parallel-deep-research SKILL.md skillA
parallel-deep-research from parallel-web/parallel-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add parallel-web/parallel-agent-skills/parallel-deep-research@git:20260925.8fc1fc4Pins git:20260925.8fc1fc4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- parallel-web/parallel-agent-skills
- Path
skills/parallel-deep-research/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260925.8fc1fc4, committed Sep 25, 2026
- First version recorded
- May 6, 2026
- Size
- 7,691 bytes
- Repository stars
- 90
- License
- MIT
ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead. Supports follow-ups with a known prior Task interaction ID.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Deep Research Research topic: $ARGUMENTS > Requires `parallel-cli` ≥ 0.3.0 for text output and context chaining. If a documented command or option is missing, check `parallel-cli --version` and that command's `--help`, then follow the installation-specific upgrade guidance in Setup. API, authentication and input errors are not evidence of an older CLI. ## When to use (vs parallel-web-search) ONLY use this skill when the user explicitly requests deep/exhaustive research. It can take several minutes and costs more than a quick search, depending on the processor and task. For normal "research X" requests, quick lookups, or fact-checking, use **parallel-web-search** instead. ## Step 1: Start the research Choose a descriptive output base in a persistent directory (e.g., `reports/ai-chip-market-2026`). Include the returned run ID to make it unique, then use this base in step 2 as `-o "$FILENAME"`. Check for existing `.json` and `.md` files before saving. ```bash parallel-cli research run "$ARGUMENTS" --processor pro-fast --text --no-wait --json ``` …
Read the whole file at its exact version.
How to install
mdr add parallel-web/parallel-agent-skills/parallel-deep-research@sha256:6d3523c233da02ecThe line at the top of this page pins the label git:20260925.8fc1fc4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_24i63guw4z2wcehc)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 6, 2026 and Sep 25, 2026, about one every 36 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260925.8fc1fc4 latest | 2026-09-25 | 8fc1fc4 | 7,691 B | A | view · diff |
| git:20260519.91443a8 | 2026-05-19 | 91443a8 | 6,367 B | A | view · diff |
| git:20260519.b667820 | 2026-05-19 | b667820 | 6,363 B | A | view · diff |
| git:20260507.4c34b08 | 2026-05-07 | 4c34b08 | 6,202 B | A | view · diff |
| git:20260506.db5cd3e | 2026-05-06 | db5cd3e | 6,336 B | B | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7691 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
parallel-web/parallel-agent-skills · 90 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_24i63guw4z2wcehc GET https://markdownregistry.com/api/v1/resolve?ref=parallel-web/parallel-agent-skills/parallel-deep-research GET https://markdownregistry.com/api/v1/blob/6d3523c233da02ecff3391f590ca3d61e345abebaad6026dd77d751fe3b7be10
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.