Agent skill

Structure Pocket Inspection

by openJiuwen-ai in openJiuwen-ai/sciencediscovery

Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center.

Apache-2.0Auto-check passed

Install Structure Pocket Inspection

skills CLI
$ npx skills add openJiuwen-ai/sciencediscovery --skill structure-pocket-inspection -a claude-code

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

GitHub CLI
$ gh skill install openJiuwen-ai/sciencediscovery structure-pocket-inspection --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/openJiuwen-ai/sciencediscovery.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/structure-pocket-inspection .claude/skills/structure-pocket-inspection && 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
structure-pocket-inspection
GitHub stars
162
Token cost
~624 tokens
SKILL.md length
241 words
Files
2 (incl. scripts)
Skills in repo
23
Repo updated
First seen
Licence
Apache-2.0

At a glance

Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center.

  • Works in 5 steps: Confirm the input PDB path, the ligand… → Read the structure as untrusted… → Invoke the frozen bundled script at… → …
  • Reproducible first-pass structure and binding-site inspection before heavier modeling
  • SKILL.md covers Workflow, Examples and Quality gates
  • Runs Python scripts from its folder; calls python

What it does

Structure Pocket Inspection is an agent skill from openJiuwen-ai/sciencediscovery. Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center. Use for reproducible first-pass structure and binding-site inspection before heavier modeling.

Its SKILL.md is about 620 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/inspect_pdb.py`). Compatibility notes: Requires Python 3 standard library only; accepts local PDB files in an authorized workspace.

The repository describes itself as: ScienceDiscovery is an all‑in‑one agentic workbench built specifically for scientific research. The licence is Apache-2.0.

When your agent uses it

  • Reproducible first-pass structure and binding-site inspection before heavier modeling

Example prompts

  • “/structure-pocket-inspection”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Requires Python 3 standard library only; accepts local PDB files in an authorized workspace.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the input PDB path, the ligand residue name or Cartesian pocket center, and the requested distance cutoff.
  2. Read the structure as untrusted scientific data. Report malformed or unsupported records instead of guessing.
  3. Invoke the frozen bundled script at $SCIENCEDISCOVERY_SKILLS_DIR/structure-pocket-inspection/scripts/inspect_pdb.py with explicit…
  4. Save the JSON result in the workspace so its input, command, environment revision, logs, and output are captured by execution provenance.
  5. Report chain counts, residues, candidate ligand atoms, nearby residues, the cutoff, and limitations. Distinguish observed coordinates from…

What it can do on your machine

Read from SKILL.md and the folder at commit cc95884. 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 1 file 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.

  • Compatibility

    Requires Python 3 standard library only; accepts local PDB files in an authorized workspace.

    From compatibility in the SKILL.md frontmatter.

Context cost

Structure Pocket Inspection loads about 624 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 241 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~624

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); the scripts in this folder are not scanned.

SKILL.md

The full file from openJiuwen-ai/sciencediscovery at commit cc95884, republished under its Apache-2.0 licence (© openJiuwen-ai). 241 words, ~624 tokens.

Download SKILL.mdSave it as .claude/skills/structure-pocket-inspection/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
structure-pocket-inspection
description
Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center. Use for reproducible first-pass structure and binding-site inspection before heavier modeling.
compatibility
Requires Python 3 standard library only; accepts local PDB files in an authorized workspace.
metadata.version
1.0.0

Structure and pocket inspection

Use this method for a transparent first-pass analysis of a local PDB structure. It does not predict affinity, docking poses, or biological function.

Workflow

  1. Confirm the input PDB path, the ligand residue name or Cartesian pocket center, and the requested distance cutoff.
  2. Read the structure as untrusted scientific data. Report malformed or unsupported records instead of guessing.
  3. Invoke the frozen bundled script at $SCIENCEDISCOVERY_SKILLS_DIR/structure-pocket-inspection/scripts/inspect_pdb.py with explicit workspace paths and options. The complete package is already mounted read-only when the execution sandbox starts; do not copy the script, read its source into context, or search the filesystem for another copy. If the workspace already contains an equivalent user-owned script, invoke that script instead. Do not copy the structure into another proprietary format.
  4. Save the JSON result in the workspace so its input, command, environment revision, logs, and output are captured by execution provenance.
  5. Report chain counts, residues, candidate ligand atoms, nearby residues, the cutoff, and limitations. Distinguish observed coordinates from inferred biology.

Examples

The corresponding bundled-script arguments for residues within 5 Å of ATP are:

sh
python "$SCIENCEDISCOVERY_SKILLS_DIR/structure-pocket-inspection/scripts/inspect_pdb.py" structure.pdb --ligand ATP --cutoff 5 --output pocket.json

For residues within 6 Å of a known pocket center:

sh
python "$SCIENCEDISCOVERY_SKILLS_DIR/structure-pocket-inspection/scripts/inspect_pdb.py" structure.pdb --center 12.4 8.1 -3.0 --cutoff 6 --output pocket.json

Quality gates

  • Treat alternate locations and model ensembles conservatively; the bundled script analyzes the first model and keeps blank or A alternate locations.
  • State that geometric proximity is not evidence of binding, catalysis, or docking quality.
  • Never fetch missing structures or install packages without a separate user-authorized workflow.

© openJiuwen-ai, 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 1 other file (scripts) in skills/structure-pocket-inspection of openJiuwen-ai/sciencediscovery.

  • SKILL.md
  • scripts/inspect_pdb.py

Open the folder on GitHubat commit cc95884

Compare with similar skills

Structure Pocket Inspection 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.

Structure Pocket Inspection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Structure Pocket Inspection this skillopenJiuwen-ai/sciencediscovery162—~624Automated safety check: PassApache-2.0
Summarizeopenclaw/openclaw392k1 repos~531Automated safety check: PassMIT
Research Summarizeralirezarezvani/claude-skills28k1 repos~2.7kAutomated safety check: PassMIT
Node Inspect Debuggeropenclaw/openclaw392k1 repos~894Automated safety check: PassMIT
Sbom Supply Chainsickn33/agentic-awesome-skills47k2 repos~3.4kAutomated safety check: PassMIT
Agent Supply Chaingithub/awesome-copilot40k1 repos~2.7kAutomated safety check: PassMIT

Similar skills

  • Summarize

    openclaw/openclaw

    Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

    392k GitHub starsUsed in 1 repo~531 tokens
    Media & CreativeAuto-check passed
  • Research Summarizer

    alirezarezvani/claude-skills

    Structured research summarization agent skill for non-dev users.

    28k GitHub starsUsed in 1 repo~2.7k tokens
    Research & ScienceAuto-check passed
  • Node Inspect Debugger

    openclaw/openclaw

    Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

    392k GitHub starsUsed in 1 repo~894 tokens
    Frontend & DesignAuto-check passed
  • Sbom Supply Chain

    sickn33/agentic-awesome-skills

    Generate, sign, and verify SBOMs and provenance attestations to secure the software supply chain.

    47k GitHub starsUsed in 2 repos~3.4k tokens
    SecurityAuto-check passed
  • Agent Supply Chain

    github/awesome-copilot

    Official

    Verify supply chain integrity for AI agent plugins, tools, and dependencies.

    40k GitHub starsUsed in 1 repo~2.7k tokens
    SecurityAuto-check passed
  • Supply Chain Security

    zhaoxuya520/reverse-skill

    A skill your agent uses for software supply-chain security assessment covering SBOM, SCA, CI/CD pipelines, container images, build integrity, dependency provenance, and vulnerability reachability.

