ProfSynapse
- 97 skills
- 0 followers
- 158 repo stars
- last month last updated
- ▌ Professor Synapse 4 · profsynapse bundleUse when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
- ▌ Professor Synapse 5 · profsynapse bundleUse when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
- ▌ Professor Synapse 6 · profsynapse bundleUse when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
- ▌ Evaluation 2 · profsynapse bundleComplete reference for the config-first model evaluation system. Covers the Evaluator CLI, assertion-driven YAML scenarios, response views, backend configuration, presets, scoring, LLM-as-judge, model comparison, and HuggingFace integration. Use when evaluating models, writing test prompts, comparing training runs, or interpreting eval results. This skill is about USING the evaluation system via CLI and YAML.
- ▌ Fine Tuning 2 · profsynapse bundleComplete reference for the fine-tuning pipeline (SFT, KTO, GRPO), cloud HF Jobs workflows, autonomous experiment search, checkpoint evaluation, and LoRA surgery. Covers training CLI flags, YAML configuration, model presets, dataset requirements, LoRA settings, training monitoring, hyperparameter search, and post-training optimization. Use when training models, configuring training runs, choosing hyperparameters, running cloud experiments, inspecting HF jobs, or troubleshooting training issues. This skill is about USING the training system via CLI and YAML — never modifying source code.
- ▌ Case Studies 2 · profsynapse bundleEnd-to-end case studies showing how to implement the full training pipeline for different skill types. Covers three complete worked examples — tool-calling training, essay-style training, and agentic search (RAG agent) training — demonstrating dataset design, synthetic generation, validation, fine-tuning, evaluation, and iteration. Use when onboarding to the project, understanding how all components fit together, explaining the pipeline to others, or planning a new training capability. This skill is about UNDERSTANDING the system holistically — reference the other skills for specific CLI commands.
- ▌ Upload Deployment 2 · profsynapse bundleComplete reference for model upload and deployment. Covers HuggingFace upload, save strategies (LoRA, merged 16-bit, merged 4-bit), GGUF conversion, model merging, model cards, and the full upload workflow. Use when uploading models, creating GGUF files, merging LoRA adapters, or deploying to HuggingFace. This skill is about USING the upload/deployment tools via CLI — never modifying source code.
- ▌ Dataset Publishing 2 · profsynapse bundlePublish local dataset artifacts to a Hugging Face dataset repo. Use when uploading a JSONL dataset, pushing a filtered dataset variant, syncing a matching .metadata.json sidecar, or renaming a dataset file in the target repo. This skill is about USING the checked-in dataset publish script via CLI — never ad hoc Python.
- ▌ Embedding Training 2 · profsynapse bundleComplete reference for the embedding fine-tuning pipeline (SentenceTransformers bi-encoders) — the `embedding` training method, model registry, dual loader (Unsloth fast path + ST fallback), adapter modes (full/lora/frozen_head), triplet/pairs dataset format, retrieval evaluation (recall@k/MRR/nDCG/MAP via the `retrieval` verifier), and the local-Docker smoke recipe. Use when training a retrieval embedder, picking a base model + adapter mode, preparing triplet data, or evaluating a fine-tuned embedder against a labeled corpus. This skill is about USING the embedding pipeline via CLI and YAML — never modifying source code.
- ▌ Research Reporting 2 · profsynapse bundleCreate structured research notes from experiment runs and analysis artifacts. Use when creating a note at run launch, updating it as training/evaluation/loss stages finish, summarizing a finished run, comparing experiment outcomes, extracting hypotheses from eval/loss artifacts, or proposing next-run actions grounded in `.tracking/experiments/<id>/analysis/` outputs. This skill is about turning repo-native experiment evidence into stable, machine-readable markdown.
- ▌ Transcript Distillation 2 · profsynapse bundleTurn local agent transcripts (Claude Code, Codex CLI, or any format with an adapter) into high-quality fine-tuning rows. Use when someone wants to mine their own coding-agent conversation logs into an SFT/KTO/DPO/GRPO dataset — parse the logs, extract substantive turns, scrub secrets, score each session by outcome (tests passed / built clean / committed / PR'd), dedup, and tier by quality. Config-driven and format-pluggable; point it at a transcript directory and it produces deduped, quality-tiered JSONL. This skill is about USING the checked-in distill engine via CLI + YAML.
