Borrowing it
Nothing to install: this file belongs to gaotiexinqu/OneResearchClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gaotiexinqu/OneResearchClaw/main/.cursor/skills/grounded-review/SKILL.mdgit clone --depth 1 https://github.com/gaotiexinqu/OneResearchClawWrote 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/gaotiexinqu/oneresearchclaw/grounded-review)<a href="https://agentmods.dev/skills/gaotiexinqu/oneresearchclaw/grounded-review"><img src="https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/grounded-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/gaotiexinqu/oneresearchclaw/grounded-review"><img src="https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/grounded-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 361 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00031 | $0.13643 |
| Opus 5 | $0.00015 | $0.06821 |
| Sonnet 5 | $0.00006 | $0.02729 |
| Haiku 4.5 | $0.00003 | $0.01364 |
Grade A, and why
grounded-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 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 — 1,451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grounded Review
This skill performs the quality-gating and repair stage of the middle layer.
It reads:
- the grounded note,
- the literature result,
- the report draft,
- optional supporting research artifacts,
and produces:
- a review diagnosis and score report
- a review state file
- a final deliverable research report
This skill is not a broad search skill and not an output rendering skill. It sits between:
grounded-summary- and the final output-formatting/rendering stage
Position in the pipeline
The intended pipeline is:
grounding -> grounded-research-lit -> grounded-summary -> grounded-review -> output rendering
This means:
grounded-summarywrites the main report draftgrounded-reviewscores, diagnoses, repairs, re-checks, and finalizes that draft- output skills then present that final report as pdf / docx / md / slides / audio / charts / fancy formats
grounded-review should therefore behave like a quality gate with bounded repair, not like a second compression stage.
Purpose
The purpose of this skill is to turn a substantial report draft into a final deliverable research report through:
- structured evaluation,
- weakness diagnosis,
- bounded repair,
- re-evaluation,
- finalization.
It should:
- preserve the core structure and substance of the report draft
- improve evidence alignment
- catch overclaiming
- restore missing important technical details if the draft still lost them
- improve section balance and readability
- strengthen explicit linkage between grounded findings and literature evidence
- remove search-process noise from the report body
- make the report suitable for downstream output-format skills
- act as a quality gate, not just a surface editor
It should not:
- perform an unrestricted new literature search
- invent new claims not grounded in the existing inputs
- radically change the research direction
- rewrite a rich report into a shorter but thinner version
- act as a presentation-formatting skill
- run an unbounded self-improvement loop
What ships with it
6 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 · 1,451 lines · 31 tokens per session scan A 1d942787e773
grounded-review is a skill published in the GitHub repository gaotiexinqu/OneResearchClaw (446 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 13,643 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
quantum-qiskit
Reference qiskit 2.x patterns for variational quantum machine learning. Covers data-encoding feature maps, variational quantum classifier (VQC) training, variational quantum eigensolver (VQE) for chemistry, matrix-product-state circuits, and noise model integration. Use when writing Python code that imports qiskit…
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
fba-simulator
Run Flux Balance Analysis (FBA) and related constraint-based simulations using COBRApy. Covers standard FBA, parsimonious FBA (pFBA), Flux Variability Analysis (FVA), loopless FBA, gene/reaction knockouts, and carbon source swapping. Outputs flux distributions and CSV files.
gsmm-validator
Validate a COBRApy genome-scale metabolic model for mass/charge balance, stoichiometric consistency, biomass producibility, dead-end metabolites, thermodynamic loops, and GPR rule formatting. Outputs a structured validation report with errors and warnings.
metabolic-study-planner
Plan publishable constraint-based metabolic modelling studies when the user has a broad biological or metabolic-engineering topic but no concrete dataset, organism, model, or hypothesis. Selects feasible BiGG/COBRA models, objectives, perturbations, analyses, metrics, figures, and risk controls before FBA code is…
gsmm-builder
Build or load a genome-scale metabolic model (GSMM) using COBRApy. Covers loading from BIGG, constructing minimal models from scratch, setting medium constraints, and exporting validated .json model files.