Skip to content
Skills Library
Programming · Automation

script-hopper-analysis

/script-hopper-analysis

Automate repeatable Hopper analysis with its installed Python SDK or extension APIs. Use for deterministic queries, controlled annotations, structured exports, or a scriptable document operation with a checkpointed evidence trail.

Repository
socket ↗
Licence
Apache-2.0
Last repository change
26.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
3
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.08.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Automate repeatable Hopper analysis with its installed Python SDK or extension APIs. Use for deterministic queries, controlled annotations, structured exports, or a scriptable document operation with a checkpointed evidence trail.

Original author description

Automate repeatable Hopper analysis with its installed Python SDK or extension APIs. Use for deterministic queries, controlled annotations, structured exports, or a scriptable document operation with a checkpointed evidence trail.

How it works

  1. Overview
  2. Workflow
  3. Guardrails
  4. Output
Original SKILL.md headings · 45 lines, 368 words
SKILL.md preview
---
name: script-hopper-analysis
description: Automate repeatable Hopper analysis with its installed Python SDK or extension APIs. Use for deterministic queries, controlled annotations, structured exports, or a scriptable document operation with a checkpointed evidence trail.
metadata:
  hermes:
    category: reverse-engineering
    tags: [hopper, python, automation]
---

# Script Hopper Analysis

## Overview

Use Hopper's installed Python SDK for narrow, repeatable document operations. Keep the script, its inputs, the document checkpoint, and its output together so another analyst can reproduce or review the transformation.

Read [references/hopper-automation-and-mcp.md](references/hopper-automation-and-mcp.md) for SDK discovery, mutation controls, MCP separation, and canonical sources.

## Workflow

1. Establish a document checkpoint.
   - Hash the input, save the Hopper document, and record the selected image, architecture, cursor or procedure scope, and Hopper version.
   - Do not let the first script run be the only copy of analyst work.

2. Discover the local SDK rather than guessing imports.
   - Use the installed Hopper help and resource bundle to locate the shipped Python API modules and examples.
   - Verify the active Python runtime can import the discovered API before writing an analysis script.

3. Write the smallest operation.
   - Prefer a query or structured export first.
   - Limit any transformation to an explicit procedure, address range, or selected document; do not sweep every procedure by default.

4. Run with an explicit mode.
   - Label the run `read-only`, `proposed-edit`, or `applied-edit`.
   - For an applied edit, preserve the pre-edit checkpoint and record each mutation class: comment, name, type, procedure, bookmark, or patch.

5. Verify in Hopper.
   - Reopen or refresh the affected document view and compare a sample of output with the assembly and pre-run state.
   - Report failed imports, unavailable APIs, and unsupported operations as calibration findings rather than substituting guessed output.

6. Preserve the evidence package.
   - Keep script source, dependency/runtime identity, parameters, stdout or logs, structured output, affected addresses, and final document checkpoint.

## Guardrails

- Do not overwrite the only Hopper document or original artifact.
- Do not treat SDK imports observed in another Hopper version as a contract for the installed version.
- Do not combine remote-model calls with a script without explicit approval for the selected artifact data.
- Use `$connect-hopper-mcp` instead of inventing an MCP transport in a Python script.

## Output

Return the Hopper and Python identities, document checkpoint, script purpose and mode, exact scope, observed output, mutations if any, verification sample, and retained evidence paths. For SDK discovery only, state `preflight only; no script or document mutation performed`.
Files in this package (3)
  • SKILL.md 3 KB
  • agents/openai.yaml 1 KB
  • references/hopper-automation-and-mcp.md 2 KB

Versions

The database has no other skills named script-hopper-analysis.

Identical content appears in 1 other GitHub folders. We show one copy with the highest score.

Database snapshot: 13.11.2026 · package version e18d06860d8e (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 87hopper-hq
    Use when the user asks to open the Hopper HQ building or view their coding-agent sessions in Hopper.
  • 87setup
    Use when setting up the Hopper HQ Codex plugin or repairing a missing Hopper CLI prerequisite.
  • 95kernelwiki
    Use when the user asks about optimizing NVIDIA Blackwell (SM100, B200) or Hopper (SM90, H100) GPU kernels — tcgen05/TMEM/CLC/NVFP4/2-SM cooperative, warp specialization, FlashAttention-4, DeepGEMM, FlashMLA, MoE, grouped GEMM, CuTe-DSL/PTX/Triton on Blackwell, or wants concrete…
  • 100python-sdk
    Python SDK patterns for Opik. Use when working in sdks/python, on SDK APIs, integrations, or message processing.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.