New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Research

by JuliusBrussee in JuliusBrussee/cavekit

Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior.

MITAuto-check passedDevelopment

Install Research

skills CLI
$ npx skills add JuliusBrussee/cavekit --skill research -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JuliusBrussee/cavekit research --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JuliusBrussee/cavekit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/research .claude/skills/research && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
research
GitHub stars
1.2k
Token cost
~782 tokens
SKILL.md length
403 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior.

  • Works in 4 steps: SCOPE → GATHER → DISTILL → …
  • A spec decision hinges on a library/API/best practice the agent is unsure of
  • SKILL.md covers WHEN TO RESEARCH, FOUR STEPS, SOURCE DISCIPLINE and WHEN TO STOP, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Research is an agent skill from JuliusBrussee/cavekit. Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Each finding cites a source; unsourced claims are flagged, never written as fact. Triggers when a spec decision hinges on a library/API/best practice the agent is unsure of, when the user says "research this", "what's the best lib for…", "check current best practice", or invokes /ck:research. Defers the §R write to the spec skill.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: Frozen — compressed spec-driven development plugin for Claude Code. Still works; active development moved to JuliusBrussee/caveman. The licence is MIT.

When your agent uses it

  • A spec decision hinges on a library/API/best practice the agent is unsure of
  • The user says research this
  • Whats the best lib for…
  • Check current best practice

Example prompts

  • “research this”
  • “s the best lib for…”
  • “check current best practice”
  • “/research”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. SCOPE
  2. GATHER
  3. DISTILL
  4. HAND OFF

What it can do on your machine

Read from SKILL.md and the folder at commit 7421e87. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Research loads about 782 tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 403 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~782

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JuliusBrussee/cavekit at commit 7421e87, republished under its MIT licence (© JuliusBrussee). 403 words, ~782 tokens.

Download SKILL.mdSave it as .claude/skills/research/SKILL.md (or your agent's skills folder).
name
research
description
Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Each finding cites a source; unsourced claims are flagged, never written as fact. Triggers when a spec decision hinges on a library/API/best practice the agent is unsure of, when the user says "research this", "what's the best lib for…", "check current best practice", or invokes /ck:research. Defers the §R write to the spec skill.

research — external knowledge → §R

Every finding cites a source. No source → flag it ?, never write a guess as fact.

"Process without library context gives you well-organized hallucinations." Build invents a plausible-but-wrong API & §B fills with avoidable bugs. Research is the external oracle: pull the real fact once, log it caveman, never re-derive.

WHEN TO RESEARCH

  • A §C/§I/§V decision hinges on a lib, API, version, or pattern you are unsure of.
  • You are about to assume how an external dependency behaves.
  • The idea touches a domain with real prior art (auth, payments, crypto, rate-limit).
  • /grill parked a ? that the outside world must answer.

Skip when the build touches only code you already wrote. Research scales to the unknown, ⊥ to habit.

FOUR STEPS

1. SCOPE

Turn the unknown into 1-3 concrete questions. Vague "research auth" → "JWT lib for Node ESM, maintained?" + "refresh-token rotation: current best practice?". A scoped question gets a citable answer; a vague one gets an essay.

2. GATHER

Use web search / docs tools. Prefer primary sources: official docs, the repo, the RFC, the paper. Two independent sources beat one confident blog. For a big sweep, spawn a sub-agent so the raw pages never touch this context — it returns only the distilled finding + source.

3. DISTILL

Crush each answer to one caveman line + its source. Drop the prose. The §R row is the memory; the tab you read is not.

R3|refresh token|rotate on use, revoke family on reuse-detect|datatracker.ietf.org/doc/html/rfc6819#section-5.2.2.3

Show full SKILL.md (165 more words)Show less
4. HAND OFF

Emit the §R rows & hand to the spec skill to append. If a finding changes a constraint or interface, note the §C/§I edit for spec too. Research proposes; spec writes.

SOURCE DISCIPLINE

  • Cite a URL, repo, RFC, or paper per row. Verbatim identifiers/versions.
  • Could not verify → write the row but flag ? in the finding & say so. An unverified claim labeled honestly is fine; one disguised as fact is a future §B.
  • Conflicting sources → log both, let the user pick. ⊥ silently average them.

WHEN TO STOP

Done when every scoped question has a sourced §R row (or an honest ?), and no build decision still rests on an unchecked assumption. ⊥ research past the questions you scoped — that is just burning the attention budget.

BOUNDARIES

  • ⊥ write SPEC.md. Hand §R rows to spec.
  • ⊥ write a finding as fact without a source.
  • ⊥ dump raw pages into context or §R. Distill or it does not land.
  • ⊥ research what you can read in the repo. Local truth > web guess.

