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 fmschulz/omics-skills --skill proposal-reviewgit clone --depth 1 https://github.com/fmschulz/omics-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/fmschulz/omics-skills/proposal-review)<a href="https://agentmods.dev/skills/fmschulz/omics-skills/proposal-review"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/proposal-review/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/fmschulz/omics-skills/proposal-review"><img src="https://agentmods.dev/badge/skills/fmschulz/omics-skills/proposal-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01287 |
| Opus 5.5 | $0.00017 | $0.00515 |
| Sonnet 5.5 | $0.00008 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
proposal-review 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 23d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal Review
Produce a decision-ready review of an AI/ML, computational biology, or bioscience proposal. Be fair, skeptical, and specific, and name missing information.
Instructions
-
Read the proposal and identify the decision context if provided: sponsor goals, rubric, budget cap, timeline, and risk tolerance.
-
If critical information is missing, do not invent it. Flag the gap and turn it into a prioritized question for the PI.
-
Structure the review with these sections:
- Executive summary
- Heilmeier catechism
- Technical merit
- Data, compute, and experimental resources
- Risk register
- Team and execution capability
- Ethics, safety, and compliance
- Budget and schedule realism
- Scorecard
- Decision and funding conditions
- Questions for the PI
-
Tailor the technical review to the proposal type:
- AI/ML: baselines, ablations, leakage prevention, calibration, external validation, compute realism
- Bio or wet lab: controls, replicates, statistical plan, assay feasibility, translational path
-
Include at least six risks covering technical, data or experimental, budget or timeline, and adoption or regulatory concerns when relevant.
-
If the sponsor supplies a rubric, use its categories, weights, and decision vocabulary. Otherwise use the default 1-to-5 scorecard below; do not mix sponsor and default weights.
-
Default weights: strategic fit and novelty 15%, technical rigor 25%, feasibility and resources 20%, team and execution 15%, risk, ethics, and compliance 15%, budget and schedule 10%.
-
Map the default weighted mean to
Strong Accept(>=4.5),Accept(>=3.7),Borderline(>=2.8), orReject(<2.8). A documented fatal flaw may override the numeric band. -
Keep the review concrete and action-oriented. Reference proposal details when available and name fatal flaws plainly.
-
For a machine-checked scorecard, write the scores to JSON and run the helper:
uv run --script "$HOME/.agents/skills/proposal-review/scripts/score_proposal.py" scorecard.json
What ships with it
1 file 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.
- 23d ago Changed · +2 lines · -5 tokens per session 6914b126e58e
- 1mo ago Changed · +13 tokens per session c0a9687697a1
- 1mo ago First seen · 106 lines · 34 tokens per session scan A 7fbc1602f403
proposal-review is a skill published in the GitHub repository fmschulz/omics-skills (11 stars, last pushed 23d ago), licensed MIT. It adds 42 tokens to every session and 1,287 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
imaging-data-commons
Queries and downloads public cancer imaging data from NCI Imaging Data Commons. Supports IDC collection discovery, DICOM access, radiology (CT, MR, PET) and pathology AI datasets, metadata SQL, visualization, licensing, and citations. Uses public metadata and download routes without authentication; optional BigQuery…
genomic-intelligence
Predicts regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
lab-hardware-cad
Designs custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a…
onekgpd
Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which…
relsa-severity-assessment
Supports multivariate severity assessment and exploratory endpoint-time score forecasting for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting. Use when combining welfare readouts — body weight or weight loss, body temperature, clinical or nesting…
scientific-slides
Builds slide decks and presentations for research talks. Used for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX…