...):
      • Read the Original Intent (Prompt).
      • Look at the Current Codebase (which is now different).
      • Self-Correction: "The original prompt asked to modify app.py, but we are now in index.js. I will apply the intent (Add Login) to index.js instead."
      • Execute the adapted prompt.
      • Update the recipe.yaml with the new file paths and SHAs.

Mode 3: Forking

When: The user says "Create a variant." Action: Copy recipe.yaml to recipe-variant-b.yaml and modify the target step there, leaving the original intact.

Related Skills

Looking for an alternative to parametric-scribe or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication