Deep Research Workflow

What it does

When your agent uses it

• Producing a research report with a citation for each claim
• Running a multi-round literature review that can be resumed
• Scoping a broad question into sub-questions and tracking coverage

Example prompts

• “Do a thorough deep dive on how vector databases handle filtered search and write a cited report.”
• “Plan an exhaustive literature review on remote work and productivity, then start round one.”
• “Resume the research from plan.json and run the next round of fetches.”

Requirements

• Python, for plan.py, iterate.py and compile.py
• Web fetching tools in the host agent

Workflow steps

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

1. 1Plan
2. 2Iterate
3. 3Compile

What it can do on your machine

Read from SKILL.md and the folder at commit 4494195. 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

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  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

Deep Research Workflow loads about 1.3k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 180 tokens; SKILL.md has 467 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~180

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3k

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

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); the scripts in this folder are not scanned.

SKILL.md

The full file from TokenRhythm/opensquilla at commit 4494195, republished under its Apache-2.0 licence (© TokenRhythm). 467 words, ~1,336 tokens.

name

deep-research

description

Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.

visibility

public

invocation

direct

description_zh

具有明确方法论、证据追踪和带引用标注综合的多轮研究。触发词如'深入研究'、'研究报告'、'文献综述'、'跨来源调查X'、'多轮调查'。区别于单轮浓缩的 summarize 技能：本技能跨迭代维护状态文件、追踪覆盖度，并生成带逐条引用的长篇报告，分为规划、迭代、汇编三个阶段。技能本身不抓取网页，而是通过OpenSqui…

provenance.origin

clawhub-mit0

provenance.license

MIT-0

provenance.upstream_url

https://clawhub.ai/in-depth-research

provenance.maintained_by

OpenSquilla

Scope → Plan → Iterate (×N) → Compile → Deliver

python {baseDir}/scripts/plan.py \
    --question "How did Manus differentiate from competing AI agents in 2025?" \
    --depth thorough \
    --out plan.json

# Show the host what to fetch this round
python {baseDir}/scripts/iterate.py --plan plan.json --round 1 --print-fetches

# After the host fetches, record results back
python {baseDir}/scripts/iterate.py --plan plan.json --round 1 \
    --record evidence_round_1.json

[
  {
    "subquestion_id": "sq-002",
    "url": "https://...",
    "title": "...",
    "excerpt": "...",
    "relevance": 0.85,
    "fetched_at": "2026-05-06T10:14:00Z"
  }
]

python {baseDir}/scripts/compile.py --plan plan.json --out report.md

© TokenRhythm, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts, references) in src/opensquilla/skills/bundled/deep-research of TokenRhythm/opensquilla.

• SKILL.md
• THIRD_PARTY_NOTICES.md
• references/methodology.md
• references/sources.md
• scripts/compile.py
• scripts/iterate.py
• scripts/plan.py

Open the folder on GitHubat commit 4494195