skills.rest
brewpirate
brewpirateCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

index

Parse .claude/triggers.json and write .claude/recall-index.json with phrase and weight fields.

Updated Jun 10, 2026
Search Tags:#indexing#recall#triggers#normalization#tokenization#lookup
One-click install
npx skills add https://github.com/brewpirate/acme-frontier-ai --skill index-brewpirate
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: index
Source: https://github.com/brewpirate/acme-frontier-ai/tree/main/catalog/projects/total-recall/skills/index
Command: npx skills add https://github.com/brewpirate/acme-frontier-ai --skill index-brewpirate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns stored trigger phrases into a searchable reverse index so agents can quickly find the files, terms, and model-specific phrases they need without rereading every trigger definition.

Core Features & Use Cases

  • Model-aware lookup: Separates phrases by model so each agent can retrieve the trigger wording best suited to its own context.
  • Reverse file mapping: Maps individual normalized words back to the files they came from for fast recall and navigation.
  • Cross-model discovery: Captures shared terms so common concepts can be found across all indexed triggers.
  • Practical use case: When the trigger library grows large, this Skill lets an agent rebuild a compact recall index that points directly to the most relevant source files.

Quick Start

Use the index skill to read .claude/triggers.json and build .claude/recall-index.json for every available model.

Frequently Asked Questions about index

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a reverse word-to-files index from trigger definitions for agent recall?▼

To build a reverse index, parse .claude/triggers.json, normalize tokens, score distinctive words, prune stop words, and write .claude/recall-index.json with phrase and weight fields for fast agent lookup.

What is reverse file mapping for model-aware trigger phrase retrieval?▼

Reverse file mapping takes normalized trigger words and maps them back to their source files, separating phrases by model so each agent retrieves context-specific wording without rereading every trigger definition.

How do I normalize tokens and score distinctive words from a triggers.json file?▼

Token normalization and word scoring are handled by the indexing process, which parses trigger definitions, prunes stop words, and assigns weights to distinctive words before writing them into the recall-index.json output file.

Can I use this indexing approach to discover shared trigger terms across multiple AI models?▼

Yes, cross-model discovery captures shared terms across all indexed triggers, allowing common concepts to be found across different models while maintaining model-specific phrase separation in the recall index.

Does this file indexing method require any external dependencies or component libraries?▼

No external dependencies or component libraries are required. The indexing process operates directly on .claude/triggers.json input files and outputs .claude/recall-index.json without needing additional packages.

When should I rebuild a recall index instead of searching trigger definitions directly?▼

Rebuild the recall index when the trigger library grows large, as it creates a compact lookup structure pointing directly to relevant source files, saving agents from rereading every trigger definition during recall workflows.

Related Skills

Explore More Software Engineering Skills→
brewpiratebrewpirate

write

Write model-scoped trigger phrases into Markdown frontmatter from `.claude/triggers.json`.

Community
Intermediate
hiyenwonghiyenwong
2

indexed-memory

Index knowledge by topic, date, and utility for rapid retrieval.

Community
Advanced
fabioc-alohafabioc-aloha

docx-to-md

Convert .docx files to Markdown with image extraction and pandoc cleanup.

Community
Intermediate
sparq-orgsparq-org
8

full-text-search

Integrate BM25 full-text search into SPARQL queries using sparq-text.

Official
Intermediate