SkillFlux

    ↑ ↓ select↵ openSearch all of SkillFlux
    Browse directory

    This page provides source information and editorial guidance. Recommendations and trust labels do not mean every skill here was tested. Results for individual skills are on the skill data pages. See skill data · Listing policy

    Overview

    This selection from K-Dense covers two research-method skills: scientific-critical-thinking examines claims, study design and evidence limits, while scientific-brainstorming supports independent idea generation, explicit criteria and decision records. scientific-schematics is preserved as optional diagram support. This page analyzes that selection without implying the entire scientific toolkit was collected.

    SkillFlux sample check

    On 2026-10-31, SkillFlux pinned this source at commit 5f2bc03, drew a seeded sample of 20 from the 177 entries it contains, and ran static health check 1.0.0 on each. 65% had no failing check, said when to use the skill and carried a license.

    • 20/20sampled entries had a SKILL.md we could check
    • 0/20fail at least one check
    • 7/20do not say when to use the skill
    • 0/20have no license we could find
    • 17/20bundle scripts the agent may run
    • 3/20include scripts that call the network
    • 0/20include destructive shell commands
    • 3/20exceed the 5,000-token body guideline
    See the 20 sampled entries
    EntryResultFlags
    K-Dense-AI/scientific-agent-skills/skills/scientific-schematics15 pass, 0 warn, 0 failBundles scripts the agent may run, Scripts call the network
    K-Dense-AI/scientific-agent-skills/skills/lab-hardware-cad14 pass, 1 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/scvelo15 pass, 0 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/scientific-slides13 pass, 2 warn, 0 failBundles scripts the agent may run, Scripts call the network
    K-Dense-AI/scientific-agent-skills/skills/peer-review14 pass, 1 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/optimize-for-gpu15 pass, 0 warn, 0 fail—
    K-Dense-AI/scientific-agent-skills/skills/nmrglue15 pass, 0 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/scvi-tools15 pass, 0 warn, 0 fail—
    K-Dense-AI/scientific-agent-skills/skills/scholar-evaluation15 pass, 0 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/treatment-plans15 pass, 0 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/torchdrug15 pass, 0 warn, 0 fail—
    K-Dense-AI/scientific-agent-skills/skills/venue-templates14 pass, 1 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/pydicom14 pass, 1 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/pymatgen15 pass, 0 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/shap15 pass, 0 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/bioservices14 pass, 1 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/paper-lookup14 pass, 1 warn, 0 failBundles scripts the agent may run, Scripts call the network
    K-Dense-AI/scientific-agent-skills/skills/scanpy14 pass, 1 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/analytical-method-validation15 pass, 0 warn, 0 failBundles scripts the agent may run
    K-Dense-AI/scientific-agent-skills/skills/pymoo14 pass, 1 warn, 0 failBundles scripts the agent may run

    The sample reads files only; it does not run any skill and does not describe entries outside the sample. Flags describe what a skill contains; they are not verdicts. Raw data · Method

    What the skills help you do

    Inputs, methods and outputs described in the collected source version.

    Extract evidence before judging a claim

    Start with the question, sampling unit, results, denominators and uncertainty. Check whether design and analysis support the claim, while distinguishing missing reporting from a procedure not performed.

    Read the source instructions ↗

    Write a traceable critique

    Organize concerns by severity with a source location, observation, effect on the claim and feasible remedy. Treat reporting completeness, risk of bias and evidence certainty separately.

    Read the source instructions ↗

    Preserve reasoning and dissent in ideation

    Generate ideas independently before clustering, defining criteria, adversarial review and literature checks. Retain raw ratings, assumptions, dissent and the final decision rationale.

    Read the source instructions ↗

    Optionally draft scientific diagrams

    scientific-schematics accepts source-backed diagram descriptions and saves PNG drafts with review logs. Model scores help guide revision rather than establish journal acceptance.

    Read the source instructions ↗

    A typical workflow

    1. Choose appraisal or ideation

      Provide a claim and its materials for appraisal or a focused question for ideation, recording goals, known information and unknowns.

    2. Preserve evidence and idea provenance

      For appraisal, extract results with their locations. For ideation, generate independently and assign stable IDs with assumptions, predictions and provenance.

    3. Apply the appropriate evaluation process

      Choose appraisal frameworks for the study design or define ideation criteria in advance, then examine alternative explanations, disagreement and evidence gaps.

    4. Record a bounded next step

      Deliver a traceable critique or decision log with remaining searches, validation and expert review tasks. Generate diagrams separately when needed.

    Best for

    • Researchers who need to locate evidence behind a paper or scientific claim and distinguish risk of bias from certainty of evidence.
    • Research teams choosing directions who need to preserve dissent, evaluation reasons and follow-up validation tasks.

    Use cases

    SkillFlux notes

    The analysis covers the two main skills and the scientific-schematics support skill, based on their instructions, references, scripts and MIT licenses at a pinned snapshot, without behavioral testing. It is not a scientific finding or an execution test; Python packages and external APIs must be prepared separately.

    Installation and use

    Open the original repository and read its README, the selected skill instructions and any linked scripts. Check installation paths, host requirements, dependencies and licenses, then follow the project documentation to verify a small task in a workspace you can restore.

    Read the original Scientific Agent Skills source

    Limitations

    • Core analytical guidance works offline. Optional brainstorming utilities need Python 3.11+ and check structure or scoring records, not scientific truth.
    • Diagram support needs Python, requests, an OpenRouter key and network access, and sends content to an external service. It produces PNG drafts whose labels and relationships need human checking; idea scores do not replace validation or expert review.

    Alternatives

    Related entries4 sources

    VoltAgent’s awesome-agent-skills brings vendor-team and community skill sources together in a curated GitHub list. Its scope is broader than a single agent, making it useful for comparing source types before checking each project’s host requirements, installation method and capability scope.

    SkillsOpen-source reposOpen sourceGitHubGlobal
    View

    Composio’s awesome-claude-skills is a curated Claude Skills list on GitHub that organizes candidate resources by topic. It is useful for surveying capability areas and then following links to the projects that provide the implementations.

    SkillsOpen-source reposOpen sourceGitHubGlobal
    View

    A web-based directory of agent plugins from official and community providers, rebuilt daily, where you can assemble a stack and install it with one script. The site is published on GitHub Pages.

    Skills + PluginsOpen-source reposGitHubOpen sourceGlobal
    View

    A library of installable SKILL.md playbooks for Claude Code, Codex, Cursor, Gemini CLI and others, with AAS Core to search the local catalog, record chosen skills and preview a plan before changing a project. The README says Core does not rank or recommend skills.

    SkillsOpen-source reposGitHubOpen sourceGlobal
    View