force-rnn-sim
Skill0 starsChanged 5 months agoNo licenceView on GitHub
Use this skill to run FORCE algorithm RNN simulations from Sussillo & Abbott 2009 (Neuron) and Sussillo & Barak 2013 fixed-point analysis. Trigger whenever the user mentions 'FORCE algorithm', 'FORCE 演算法', 'FORCE simulation', 'Sussillo FORCE', 'chaotic RNN training', 'RLS recurrent network', 'fixed point analysis', 'opening the black box', or wants to train a recurrent neural network to produce a target dynamical pattern (sinusoid mixture or Lorenz attractor). Also trigger for: 'demo FORCE', '跑 FORCE', 'computational neuroscience RNN demo', 'reservoir computing demo', 'Lorenz attractor RNN', 'Stage 3 computational neuroscience', 'Stage 4 fixed point', 'slow manifold analysis'. Skill produces PNG figures. Four variants: sinusoid (FORCE-Output, ~30s), lorenz-output (FORCE-Output on chaotic target, ~30s), lorenz-internal (FORCE-Internal v3 phase-split, ~6min, matches paper Fig 3 with clean butterfly), fixed-points (Sussillo & Barak 2013 fixed-point analysis on trained v3 network, ~45s, requires v3 to have run first). Do NOT trigger for general RNN/LSTM training, gradient descent, BPTT, transformer training — this skill is specifically for FORCE/RLS-based recurrent training and its dynamical-systems analysis.
- Installs packages
In this repository44 other files it gives its agents.
- jev-autoresearch-rsi/AGENTS.mdAGENTS.md
- jev-engineering/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- jev-engineering/CLAUDE.mdCLAUDE.md
- voice2txt/CLAUDE.mdCLAUDE.md
- admission-noteSkill
- article-writerSkill
- classroom-voteSkill
- cognitive_task_pilot_skillSkill
- cognitive-test-to-samdSkill
- dashboard-builderSkill
- data-analyzerSkill
- datapilotSkill
- ddm-simulatorSkill
- design-deploy-ios-appSkill
- email-assistantSkill
- end-of-daySkill
- hhsa-clinical-timeseriesSkill
- hhsa-closed-loop-prototypingSkill
- install-skill-packSkill
- jev-autoresearch-rsiSkill
- knowledge-baseSkill
- lecture-notesSkill
- litreview-agentSkill
- materials-to-pptxSkill
- mcp-obsidian-setupSkill
- medicloud-word-captureSkill
- meeting-minutesSkill
- mortality-analysisSkill
- neuropilotSkill
- neuropsych-dementia-ddxSkill
- openclaw-automationSkill
- personal-medical-websiteSkill
- publish-lab-blogSkill
- research-3d-publication-packSkill
- research-organizerSkill
- resume-tailorSkill
- rsi-knowledge-dashboardSkill
- soil-deck-pipelineSkill
- soil-html-deckSkill
- soil-image-deckSkill
- soil-teaching-deckSkill
- yangming-council-recordSkill
- interactive-website-designerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.