Deep Research

Run deep research through DeepAPI and save a report with sources. Use when asked for deep research, DeepAPI research, or Perplexity deep research.

4,336 stars 628 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add davidondrej/skills --skill deep-research
Manual install
git clone --depth 1 https://github.com/davidondrej/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/deep-research ~/.claude/skills/deep-research

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Deep Research

Use DeepAPI (`POST /v1/research/deep`) for all deep research.

## API key

Read `DEEPAPI_API_KEY` from the environment, falling back to `~/.deepapi/env`. Never source `~/.zshrc`; it breaks the shell (exit 126).

```bash
[ -n "$DEEPAPI_API_KEY" ] || . ~/.deepapi/env
KEY=$DEEPAPI_API_KEY
BASE=${DEEPAPI_API_BASE_URL:-https://deepapi.co}
```

If the key is missing, stop and ask the user. Never print or log it. Get a key at deepapi.co.

## 1. Build the prompt

Follow the `research-prompt` skill. Write one self-contained paragraph:

- Lead with the main question and the decision it informs.
- Include all context and 3-6 numbered sub-questions. Keep one mission per prompt.
- State what to include or avoid. Prefer primary sources; separate fact from inference.

Field limits: `query` ≤ 4000 characters (the prompt), optional `context` ≤ 8000, optional `instructions` ≤ 2000. Do not send `model` or `provider`; the API rejects them.

## 2. Run it

One call returns a cited answer, targeting 700-1,120 words. The server allows up to ~5 minutes.

```bash
IDK=$(uuidgen)   # keep this; retries must reuse the SAME Idempotency-Key
jq -n --rawfile p /tmp/dr_prompt.txt '{query:$p, maxCostUsd:"0.70"}' > /tmp/dr_body.json
curl -s --max-time 320 "$BASE/v1/research/deep" \
  -H "Authorization: Bearer $KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDK" \
  -d @/tmp/dr_body.json > /tmp/dr_result.json
```
Read the full skill on GitHub

Details

Skill name
deep-research
Path
skills/deep-research/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Deep Research skill do?

Run deep research through DeepAPI and save a report with sources. Use when asked for deep research, DeepAPI research, or Perplexity deep research.

How do I install the Deep Research skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add davidondrej/skills --skill deep-research. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Deep Research popular?

It lives in davidondrej/skills, which has 4,336 GitHub stars and 628 forks.

Related skills

Browser Harness

4.3k

davidondrej/skills

Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.

Testing & QAIn 2 lists628

4x4

4.3k

davidondrej/skills

Pull 16 fast decisions out of the user with 4 sets of 4 open questions, then present an implementation plan. Only for risky changes, large product decisions, or large refactors. Run when the user types /4x4. Agents may suggest it in one line but never start it on their own.

AI, LLMs & Agents628

Adr Verbatim

4.3k

davidondrej/skills

Record concise ADRs that preserve the user's decisions without conversational noise. Use for "adr-verbatim", "new ADR", "document that as an ADR", "record this decision", or supplied ADR wording.

Other628

Domain Check

2.1k

ai4s-research/open-science

Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong (unit/dimension mismatch, Euclidean distance on lat/lon without a CRS, 0-based/1-based coordinate and strand errors, impossible SMILES valence, uncorrected multiple comparisons, averaging

Research & Science231

Paper Cinder Transition

7.7k

MengTo/Skills

Change between pages, chapters or scenes with a paper-burn transition, a ragged ember line that sweeps across the frame, chars the old page ahead of it and reveals the next scene live behind it, written as one WebGL composite pass over a frozen frame and a scissored live scene. Covers the front's silhouette, the luminous ember gradient with a beading gold thread, torn porous charcoal that is alpha-masked, baked noise, finite-difference slopes, the 0.75-scale live scene, sweep direction, timing, reduced motion and visibility pausing. Use for a burn transition, paper burn, cinder wipe, chapter c

Research & Science885

Publication Figures

2.1k

ai4s-research/open-science

Use whenever you generate or review a chart, plot, table, or paper figure in this workspace, including work delegated by paper-writing, literature-survey, and experiment skills. Applies the Open Science publication style, enforces readable final-size layout for figures and tables, and rejects generic diagram-tool output as a publication figure. Interactive Plotly/HTML may be used for exploration, but paper delivery requires a static publication-ready export.

Research & Science231

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.