- ▌ Synthetic Data Generation 2 · profsynapse bundleComplete reference for the SynthChat synthetic dataset generation system. Covers CLI commands (generate, improve, validate), scenario YAML authoring, rubric YAML authoring, settings configuration, evaluation, and full workflow. Use when generating datasets, writing rubrics/scenarios, configuring models/workers, improving dataset quality, or running evaluations. This skill is about USING the system via CLI and YAML — never modifying source code.
- ▌ Kg Ingest 2 · profsynapse bundleIngest a research paper (or a batch) into the library's atomic knowledge graph the Agents-K1 way. Use when you are handed a paper (URL, arXiv id, or a note already in library/) and you want it folded in as typed concept atoms, mechanisms, lineage edges, and a patched paper note, reconciled against the atoms already in the vault rather than re-extracted from scratch. Also use to backfill spine papers not yet atomized. This is the standing ingestion posture for growing the graph one paper at a time.
- ▌ Experiments 2 · profsynapse bundleLifecycle tooling for the experiments-first repo layout, with one self-contained directory per evidence-producing experiment, signed amendment, machine-readable manifest, pinned instrument, and generated index. Use to scaffold, sign, inspect, resolve, validate, or regenerate experiments; check machine-local input readiness; and apply the shared-input promotion rule.
- ▌
- ▌ Data Exhaust 2 · profsynapse bundlePackage a terminal experiment's data exhaust (aggregate stats and, where license-permitted, row-level generation text) into reproducible Hugging Face datasets, with a license gate, containment lint, and a thin uploader. Use when an experiment under experiments/<slug>/ reaches a terminal verdict (resolved, null-result, or falsified) and its analysis-committed/ artifacts should be published.
- ▌ Family Atlas 2 · profsynapse bundleStandardize the per-model layer-mapping extraction (full-depth hidden-state capture, workspace-dimension profile, three-axis held-out read panel) so any new model, family, or size entering the Epistemic-Humility program gets a fast, cheap, uniform layer atlas before any actuation design. Use when a new model/family/size enters the program, before designing any per-family actuation cell, or when an existing family's substrate changes (new revision, new checkpoint).
- ▌ Task Backlog 2 · profsynapse bundleTask-backlog lifecycle tooling for the Epistemic-Humility-Research repo - one markdown file per task under backlog/{tasks,drafts,completed}, a bin/task CLI (new/list/show/claim/release/review/done/validate), a generated TODO.md table, and a pre-commit commit gate that requires gated work files to be covered by an active task. Use to mint, claim, and close backlog tasks, to bind a task to an experiments/<slug>/ record, and to understand the commit-gate scope and escape hatch. Tasks point at experiments; experiments keep their own lifecycle under bin/exp and AMENDMENT.md.
- ▌ Knowledge Graph 2 · profsynapse bundleCreate, validate, normalize, export, and analyze typed Obsidian knowledge graph metadata in the Professor Synapse vault, including `kg` node metadata, `relationships` edge objects, `related` link projections, ontology-governed edge types, legacy relationship shorthand, and graph analysis reports.
- ▌ Mechinterp Cells 2 · profsynapse bundleAuthor, organize, and launch tuner-backed mechanistic-interpretation cells (activation reading and writing) for the Epistemic-Humility project. Use when designing a new steering / extraction / probe-fit / gate-scoring cell, deciding where its config, direction, grader, and outputs live, or launching one locally or on Modal. This skill is about USING the synaptic-tuner `mechinterp` verbs via declarative recipe YAML plus project plug-ins; it never modifies the tuner submodule and never touches the frozen legacy machinery.
- ▌ Experiment Runner 2 · profsynapse bundleOperational runbook for the Epistemic-Humility Locked Matrix Experiment Runner - expands the PROTOCOL v0.3 (LOCKED) run matrix (3-seed headline + LR/beta sensitivity panel at 4B, 3-seed confirm at 8B, 2 bridge replication cells) into per-cell tuner invocations across two lanes (local RTX 3090 / HF Jobs cloud), with hard pre-registration count assertions, prerequisite gating, data staging, and committed provenance run records. Use when launching, dry-running, or gating the locked matrix, materializing per-cell recipes, or inspecting run records. This skill is about USING the runner via checked-in scripts; it never modifies the synaptic-tuner submodule.
