GitHub
mechinterp-decoder
Analyze SAE decoder weights - output influence, feature importance, and decoder similarity
☆ 1View skill
Business AI Skills
Discover Business skills, compare source repositories and read the instructions for each workflow.
Categories: Business
Business Clear filters
Browse skills
GitHub
mechinterp-validation-suite
Run credibility checks on feature interpretations including split-half stability and shuffle null tests
☆ 1View skill
GitHub
mechinterp-glossary-and-constraints
Reference skill for Splatoon ability families, AP rungs, token constraints, and domain rules for mechinterp experiments
☆ 1View skill
GitHub
mechinterp-state
Manage research state for SAE feature analysis including hypotheses, evidence tracking, and research history
☆ 1View skill
GitHub
mechinterp-next-step-planner
Propose next mechanistic interpretability experiments based on research state, hypotheses, and existing evidence
☆ 1View skill
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...
☆ 1View skill
GitHub
mechinterp-investigator
Orchestrate a systematic research program to investigate and meaningfully label SAE features
☆ 1View skill
GitHub
mechinterp-labeler
Manage feature labeling workflow - queue management, label storage, similar features, progress tracking
☆ 1View skill
GitHub
mechinterp-overview
Quick "first look" overview of SAE features - top tokens, activation stats, weapons, families, sample contexts
☆ 1View skill
GitHub
mechinterp-patterns
Reference catalog of recurring SAE feature patterns - check when labeling new features, add new patterns as discovered
☆ 1View skill
GitHub
mechinterp-cluster-mapper
Analyze relationships across multiple SAE features - co-activation patterns, shared drivers, and subsystem identification
☆ 1View skill
GitHub
mechinterp-runner
Execute mechanistic interpretability experiments from JSON specs - family sweeps, itemsets, interactions, minimal cores, validation
☆ 1View skill
GitHub
mechinterp-crossmodel-matcher
Match SAE features between Ultra (24K) and Full (2K) models based on activation patterns and token overlap
☆ 1View skill
GitHub
mechinterp-ability-semantics
Reference for ability family semantic groupings and gameplay meanings
☆ 1View skill
GitHub
core-rules
Use ALWAYS. Core development rules for production-ready code - guard clauses, no shortcuts, no mocking.
☆ 1View skill
GitHub
pr-workflow
Use when creating, reviewing, or merging pull requests. Includes CI checks, review requirements, and merge approval rules.
☆ 1View skill
GitHub
tdd
Use when implementing ANY new feature or fixing bugs. Test-Driven Development - write tests BEFORE implementation code.
☆ 1View skill
GitHub
verification
Use before claiming ANY work is complete. Evidence before claims, always. Non-negotiable verification gate.
☆ 1View skill
GitHub
quality-gate
PFLICHT bei JEDER Antwort mit Code-Änderungen! Die 8-Punkt-Checklist MUSS als ERSTES in der Response stehen. Keine Ausnahmen.
☆ 1View skill
GitHub
delegation
Use when deciding whether to delegate work to subagents. Lists available agents with triggers and capabilities. Delegate aggressively.
☆ 1View skill
GitHub
debugging
Use when facing ANY technical issue. Systematic debugging - root cause investigation BEFORE attempting fixes.
☆ 1View skill
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.
☆ 1View skill
GitHub
worktree
Use before ANY code changes. Ensures work happens in isolated git worktrees, not on main branch. Critical safety check.
☆ 1View skill
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.
☆ 1View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.