    41k GitHub starsUsed in 4 repos~953 tokens
    SecurityAuto-check: warnings

More from openJiuwen-ai/sciencediscovery

All 23 skills in this repo
  • Code Engineer

    openJiuwen-ai/sciencediscovery

    A skill your agent uses when you need to write and execute Python/R code to process, transform, and analyze data, delivering reproducible computational results with complete code-level methodology…

    162 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Gitcode

    openJiuwen-ai/sciencediscovery

    Operate GitCode issues, PRs, wikis, code/MR refs, and cached org templates.

    162 GitHub stars~4.3k tokensUpdated today
    Auto-check passed
  • Antibody Design

    openJiuwen-ai/sciencediscovery

    Prepare, launch, monitor, and summarize the real RFdiffusion to ProteinMPNN to Protenix antibody pipeline on a local or remote ScienceDiscovery Runner with sandboxed Ascend NPUs.

    162 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Science Research Team

    openJiuwen-ai/sciencediscovery

    A skill your agent uses to orchestrate a multi-domain research team for literature/evidence research and data analysis.

    162 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Literature Searcher

    openJiuwen-ai/sciencediscovery

    A skill your agent uses when a research workflow needs verified academic source retrieval through literature-search MCP interfaces available in the current session before evidence extraction.

    162 GitHub stars~5.8k tokensUpdated today
    Auto-check passed
  • Create GitHub PR

    openJiuwen-ai/sciencediscovery

    Open or update a pull request on GitHub's openJiuwen-ai/sciencediscovery: run the UT/ST/E2E layers locally, push the branch to the operator's own GitHub fork, write a body that says what was…

    162 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

Questions about Structure Pocket Inspection

What does Structure Pocket Inspection do?

Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center. Structure Pocket Inspection is an agent skill from openJiuwen-ai/sciencediscovery. Inspect a local PDB structure, summarize chains and residue composition, and identify protein atoms near a user-specified ligand or pocket center.

When should I use Structure Pocket Inspection?

Structure Pocket Inspection fits situations like: reproducible first-pass structure and binding-site inspection before heavier modeling.

How do I install Structure Pocket Inspection in Claude Code?

Run `npx skills add openJiuwen-ai/sciencediscovery --skill structure-pocket-inspection -a claude-code`. Or copy the skill folder (skills/structure-pocket-inspection in openJiuwen-ai/sciencediscovery) into .claude/skills/structure-pocket-inspection in your project. Claude Code loads it when a task matches its description.

How do I install Structure Pocket Inspection in Codex?

Run `npx skills add openJiuwen-ai/sciencediscovery --skill structure-pocket-inspection -a codex`. Or copy the skill folder (skills/structure-pocket-inspection in openJiuwen-ai/sciencediscovery) into .agents/skills/structure-pocket-inspection in your project. Codex loads it when a task matches its description.

Can I use Structure Pocket Inspection 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 openJiuwen-ai/sciencediscovery --skill structure-pocket-inspection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/structure-pocket-inspection, .gemini/skills/structure-pocket-inspection, .github/skills/structure-pocket-inspection and .opencode/skills/structure-pocket-inspection in your project.

What does Structure Pocket Inspection need to run?

Going by SKILL.md and its folder, Structure Pocket Inspection needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3. Compatibility (from SKILL.md): Requires Python 3 standard library only; accepts local PDB files in an authorized workspace..

Does Structure Pocket Inspection 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 Structure Pocket Inspection 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Structure Pocket Inspection use?

Structure Pocket Inspection is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Structure Pocket Inspection use?

About 624 tokens (SKILL.md is roughly 2.5k 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 Structure Pocket Inspection?

Skills that share tags, products or a category with Structure Pocket Inspection: Summarize (openclaw/openclaw, 392k stars), Research Summarizer (alirezarezvani/claude-skills, 28k stars), Node Inspect Debugger (openclaw/openclaw, 392k stars) and Sbom Supply Chain (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Structure Pocket Inspection?

openJiuwen-ai (a GitHub organization) maintains it in openJiuwen-ai/sciencediscovery, which has 162 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 11, 2026.

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