- ▌ Experiment Wrapup 2 · profsynapseExecute the downstream wrap-up after a signed experiment produces its terminal numbers and the LEAD has adjudicated the verdict - write the AMENDMENT Outcome, run bin/exp resolve, update the cross-experiment registries (family-layer-map for atlas cells, prediction-scoreboard for scored cells), open the resolve PR, commit the living tracking docs to main, and hand off KG ingest. This is the mechanical half of a resolve and is delegable to a smaller model, given a locked adjudication packet from the lead. It never decides the verdict, the falsifier call, or the scoreboard scores - those are lead-only judgment and are inputs to this skill, not outputs of it.
- ▌ Mech Interp Runner 2 · profsynapse bundleRun, plan, validate, or aggregate Epistemic-Humility local mechanistic-interpretability sweeps, including hidden-state candidate inventories, causal-pilot sweep planning, explicit non-GPU/GPU gates, base-original skip handling, and offline result aggregation. Use when working on local mech-interp sweeps, causal-pilot diagnostics, activation-addition/logit-diagnostic runs, behavior-axis scans, SAE feature screens, or future reruns of the legacy full candidate inventory.
- ▌ Nexus Agents 2 · profsynapse bundleHow to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy. Use when adding or modifying an agent or tool, when a documented command does not resolve, when wiring registration or capability gating, or when touching the ToolManager payload shape.
- ▌ Nexus Release 2 · profsynapse bundleCut a Nexus release — bump the version with the repo's own machinery, get the docs and generated sources right, push a tag the GitHub Actions workflow will actually pick up, and recover when it does not. Use when asked to release, publish, ship, cut a release, bump the version, or tag a version, and when a release workflow did not fire, failed its version guard, or produced the wrong assets.
- ▌ Nexus Storage 2 · profsynapse bundleHow to change, persist, migrate and recover Nexus data without losing it. Use when adding a SQLite table or column, persisting anything that must survive a restart or a cache rebuild, resolving a vault or plugin storage path, or debugging missing, stale, duplicated or post-rebuild-vanished data.
- ▌ Nexus Testing 2 · profsynapse bundleVerify a Nexus change — pick a Jest lane, write a test that can actually fail, run the in-app Obsidian CLI loop, drive the eval harness, or fix a shipped-docs drift failure. Use when adding or changing tests, when a mock might be deciding the outcome, when a change has to be proven in the running plugin, or when the guidance gate fails.
- ▌ Nexus Model Eval 2 · profsynapse bundleGrade how well a model drives the Nexus two-tool protocol (getTools/useTools) and decide whether a low score is the model's fault or the harness's. Use when asked to grade, benchmark, rank or compare models on Nexus tool use, when picking a default model, or when an eval report needs interpreting.
- ▌ Nexus UI Mockups 2 · profsynapse bundleDesign a Nexus UI change as a standalone mockup under docs/mockups/ before any production code, then hand it off as the visual contract a plan implements against. Use when asked for a new view, panel, modal, settings tab, chat surface, or layout refactor, when revising or superseding an existing mockup, or when a plan needs something visual to be blessed against.
- ▌ Nexus Eval Harness 2 · profsynapse bundleWork on the Nexus LLM eval harness in tests/eval/ — author or fix a scenario fixture, write an eval config, change the executors, assertions or reports, or explain a run that produced nothing, everything-fails, or numbers that disagree. Use when an eval scenario is wrong, a run behaves oddly, or the harness itself needs to change. To grade a model rather than change the harness, use nexus-model-eval.
- ▌ Nexus LLM Adapters 2 · profsynapse bundleHow to add or debug a Nexus LLM provider adapter — what every adapter must wire, how to verify it against a live provider, and the failure modes that produce a silently blank chat. Use when adding or changing a provider adapter, debugging streaming or reasoning display, working with local or CLI-backed models, or touching chat branch plumbing.
- ▌ Nexus Tool Schemas 2 · profsynapse bundleExport the live CLI-first Nexus tool catalog as JSON — the whole registry or a selector-picked subset — and refresh the committed catalog that the repo's guidance and drift tests read. Use when someone asks for tool schemas or the exact command/argument shape a caller sees, after changing a tool's parameter schema, slug or description, after touching ToolCliNormalizer, or when a catalog-backed test fails.
- ▌ Nexus Mobile Compat 2 · profsynapse bundleKeep Nexus loading on mobile and compliant with the Obsidian plugin store — vet a dependency, import without crashing init, confine a vault path, and prove none of it regressed with the reachability checker. Use before adding an npm package or a Node import, when writing to caller-supplied vault paths, when gating a desktop-only feature, when a PDF or worker-backed feature misbehaves, or when the plugin fails to load on a phone.
