Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Aperivue/medsci-skills --skill publish-skillgit clone --depth 1 https://github.com/Aperivue/medsci-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aperivue/medsci-skills/publish-skill)<a href="https://agentmods.dev/skills/aperivue/medsci-skills/publish-skill"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/publish-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aperivue/medsci-skills/publish-skill"><img src="https://agentmods.dev/badge/skills/aperivue/medsci-skills/publish-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 321 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 325 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 359 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 369 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.03569 |
| Opus 5 | $0.00020 | $0.01784 |
| Sonnet 5 | $0.00008 | $0.00714 |
| Haiku 4.5 | $0.00004 | $0.00357 |
Grade A, and why
publish-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: publish-skill
Convert a personal agent skill into a clean, distributable, open-source-ready skill package. This skill walks through a 7-phase pipeline that audits for personally identifiable information, generalizes language and role assumptions, verifies license compatibility, checks cross-platform adapter needs, and prepares the final package for commit.
Communication Rules
- Communicate with the user in their preferred language
- Use English for technical terms (PII, MIT, CC BY, GPL, YAML frontmatter)
- Present audit findings in structured tables
Phase 0: Init and Identify Source
Required Inputs
Collect from the user:
- Source skill path: directory containing the personal skill (e.g.,
~/.claude/skills/my-skill/or~/.agents/skills/my-skill/) - Target package path: directory of the distributable package (e.g.,
~/workspace/<your-package>/) - Target license: license of the package (default: MIT)
Actions
- Read
SKILL.mdfrom the source skill directory - Inventory all files recursively (
ls -R) - Classify skill type:
- Standalone: self-contained skill with no agent delegation
- Orchestrator: delegates to sub-agents (NOT suitable for distribution without refactoring)
- Wrapper: thin wrapper around another tool/API
- Present inventory table to the user:
| File | Lines | Type | Notes |
|------|-------|------|-------|
Gate: User confirms source skill and target package before proceeding.
Phase 0.5: Skill-Worthiness Gate
Before spending effort on PII scrubbing and generalization, confirm the workflow is worth distributing as a skill at all. A skill earns its place by encoding a reusable decision heuristic, a hard-won constraint, or a verification step — not a snippet anyone could reconstruct in five minutes. Apply all three gates; any "no" (or "yes" on the inverse) stops publication in favor of documentation or a memory note instead.
| Gate | Question | Pass condition |
|---|---|---|
| Uniqueness | Could a competent user get the same result by searching the web for ~5 minutes, or by asking a general assistant with no skill installed? | No |
| Specificity | Does it encode a workflow, decision heuristic, constraint, or convention specific to this domain or a recurring task — rather than a generic code snippet or a standard-library example? | Yes |
| Effort | Did discovering it take real debugging, study design, operational effort, or a reviewer-anticipation lesson (a pitfall, a verification step, a domain convention)? | Yes |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 371 lines · 40 tokens per session scan A a81e8783f294
publish-skill is a skill published in the GitHub repository Aperivue/medsci-skills (292 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 3,569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clinical-trials-search
Search ClinicalTrials.gov with natural language queries. Find clinical trials, enrollment, and outcomes using Valyu semantic search.
shidi
A Chinese-language research assistant role that turns a user’s ideas into literature reviews, experiment plans, figures and organised data.
clinical-research
Use when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging), estimating sample size and power for two-arm designs (means / proportions / survival), or scoring a study plan for feasibility and a GO /…
sr-search-record
An automated literature-review search and screening workflow using OpenAlex, an open database and API for scholarly research, and Zotero, a reference manager.
review-synthesis
A literature-review workflow that combines evidence from the full text of selected research papers into a findings document. It uses different review methods for systematic, semi-systematic, and integrative reviews.
review-draft
A workflow for expanding a first draft of a review article into a structured academic manuscript. A review article combines and organizes existing research rather than reporting a new experiment.