© JuliusBrussee, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/research of JuliusBrussee/cavekit.

Open the folder on GitHubat commit 7421e87

Compare with similar skills

Research next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research this skillJuliusBrussee/cavekit1.2k—~782Automated safety check: PassMIT
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Openspec Verify ChangeFission-AI/OpenSpec71k2 repos~4.6kAutomated safety check: PassMIT
Warp Factory Fileswarpdotdev/warp65k1 repos~2.5kAutomated safety check: PassAGPL-3.0
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Analyze Logsactivepieces/activepieces25k1 repos~1.6kAutomated safety check: PassMIT

Similar skills

  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed

  • Openspec Verify Change

    Fission-AI/OpenSpec

    Verify implementation matches OpenSpec change artifacts. An agent skill from Fission-AI/OpenSpec.

    71k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed

  • Warp Factory Files

    warpdotdev/warp

    Authors and edits file-based Warp software factory definitions rooted at factory.yaml, covering agents, automations, scorers and webhooks, and validates them before a pull request.

    65k GitHub starsUsed in 1 repo~2.5k tokens
    DevelopmentAuto-check passed

  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Analyze Logs

    activepieces/activepieces

    Analyze application logs from the .evlog/logs/ directory. An agent skill from activepieces/activepieces.

    25k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

  • GitHub Review Iteration

    prisma/orm

    Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from JuliusBrussee/cavekit

All 8 skills in this repo

  • Backprop: Bug-to-Spec Protocol

    JuliusBrussee/cavekit

    After a bug is found, traces its root cause and feeds a new testable invariant back into the project spec so the bug class can't recur.

    1.2k GitHub stars~653 tokensUpdated 1 mo ago
    Auto-check passed

  • Caveman Spec Compression

    JuliusBrussee/cavekit

    Compresses SPEC.md writes and spec-referencing prose into terse, symbol-heavy fragments that drop articles, filler and hedging while keeping facts intact.

    1.2k GitHub stars~721 tokensUpdated 1 mo ago
    Auto-check passed

  • Spec Drift Check

    JuliusBrussee/cavekit

    Read-only detector that compares SPEC.md with the code and reports invariant, interface and task drift grouped by severity, without changing anything.

    1.2k GitHub stars~666 tokensUpdated 1 mo ago
    Auto-check passed

  • Adversarial Spec Review

    JuliusBrussee/cavekit

    Builds a skeptical reviewer grounded in the codebase and research notes to try to refute a spec before any code is written, citing file:line evidence and ending in a go or no-go gate.

    1.2k GitHub stars~959 tokensUpdated 1 mo ago
    Auto-check passed

  • Deepen Module Design

    JuliusBrussee/cavekit

    Scans the code a spec touches for its shallowest module, then proposes a refactor that hides more behind a smaller interface without changing behavior.

    1.2k GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Grill Before Spec

    JuliusBrussee/cavekit

    Interrogates a vague idea one question at a time, recommending an answer each round and recording results as goals and constraints before a spec is written.

    1.2k GitHub stars~812 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Research

What does Research do?

Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Research is an agent skill from JuliusBrussee/cavekit. Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior.

When should I use Research?

Research fits situations like: A spec decision hinges on a library/API/best practice the agent is unsure of; the user says research this; whats the best lib for…; check current best practice.

How do I install Research in Claude Code?

Run `npx skills add JuliusBrussee/cavekit --skill research -a claude-code`. Or copy the skill folder (skills/research in JuliusBrussee/cavekit) into .claude/skills/research in your project. Claude Code loads it when a task matches its description.

How do I install Research in Codex?

Run `npx skills add JuliusBrussee/cavekit --skill research -a codex`. Or copy the skill folder (skills/research in JuliusBrussee/cavekit) into .agents/skills/research in your project. Codex loads it when a task matches its description.

Can I use Research in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JuliusBrussee/cavekit --skill research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research, .gemini/skills/research, .github/skills/research and .opencode/skills/research in your project.

What does Research need to run?

SKILL.md names no scripts, command-line tools or credentials: Research is instructions for the agent only.

Does Research access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Research safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Research use?

Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Research use?

About 782 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Research?

Skills that share tags, products or a category with Research: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Openspec Verify Change (Fission-AI/OpenSpec, 71k stars), Warp Factory Files (warpdotdev/warp, 65k stars) and Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research?

JuliusBrussee (a GitHub user) maintains it in JuliusBrussee/cavekit, which has 1,152 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 14, 2026.

Source: JuliusBrussee/cavekit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.