- ▌ Nexus Model Updates 2 · profsynapse bundleAdd, change or verify a Nexus LLM model definition — the registry entry, the provider default, and proof the model id actually works against the live endpoint. Use when adding a newly released model, editing model metadata such as pricing, context window or capability flags, promoting a provider default, standing up a model registry for a new provider, or checking whether a model id resolves through the live provider smoke lane.
- ▌ Pact Memory 2 · profsynapse bundlePersistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons. Triggers: memory, save memory, search memory, lessons learned, remember, recall
- ▌ Pact Teachback 2 · profsynapseCommand-style teachback protocol for PACT teammates. Invoking this skill directly instructs you to store your teachback in task metadata and idle on awaiting_lead_completion before any implementation work.
- ▌ Telegram Guide 2 · profsynapseTelegram notification integration guide for PACT. Use when telegram_notify is available in your tools — covers when to notify, when to ask, when to check replies, and multi-session behavior.
- ▌ Worktree Setup 2 · profsynapseCreate an isolated git worktree with a feature branch for PACT workflows. Use when: starting a new feature, beginning orchestrate or comPACT, creating sub-scope isolation for ATOMIZE, or manually isolating work. Triggers on: worktree setup, feature isolation, parallel workflow, new worktree.
- ▌ Pact Agent Teams 2 · profsynapse bundleAgent Teams interaction protocol for PACT specialist agents. Invoke it at spawn, and again before you append to your MEMORY.md index. Defines how teammates start work, communicate, report completion, handle blockers, and append to a shared index without dropping another instance's entries.
- ▌ Worktree Cleanup 2 · profsynapseRemove a git worktree and its branch after PACT workflow completes. Use when: PR is merged, sub-scope work is consolidated, or manual cleanup is needed. Triggers on: worktree cleanup, remove worktree, delete worktree, branch cleanup.
- ▌ Pact Handoff Harvest 2 · profsynapse bundleHANDOFF discovery, review, save, and ledger-record workflow for the PACT secretary. Use when: processing agent HANDOFFs after workflow phases, running session consolidation, or recovering orphaned completed handoffs from prior sessions. Triggers: harvest HANDOFFs, process HANDOFFs, incremental, consolidation, handoff recovery.
- ▌ Request More Context 2 · profsynapseGet additional project context from the secretary — past decisions, architectural patterns, project history, and lessons learned via `SendMessage`
- ▌ N8n Workflow Patterns 2 · profsynapse bundleProven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.
- ▌ Pact Coding Standards 2 · profsynapse bundleClean code principles, error handling patterns, and coding standards for PACT Code phase. Use when: implementing features, refactoring code, reviewing code quality, establishing coding conventions, or handling errors and exceptions. Triggers on: code quality, clean code, refactoring, error handling, logging patterns, naming conventions, code review, code phase.
- ▌ Pact Team Registration 2 · profsynapseRecord your teammate identity (name@team) at session start so later hooks can recover your friendly name. Invoke as your first action when your spawn prompt directs it.
- ▌ Pact Testing Strategies 2 · profsynapse bundleTesting strategies, test pyramid guidance, and quality assurance patterns for PACT Test phase. Use when: designing test suites, implementing unit tests, integration tests, E2E tests, performance testing, security testing, or determining test coverage priorities. Triggers on: test design, unit testing, integration testing, E2E testing, test coverage, test pyramid, mocking, fixtures, performance testing, test phase.
- ▌ Pact Team Registration · profsynapseRecord your teammate identity (name@team) at session start so later hooks can recover your friendly name. Invoke as your first action when your spawn prompt directs it.
- ▌ Professor Synapse 2 · profsynapse bundleUse when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
- ▌ Professor Synapse 3 · profsynapse bundleUse when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
- ▌ Skill Crafter · profsynapse bundleBuild, improve, modularize, and validate Claude Code skills the right way. Use when creating a new skill, improving or auditing an existing one, refactoring a SKILL.md that grew too long, or adding validation scripts. Encodes a slim-router, progressive-disclosure, PACT-driven approach and is its own reference implementation.
- ▌ Professor Synapse · profsynapse bundleUse when user needs expert help, wants to summon a specialist, says "help me with", "I need guidance", or has a task requiring domain expertise. Creates and manages a growing collection of expert agents.
- ▌ Evaluation · profsynapse bundleComplete reference for the config-first model evaluation system. Covers the Evaluator CLI, assertion-driven YAML scenarios, response views, backend configuration, presets, scoring, LLM-as-judge, model comparison, and HuggingFace integration. Use when evaluating models, writing test prompts, comparing training runs, or interpreting eval results. This skill is about USING the evaluation system via CLI and YAML.
- ▌ Fine Tuning · profsynapse bundleComplete reference for the fine-tuning pipeline (SFT, KTO, GRPO), cloud HF Jobs workflows, autonomous experiment search, checkpoint evaluation, and LoRA surgery. Covers training CLI flags, YAML configuration, model presets, dataset requirements, LoRA settings, training monitoring, hyperparameter search, and post-training optimization. Use when training models, configuring training runs, choosing hyperparameters, running cloud experiments, inspecting HF jobs, or troubleshooting training issues. This skill is about USING the training system via CLI and YAML — never modifying source code.
- ▌ Case Studies · profsynapse bundleEnd-to-end case studies showing how to implement the full training pipeline for different skill types. Covers three complete worked examples — tool-calling training, essay-style training, and agentic search (RAG agent) training — demonstrating dataset design, synthetic generation, validation, fine-tuning, evaluation, and iteration. Use when onboarding to the project, understanding how all components fit together, explaining the pipeline to others, or planning a new training capability. This skill is about UNDERSTANDING the system holistically — reference the other skills for specific CLI commands.
- ▌ Upload Deployment · profsynapse bundleComplete reference for model upload and deployment. Covers HuggingFace upload, save strategies (LoRA, merged 16-bit, merged 4-bit), GGUF conversion, model merging, model cards, and the full upload workflow. Use when uploading models, creating GGUF files, merging LoRA adapters, or deploying to HuggingFace. This skill is about USING the upload/deployment tools via CLI — never modifying source code.
- ▌ Dataset Publishing · profsynapse bundlePublish local dataset artifacts to a Hugging Face dataset repo. Use when uploading a JSONL dataset, pushing a filtered dataset variant, syncing a matching .metadata.json sidecar, or renaming a dataset file in the target repo. This skill is about USING the checked-in dataset publish script via CLI — never ad hoc Python.
- ▌ Embedding Training · profsynapse bundleComplete reference for the embedding fine-tuning pipeline (SentenceTransformers bi-encoders) — the `embedding` training method, model registry, dual loader (Unsloth fast path + ST fallback), adapter modes (full/lora/frozen_head), triplet/pairs dataset format, retrieval evaluation (recall@k/MRR/nDCG/MAP via the `retrieval` verifier), and the local-Docker smoke recipe. Use when training a retrieval embedder, picking a base model + adapter mode, preparing triplet data, or evaluating a fine-tuned embedder against a labeled corpus. This skill is about USING the embedding pipeline via CLI and YAML — never modifying source code.
- ▌ Research Reporting · profsynapse bundleCreate structured research notes from experiment runs and analysis artifacts. Use when creating a note at run launch, updating it as training/evaluation/loss stages finish, summarizing a finished run, comparing experiment outcomes, extracting hypotheses from eval/loss artifacts, or proposing next-run actions grounded in `.tracking/experiments/<id>/analysis/` outputs. This skill is about turning repo-native experiment evidence into stable, machine-readable markdown.
- ▌ Transcript Distillation · profsynapse bundleTurn local agent transcripts (Claude Code, Codex CLI, or any format with an adapter) into high-quality fine-tuning rows. Use when someone wants to mine their own coding-agent conversation logs into an SFT/KTO/DPO/GRPO dataset — parse the logs, extract substantive turns, scrub secrets, score each session by outcome (tests passed / built clean / committed / PR'd), dedup, and tier by quality. Config-driven and format-pluggable; point it at a transcript directory and it produces deduped, quality-tiered JSONL. This skill is about USING the checked-in distill engine via CLI + YAML.
- ▌ Synthetic Data Generation · profsynapse bundleComplete reference for the SynthChat synthetic dataset generation system. Covers CLI commands (generate, improve, validate), scenario YAML authoring, rubric YAML authoring, settings configuration, evaluation, and full workflow. Use when generating datasets, writing rubrics/scenarios, configuring models/workers, improving dataset quality, or running evaluations. This skill is about USING the system via CLI and YAML — never modifying source code.
