← Back to Skills Marketplace
heyheya11

Case Echo

by heyheya11 · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
81
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install case-echo
Description
extract simple structured json fields from a short chinese medical case description. use when the user provides a brief chinese case summary and wants standa...
README (SKILL.md)

Case Echo

Extract structured JSON fields from a short Chinese medical case description.

Use this skill for

  • short case summaries in Chinese
  • quick field extraction from one paragraph of case text
  • converting semi-structured case text into simple JSON
  • standardizing obvious fields before downstream analysis

Fields

Extract these fields when present:

  • sex
  • age
  • diagnosis
  • stage
  • egfr
  • pd_l1
  • brain_metastasis
  • raw_text

Execution

Run the bundled shell script and pass the original case text as one quoted argument:

bash scripts/run_case_echo.sh "\x3CUSER_CASE_TEXT>"

Replace \x3CUSER_CASE_TEXT> with the user's original case text.

Output rules

  • Return valid JSON only.
  • Do not add explanation before or after the JSON.
  • Keep missing fields as null.
  • Do not invent values not present in the input text.
  • This skill only structures text. It does not provide diagnosis or treatment recommendations.
Usage Guidance
This skill appears coherent and limited to parsing provided Chinese case text into JSON. Before installing: 1) Ensure python3 is available on the host (the SKILL.md should declare this dependency). 2) Treat any input as protected health information — avoid feeding real patient-identifiable data unless you have appropriate consent and controls. 3) Test with non-sensitive examples to confirm the output format meets your needs; the extraction is regex-based and intentionally simple, so it may miss or mis-handle nonstandard phrasing. 4) If you need production use, consider reviewing/expanding the extraction patterns or adding logging/privacy controls.
Capability Analysis
Type: OpenClaw Skill Name: case-echo Version: 0.1.0 The skill is vulnerable to shell injection in `scripts/run_case_echo.sh`, as it passes unvalidated user input (`$1`) directly into a shell command. While the Python logic in `scripts/extract_case.py` is a benign regex-based parser for medical text, the execution wrapper in `SKILL.md` and the shell script could allow an attacker to execute arbitrary commands via shell metacharacters (e.g., backticks or command substitution) within the case text.
Capability Assessment
ℹ Purpose & Capability
The name/description (extract structured fields from Chinese case text) aligns with the included scripts which perform regex-based extraction. Minor mismatch: SKILL metadata lists no required binaries, but the runtime instruction and scripts invoke python3, so the skill implicitly requires a python3 runtime to be available.
✓ Instruction Scope
SKILL.md instructs running the bundled shell script with the case text as a single argument. The scripts only read the provided text and return JSON; they do not access other files, environment variables, or external endpoints.
✓ Install Mechanism
Instruction-only installation (no install spec). Two small local scripts are bundled; nothing is downloaded or extracted from external URLs.
✓ Credentials
The skill requests no environment variables or credentials. The code does not attempt to read secrets or unrelated env vars.
✓ Persistence & Privilege
The skill is not always-enabled and does not modify agent/system configuration. It runs only when invoked and has no elevated persistence or privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install case-echo
  3. After installation, invoke the skill by name or use /case-echo
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
initial public release
Metadata
Slug case-echo
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Case Echo?

extract simple structured json fields from a short chinese medical case description. use when the user provides a brief chinese case summary and wants standa... It is an AI Agent Skill for Claude Code / OpenClaw, with 81 downloads so far.

How do I install Case Echo?

Run "/install case-echo" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Case Echo free?

Yes, Case Echo is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Case Echo support?

Case Echo is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Case Echo?

It is built and maintained by heyheya11 (@heyheya11); the current version is v0.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments