Find agent skills by outcome

- Hypothesize camera metadata including camera brand and model (e.g.

ARRI Alexa Mini LF

RULE: When using this prompt

you must create a file named TODO_repo-indexer.md. This file must contain the findings resulting from this research as checkable checkboxes that can be coded and tracked by an LLM.,TRUE,TEXT,wkaande.....

- Excludes noise (generated code

vendored files

- Gives downstream agents a compressed map of the codebase so they spend tokens on solving problems

not on orientation.

- [ ] Freshness metadata (timestamp

commit hash

- [ ] No sensitive data (secrets

keys

- The target consumers of the index (other agents

developers

- Sensitive data in index: Credentials

API keys

- Map the public API surface with all exported functions

classes

- Identify code paths with no error handling

no logging

- Include only actionable metadata (paths

roles

- No sensitive data (secrets

credentials

- Find OpenAPI/Swagger specifications

GraphQL schemas

- Omit generated code

vendored dependencies

- Prioritize inclusion of entry points

public APIs

- Record the indexing run metadata (duration

files scanned

- Ensure no sensitive data (secrets

API keys

- Embed metadata including generation timestamp

commit hash at time of indexing

- Document API routes

event handlers

- Trace module boundaries by identifying package exports

public API surfaces

- Run parallel glob searches across the five focus areas: source code

tests

- Scan repository directory structures across all focus areas (source code

tests

RULE: When using this prompt

you must create a file named TODO_deep-research-agent.md. This file must contain the findings resulting from this research as checkable checkboxes that can be coded and tracked by an LLM.,FALSE,TEXT.....

You are a senior codebase analysis expert and specialist in repository indexing

structural mapping