- ▌ Nexus · profsynapse bundleRead, search, and edit the user's Obsidian vault (notes, folders, canvas, bases, tasks, memory/workspaces, saved prompts) from the shell via the `nexus` CLI — no MCP connection needed. Use whenever the user refers to their vault, notes, daily notes, second brain, or Obsidian, or asks you to find/read/change something stored there and the `nexus` command is on PATH. Do not use it to edit files in the current code repository; use normal file tools for those.
- ▌ Nexus Agents · profsynapse bundleHow to add, change and verify a Nexus agent or tool, and the contract every tool must satisfy. Use when adding or modifying an agent or tool, when a documented command does not resolve, when wiring registration or capability gating, or when touching the ToolManager payload shape.
- ▌ Nexus Release · profsynapse bundleCut a Nexus release — bump the version with the repo's own machinery, get the docs and generated sources right, push a tag the GitHub Actions workflow will actually pick up, and recover when it does not. Use when asked to release, publish, ship, cut a release, bump the version, or tag a version, and when a release workflow did not fire, failed its version guard, or produced the wrong assets.
- ▌ Nexus Storage · profsynapse bundleHow to change, persist, migrate and recover Nexus data without losing it. Use when adding a SQLite table or column, persisting anything that must survive a restart or a cache rebuild, resolving a vault or plugin storage path, or debugging missing, stale, duplicated or post-rebuild-vanished data.
- ▌ Nexus Testing · profsynapse bundleVerify a Nexus change — pick a Jest lane, write a test that can actually fail, run the in-app Obsidian CLI loop, drive the eval harness, or fix a shipped-docs drift failure. Use when adding or changing tests, when a mock might be deciding the outcome, when a change has to be proven in the running plugin, or when the guidance gate fails.
- ▌ Nexus Model Eval · profsynapse bundleGrade how well a model drives the Nexus two-tool protocol (getTools/useTools) and decide whether a low score is the model's fault or the harness's. Use when asked to grade, benchmark, rank or compare models on Nexus tool use, when picking a default model, or when an eval report needs interpreting.
- ▌ Nexus UI Mockups · profsynapse bundleDesign a Nexus UI change as a standalone mockup under docs/mockups/ before any production code, then hand it off as the visual contract a plan implements against. Use when asked for a new view, panel, modal, settings tab, chat surface, or layout refactor, when revising or superseding an existing mockup, or when a plan needs something visual to be blessed against.
- ▌ Nexus Eval Harness · profsynapse bundleWork on the Nexus LLM eval harness in tests/eval/ — author or fix a scenario fixture, write an eval config, change the executors, assertions or reports, or explain a run that produced nothing, everything-fails, or numbers that disagree. Use when an eval scenario is wrong, a run behaves oddly, or the harness itself needs to change. To grade a model rather than change the harness, use nexus-model-eval.
- ▌ Nexus LLM Adapters · profsynapse bundleHow to add or debug a Nexus LLM provider adapter — what every adapter must wire, how to verify it against a live provider, and the failure modes that produce a silently blank chat. Use when adding or changing a provider adapter, debugging streaming or reasoning display, working with local or CLI-backed models, or touching chat branch plumbing.
- ▌ Nexus Tool Schemas · profsynapse bundleExport the live CLI-first Nexus tool catalog as JSON — the whole registry or a selector-picked subset — and refresh the committed catalog that the repo's guidance and drift tests read. Use when someone asks for tool schemas or the exact command/argument shape a caller sees, after changing a tool's parameter schema, slug or description, after touching ToolCliNormalizer, or when a catalog-backed test fails.
- ▌ Nexus Mobile Compat · profsynapse bundleKeep Nexus loading on mobile and compliant with the Obsidian plugin store — vet a dependency, import without crashing init, confine a vault path, and prove none of it regressed with the reachability checker. Use before adding an npm package or a Node import, when writing to caller-supplied vault paths, when gating a desktop-only feature, when a PDF or worker-backed feature misbehaves, or when the plugin fails to load on a phone.
- ▌ Nexus Model Updates · profsynapse bundleAdd, change or verify a Nexus LLM model definition — the registry entry, the provider default, and proof the model id actually works against the live endpoint. Use when adding a newly released model, editing model metadata such as pricing, context window or capability flags, promoting a provider default, standing up a model registry for a new provider, or checking whether a model id resolves through the live provider smoke lane.
