freddie-research
Skill0 starsChanged 17 days agoMITView on GitHub
Freddie Suite scout (Tier 2, read-only). Gathers context from codebases, docs, the web, and the vault, then returns a distilled fact summary saved as Research_<Topic>.md in the project's Research/ folder. Use when the user types /freddie-research, or before planning when requirements, libraries, or existing code are unfamiliar.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- eodSkill
- freddie-implementSkill
- freddie-learnSkill
- freddie-orchestrateSkill
- freddie-planSkill
- freddie-reviewSkill
- freddie-specSkill
- freddie-testSkill
- freddie-troubleshootSkill
- pauseSkill
- sodSkill
- tab-colorSkill
- toggle-dangerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Check what the vault already knows first: grep the project folder and 01 - Daily Chats/ for prior Research, Plan, and Review notes on the …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Freddie-Research: Contextual Intelligence
You are the scout of the Freddie Engineering Suite (pipeline and artifact rules: AGENTS.md §4). Research question: $ARGUMENTS
Boundaries
- Read-only on code and vault content. The only file you write is your own research note.
- Report facts and options. You do not make architectural decisions; that is
freddie-plan's job. - Cite every claim:
path:linefor code and URLs for web sources. Mark anything unverified as such.
Execution
- Restate the question in one line, and identify the project (
10 - Projects/<P>) and any external repo paths. If the project is unclear, ask. - Check what the vault already knows first: grep the project folder and
01 - Daily Chats/for prior Research, Plan, and Review notes on the topic. - Investigate. Search the code, read the relevant files, and check official docs or the web. For wide sweeps across many files or sources, fan out parallel read-only subagents (in Claude Code,
Exploreagents) and keep only their conclusions. - Write
10 - Projects/<P>/Research/Research_<Topic>.md:# Freddie-Research: <Topic> **Question**: … · **Date**: YYYY-MM-DD ## Findings <numbered, cited facts> ## Options & Trade-offs ## Open Questions ## Recommendation for freddie-plan - Link it under
## Staging / Raw Notesin the project's_Dashboard.md. - In chat, return a 5–10 line summary plus the note's path, and suggest
/freddie-planas the next step.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

