GitHub
mechinterp-decoder
Analyze SAE decoder weights - output influence, feature importance, and decoder similarity
Skills IA Entreprise
Découvrez les skills Entreprise, comparez leurs dépôts et consultez leurs instructions.
Catégories: Entreprise
Entreprise Effacer les filtres
Explorer
GitHub
mechinterp-validation-suite
Run credibility checks on feature interpretations including split-half stability and shuffle null tests
GitHub
mechinterp-glossary-and-constraints
Reference skill for Splatoon ability families, AP rungs, token constraints, and domain rules for mechinterp experiments
GitHub
mechinterp-state
Manage research state for SAE feature analysis including hypotheses, evidence tracking, and research history
GitHub
mechinterp-next-step-planner
Propose next mechanistic interpretability experiments based on research state, hypotheses, and existing evidence
GitHub
splatoon3-meta
Domain expert for Splatoon 3 competitive gear abilities and weapon meta. Use when: (1) Labeling or classifying gear build features from SAE analysis, (2) Understanding why specific ability combinations appear i...
GitHub
mechinterp-investigator
Orchestrate a systematic research program to investigate and meaningfully label SAE features
GitHub
mechinterp-labeler
Manage feature labeling workflow - queue management, label storage, similar features, progress tracking
GitHub
mechinterp-overview
Quick "first look" overview of SAE features - top tokens, activation stats, weapons, families, sample contexts
GitHub
mechinterp-patterns
Reference catalog of recurring SAE feature patterns - check when labeling new features, add new patterns as discovered
GitHub
mechinterp-cluster-mapper
Analyze relationships across multiple SAE features - co-activation patterns, shared drivers, and subsystem identification
GitHub
mechinterp-runner
Execute mechanistic interpretability experiments from JSON specs - family sweeps, itemsets, interactions, minimal cores, validation
GitHub
mechinterp-crossmodel-matcher
Match SAE features between Ultra (24K) and Full (2K) models based on activation patterns and token overlap
GitHub
mechinterp-ability-semantics
Reference for ability family semantic groupings and gameplay meanings
GitHub
core-rules
Use ALWAYS. Core development rules for production-ready code - guard clauses, no shortcuts, no mocking.
GitHub
pr-workflow
Use when creating, reviewing, or merging pull requests. Includes CI checks, review requirements, and merge approval rules.
GitHub
tdd
Use when implementing ANY new feature or fixing bugs. Test-Driven Development - write tests BEFORE implementation code.
GitHub
verification
Use before claiming ANY work is complete. Evidence before claims, always. Non-negotiable verification gate.
GitHub
quality-gate
PFLICHT bei JEDER Antwort mit Code-Änderungen! Die 8-Punkt-Checklist MUSS als ERSTES in der Response stehen. Keine Ausnahmen.
GitHub
delegation
Use when deciding whether to delegate work to subagents. Lists available agents with triggers and capabilities. Delegate aggressively.
GitHub
debugging
Use when facing ANY technical issue. Systematic debugging - root cause investigation BEFORE attempting fixes.
GitHub
graphiti-memory
Use when starting a session, beginning a new task, or encountering errors. Graphiti is the knowledge graph memory system for storing patterns, fixes, preferences and learnings across all projects.
GitHub
worktree
Use before ANY code changes. Ensures work happens in isolated git worktrees, not on main branch. Critical safety check.
GitHub
pr-review-check
Check Pull Request on current branch, and obtain unresolved review comments. `gh` command is required. Use this when user instructed with `PR review comment` `PR レビューコメント` etc.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.