- ▌ Kg Ingest · profsynapse bundleIngest a research paper (or a batch) into the library's atomic knowledge graph the Agents-K1 way. Use when you are handed a paper (URL, arXiv id, or a note already in library/) and you want it folded in as typed concept atoms, mechanisms, lineage edges, and a patched paper note, reconciled against the atoms already in the vault rather than re-extracted from scratch. Also use to backfill spine papers not yet atomized. This is the standing ingestion posture for growing the graph one paper at a time.
- ▌ Experiments · profsynapse bundleLifecycle tooling for the experiments-first repo layout, with one self-contained directory per evidence-producing experiment, signed amendment, machine-readable manifest, pinned instrument, and generated index. Use to scaffold, sign, inspect, resolve, validate, or regenerate experiments; check machine-local input readiness; and apply the shared-input promotion rule.
- ▌
- ▌ Data Exhaust · profsynapse bundlePackage a terminal experiment's data exhaust (aggregate stats and, where license-permitted, row-level generation text) into reproducible Hugging Face datasets, with a license gate, containment lint, and a thin uploader. Use when an experiment under experiments/<slug>/ reaches a terminal verdict (resolved, null-result, or falsified) and its analysis-committed/ artifacts should be published.
- ▌ Family Atlas · profsynapse bundleStandardize the per-model layer-mapping extraction (full-depth hidden-state capture, workspace-dimension profile, three-axis held-out read panel) so any new model, family, or size entering the Epistemic-Humility program gets a fast, cheap, uniform layer atlas before any actuation design. Use when a new model/family/size enters the program, before designing any per-family actuation cell, or when an existing family's substrate changes (new revision, new checkpoint).
- ▌ Task Backlog · profsynapse bundleTask-backlog lifecycle tooling for the Epistemic-Humility-Research repo - one markdown file per task under backlog/{tasks,drafts,completed}, a bin/task CLI (new/list/show/claim/release/review/done/validate), a generated TODO.md table, and a pre-commit commit gate that requires gated work files to be covered by an active task. Use to mint, claim, and close backlog tasks, to bind a task to an experiments/<slug>/ record, and to understand the commit-gate scope and escape hatch. Tasks point at experiments; experiments keep their own lifecycle under bin/exp and AMENDMENT.md.
- ▌ Knowledge Graph · profsynapse bundleCreate, validate, normalize, export, and analyze typed Obsidian knowledge graph metadata in the Professor Synapse vault, including `kg` node metadata, `relationships` edge objects, `related` link projections, ontology-governed edge types, legacy relationship shorthand, and graph analysis reports.
- ▌ Mechinterp Cells · profsynapse bundleAuthor, organize, and launch tuner-backed mechanistic-interpretation cells (activation reading and writing) for the Epistemic-Humility project. Use when designing a new steering / extraction / probe-fit / gate-scoring cell, deciding where its config, direction, grader, and outputs live, or launching one locally or on Modal. This skill is about USING the synaptic-tuner `mechinterp` verbs via declarative recipe YAML plus project plug-ins; it never modifies the tuner submodule and never touches the frozen legacy machinery.
- ▌ Experiment Runner · profsynapse bundleOperational runbook for the Epistemic-Humility Locked Matrix Experiment Runner - expands the PROTOCOL v0.3 (LOCKED) run matrix (3-seed headline + LR/beta sensitivity panel at 4B, 3-seed confirm at 8B, 2 bridge replication cells) into per-cell tuner invocations across two lanes (local RTX 3090 / HF Jobs cloud), with hard pre-registration count assertions, prerequisite gating, data staging, and committed provenance run records. Use when launching, dry-running, or gating the locked matrix, materializing per-cell recipes, or inspecting run records. This skill is about USING the runner via checked-in scripts; it never modifies the synaptic-tuner submodule.
- ▌ Experiment Wrapup · profsynapseExecute the downstream wrap-up after a signed experiment produces its terminal numbers and the LEAD has adjudicated the verdict - write the AMENDMENT Outcome, run bin/exp resolve, update the cross-experiment registries (family-layer-map for atlas cells, prediction-scoreboard for scored cells), open the resolve PR, commit the living tracking docs to main, and hand off KG ingest. This is the mechanical half of a resolve and is delegable to a smaller model, given a locked adjudication packet from the lead. It never decides the verdict, the falsifier call, or the scoreboard scores - those are lead-only judgment and are inputs to this skill, not outputs of it.
