Install
$ agentstack add skill-shikaijieskj-science-skills-science-response ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Science Reviewer Response
Use this skill to turn review comments and author notes into an auditable response package. The response letter should help the editor verify that every concern has a concrete answer.
Chinese trigger examples include 审稿意见回复, 逐点回复, 大修回复, 小修回复, and 如何回复 reviewer.
Default stance
- Preserve reviewer comments faithfully.
- Answer every editor and reviewer item.
- Map every claimed change to manuscript location, figure, table, supplement, citation, or
AUTHOR_INPUT_NEEDED.
- Do not invent experiments, analyses, citations, line numbers, figure panels, or changes.
- Prefer concise, evidence-linked replies over defensive explanations.
- If a response pushes back, first show that the concern was understood, then anchor the
disagreement in evidence, journal scope, or study design.
Open extra files
| File | Open when | |---|---| | [references/response-structure.md](references/response-structure.md) | Need full response-package anatomy and tracker fields | | [references/tone-and-traceability.md](references/tone-and-traceability.md) | Need disagreement phrasing, tone repair, or line/figure mapping | | [references/qa-checklist.md](references/qa-checklist.md) | Before finalizing or auditing a draft response |
Workflow
- Identify decision type: minor revision, major revision, revise-and-resubmit, transfer, reject
with invitation, or unclear.
- Extract editor instructions first and label them
E.1,E.2. - Split reviewer comments into
R1.1,R1.2,R2.1... - Classify each item:
data, analysis, method, statistics, writing, figure, citation, scope, ethics/policy, or misunderstanding.
- Assign action:
revised, new analysis, new experiment, clarified, added citation, justified no change, or AUTHOR_INPUT_NEEDED.
- Draft responses only after the tracker is complete.
- Run QA for completeness, traceability, factuality, and tone.
Output format
Response strategy summary
- Decision type:
- Overall posture:
- Major risks:
Comment-response tracker
| ID | Concern | Type | Severity | Action | Manuscript location | Missing input |
Draft point-by-point response
[letter]
Revision checklist
- [specific manuscript changes]
Risk flags
- [specific flags or "None"]
For Chinese author notes, write the submission-facing response in English and include a brief Chinese action checklist.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: shikaijieskj
- Source: shikaijieskj/science-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.