xushuwenn/redact/medchem-ro5-pass
Claude Code and agent skill by xushuwenn/redact
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Detect problematic functional groups in molecules using medchem CommonAlertsFilters.
Install
npx vskill@latest install xushuwenn/redact/medchem-ro5-passSKILL.md
Common Alerts Filter with medchem
When to Use
- Detect problematic functional groups in molecules
- Use medchem CommonAlertsFilters
- Follow task-specific implementation constraints exactly: use the required library/API directly, and do not substitute RDKit or another chemistry library unless the task explicitly allows it.
- Check if molecule passes safety criteria
Input
/root/input.txt: SMILES input- Do not assume exactly one molecule unless the file clearly contains only one record; if multiple non-empty molecule rows are present, process every row exactly once.
Output Format
To /root/output.txt:
A molecule PASSES if:
- status is "ok", OR
- status is "annotations" with 0 alert reasons
- If the task input contains multiple molecule records or IDs, emit one result block/line per input record in the required task format, and ensure the output covers all records.
New Section
Execution Checklist
- Write the required results to
/root/output.txtbefore declaring completion. - If
/root/input.txtcontains multiple molecule rows, process every non-empty record exactly once. - Before finishing, verify output cardinality: the number of result blocks/lines matches the number of input records, and any summary totals agree.
- Follow task-level and system-level protocol exactly when present (required library/API, tool-call schema, or completion formatting). Higher-priority instructions override this skill's examples.
- If the environment requires an exact completion string (for example,
ACTION: TASK_COMPLETE), output that exact string verbatim as the final chat message and nothing else. - Do not summarize results in chat after writing the file unless the task explicitly asks for it.
Using medchem
Alert Detection
- CommonAlertsFilters detects problematic functional groups
- Count number of alerts
- Determine pass/fail based on status
- Process every molecule present in the input source.
- Before finishing, verify the number of output result blocks matches the number of input molecules/records.
- If you include totals or pass/fail counts, reconcile them against the full input set.
Tips
- Check status field to determine pass/fail
- Zero alerts means pass (yes)
- Handle different status return types
- Before coding, verify all hard constraints: required library, exact input/output paths, and exact output format.
- For batch inputs, count input records first and reconcile them with the final output.
- Re-read task-specific output requirements before finishing; if the task requires an exact completion string or response format, use it verbatim.
- Do not claim the result is fully compliant unless you checked all stated task and environment constraints.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingdata/skills/trace2skill/skills_raw/error_only/medchem-ro5-pass/SKILL.md
Popularity
- Repository stars
- 13
- 7-day trend score
- 18
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/xushuwenn/redact/medchem-ro5-pass)