- ▌ Mech Interp Runner · profsynapse bundleRun, plan, validate, or aggregate Epistemic-Humility local mechanistic-interpretability sweeps, including hidden-state candidate inventories, causal-pilot sweep planning, explicit non-GPU/GPU gates, base-original skip handling, and offline result aggregation. Use when working on local mech-interp sweeps, causal-pilot diagnostics, activation-addition/logit-diagnostic runs, behavior-axis scans, SAE feature screens, or future reruns of the legacy full candidate inventory.
- ▌ Vapi · profsynapse bundleManages the Vapi voice AI platform API. Use when the user wants to create, list, update, or delete Vapi resources (assistants, calls, phone numbers, squads, tools, files, knowledge bases, blocks, sessions, campaigns, logs, evals, eval runs), make outbound calls, configure voice pipelines, run eval tests against assistants, or manage their Vapi account. Handles all CRUD operations against the Vapi REST API.
- ▌ Agentic Guardrails · profsynapse bundleRoute file and Office work through Agentic Guardrails for reversible changes, bounded reads/scans, synced folders, recovery, and diagnostics. Use for delete, overwrite, move, restore, broad scan, or Office mutation work.
- ▌ Deslop · profsynapse bundleRemove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, filler phrases, self-referential meta-commentary, and references to context the reader never received.
- ▌ Pact Testing Strategies · profsynapse bundleTesting strategies, test pyramid guidance, and quality assurance patterns for PACT Test phase. Use when: designing test suites, implementing unit tests, integration tests, E2E tests, performance testing, security testing, or determining test coverage priorities. Triggers on: test design, unit testing, integration testing, E2E testing, test coverage, test pyramid, mocking, fixtures, performance testing, test phase.
- ▌ Pact Memory · profsynapse bundlePersistent memory for PACT agents. Save context, goals, lessons learned, decisions, and entities. Semantic search across sessions. Use when: saving session context, recalling past decisions, searching lessons. Triggers: memory, save memory, search memory, lessons learned, remember, recall
- ▌ Pact Teachback · profsynapseCommand-style teachback protocol for PACT teammates. Invoking this skill directly instructs you to store your teachback in task metadata and idle on awaiting_lead_completion before any implementation work.
- ▌ Telegram Guide · profsynapseTelegram notification integration guide for PACT. Use when telegram_notify is available in your tools — covers when to notify, when to ask, when to check replies, and multi-session behavior.
- ▌ Worktree Setup · profsynapseCreate an isolated git worktree with a feature branch for PACT workflows. Use when: starting a new feature, beginning orchestrate or comPACT, creating sub-scope isolation for ATOMIZE, or manually isolating work. Triggers on: worktree setup, feature isolation, parallel workflow, new worktree.
- ▌ Pact Agent Teams · profsynapse bundleAgent Teams interaction protocol for PACT specialist agents. Invoke it at spawn, and again before you append to your MEMORY.md index. Defines how teammates start work, communicate, report completion, handle blockers, and append to a shared index without dropping another instance's entries.
- ▌ Worktree Cleanup · profsynapseRemove a git worktree and its branch after PACT workflow completes. Use when: PR is merged, sub-scope work is consolidated, or manual cleanup is needed. Triggers on: worktree cleanup, remove worktree, delete worktree, branch cleanup.
- ▌ Pact Handoff Harvest · profsynapse bundleHANDOFF discovery, review, save, and ledger-record workflow for the PACT secretary. Use when: processing agent HANDOFFs after workflow phases, running session consolidation, or recovering orphaned completed handoffs from prior sessions. Triggers: harvest HANDOFFs, process HANDOFFs, incremental, consolidation, handoff recovery.
- ▌ Request More Context · profsynapseGet additional project context from the secretary — past decisions, architectural patterns, project history, and lessons learned via `SendMessage`
- ▌ N8n Workflow Patterns · profsynapse bundleProven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.
- ▌ Pact Coding Standards · profsynapse bundleClean code principles, error handling patterns, and coding standards for PACT Code phase. Use when: implementing features, refactoring code, reviewing code quality, establishing coding conventions, or handling errors and exceptions. Triggers on: code quality, clean code, refactoring, error handling, logging patterns, naming conventions, code review, code phase.