The library
Everything we index — ranked by what works, never by stars.
forSalesMarketingHRFinanceLegalOpsProductEngineeringDataProductivitySupportsetup≤ plug & play≤ + a key≤ multi-tool
● works · ● untested / no effect · ● hurts — every rank is measured against a no-skill baseline
untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★64→untested★9,423→untested★30,073→untested★64→untested★9,423→untested★47,644→untested★9,423→untested★481→untested★64→untested★9,423→untested★216→untested★64→untested★9,423→untested★64→untested★8,999→untested★64→untested★64→untested★2→untested★64→untested★46→untested★64→untested★2→untested★64→untested★64→untested★0→untested★64→untested★64→untested★64→untested★6,340→untested★1→untested★64→untested★37,525→
Download and verify mirrored Aminet packagesskillEngineeringOpsL2
aminet-mirror · Bulk downloading packages with fallback mirrors, atomic state persistence, and resume-from-interruption.
Extend model context windows to 32k-128k tokensskillEngineeringProductL3
long-context · Processing long documents (32k-128k+ tokens) by extending pre-trained models with RoPE/YaRN interpolation.
Scan Aminet packages for viruses and threatsskillEngineeringOpsL2
aminet-scanner · Enforcing security gates on Amiga package installation via 3-layer scanning (signature + heuristic + emulated).
Merge fine-tuned models without retrainingskillEngineeringProductL3
model-merging · Creating specialized models by blending domain expertise (math+coding+chat) in minutes without retraining.
Generate content across 10 applied domainsskillMarketingProductL1
kp-applied-domain · Guiding generation of Applied & Practical tier content across 10 subjects with real-world relevance.
Prune models to 50% sparsity for faster inferenceskillEngineeringProductL3
model-pruning · Achieving 50% sparsity with minimal accuracy loss via one-shot pruning without retraining.
Generate knowledge pack content suitesskillProductEngineeringL2
kp-content-authoring · Generating consistent, scaffolded educational content across 4 tiers with prerequisite chains.
Train sparse Mixture of Experts modelsskillEngineeringProductL4
moe-training · Scaling model capacity without proportional compute via conditional expert routing.
Validate knowledge pack content against schemasskillProductEngineeringL2
kp-content-validation · Ensuring all tier packs meet quality bars before publishing.
Accelerate inference with speculative decodingskillEngineeringProductL3
speculative-decoding · 2-8x inference speedup with small draft model validated by large verifier.
Teach core academic subjects systematicallyskillProductL1
kp-core-academic-domain · Structuring foundational knowledge across Math, Reading, Science, Social Studies, Arts, PE, Tech.
Generate publication-quality research diagramsskillProductEngineeringL2
academic-plotting · Creating journal-ready plots with minimal code (IEEE/Nature style templates included).
Coordinate knowledge pack generation batchesskillOpsL3
kp-pipeline-orchestration · Managing multi-tier content workflows ensuring prerequisites before generating downstream tiers.
Write ML papers for top conferencesskillProductEngineeringL1
ml-paper-writing · Rapidly drafting ML papers with automatic figure integration and citation formatting.
Review educational content qualityskillProductL1
kp-quality-review · Filtering low-quality tier packs before release; blocks unmet prerequisites.
Create conference presentation slidesskillMarketingProductL2
presenting-conference-talks · Converting research papers to engaging talks with audience-appropriate complexity scaffolding.
Teach specialized domain subjectsskillProductL1
kp-specialized-domain · Route specialized domain queries (philosophy, theology, arts, trades, astronomy) to correct curriculum pack.
Write systems papers for top venuesskillProductEngineeringL1
systems-paper-writing · Structure a 10-12 page OSDI/SOSP/ASPLOS/NSDI/EuroSys paper with authoritatively grounded paragraph blueprints.
Learn electronics from fundamentalsskillProductL1
electronics · Route electronics learning queries from Ohm's law through PCB design to correct instructional module.
Discover high-impact research directionsskillProductEngineeringL1
brainstorming-research-ideas · Move from vague curiosity to concrete, defensible research direction via problem-first vs. solution-first analysis and abstraction-ladder exploration.
Read and manage calendar eventsskillProductivityOpsL2
google-calendar · Query and modify Google Calendar events programmatically with automatic pagination and empty-field cleanup.
Audit PRs against spec complianceskillEngineeringL1
adversarial-pr-review · Verify PR claims match actual implementation against approved spec before merge, detecting scope creep and divergences.
Unlock creative research thinkingskillProductEngineeringL1
creative-thinking-for-research · Escape local-optimum thinking via bisociation, problem reformulation, and tension-resolution frameworks grounded in decades of creativity research.
Create git commits with messagesskillEngineeringL1
commit-changes · Generate conventional, focused commits with context-aware message from current tree state without secrets leakage.
Compile research into AI artifactsskillProductDataL3
ara-compiler · Ingest papers, code, experiments into falsifiable, agent-traversable knowledge package with cognitive + physical layers and provenance tracking.
Add new capabilities to systemskillEngineeringOpsL2
create-skill · Author new Hermes skills with correct metadata format and immediate ~/.hermes/ installation for auto-load.
Apply refactors across multiple filesskillEngineeringL2
batch-rewrite-pattern · Apply identical refactor (rename symbol, swap import, migrate signature) across many files in single planned batch rather than N manual passes.
Record research decisions and experimentsskillDataOpsL2
ara-research-manager · Manage multi-version research artifact evolution with checkpoints, exploration branching, and job resumption tracking.
Review PRs with AI automationskillEngineeringL2
octorus · Route incoming queries to most relevant agent skill using trigger pattern matching and confidence scoring.
Create new content cartridgesskillProductOpsL3
cartridge-forge · Generate executable parameter cartridges with reproducible hyperparameters and runtime-compatible loader stubs.
Review research artifact rigorskillProductDataL2
ara-rigor-reviewer · Verify ARA claims are grounded in actual source evidence, detect hallucinations, and flag unsourced assertions before publication.
Checkpoint long-running batch jobsskillEngineeringOpsL2
checkpoint-resume-long-job · Enable resumption of long-running jobs with periodic checkpoints rather than full restart on failure.
Optimize prompts for AI toolsskillProductEngineeringL1
prompt-master · Create reproducible, version-controlled prompt templates with automated test coverage and performance tracking.
Review code for bugs and styleskillEngineeringL1
code-review · Perform effort-calibrated code review with bug hunting, reuse/simplification, and efficiency improvements.
Generate conventional commit messagesskillEngineeringL1
commit-style · Retroactively enforce commit style (conventional commits, scoping, subject length) across existing commits.
Install easyskillz into your repositoryskillEngineeringL2
INSTALL-SKILL · Enable immediate auto-load of skill by installing to ~/.hermes/skills/ without manual activation.
Pause before irreversible decisionsskillProductivityL1
decision-framework-invoker · High-stakes decisions where reversibility matters and second-order consequences are hard to see
Define skill schema structureskillEngineeringL1
.deepschema.SKILL.md.yml · Enforcing behavioral correctness in AI workflow skills without manual gate-keeping
Retire and archive completed workskillOpsL2
done-retirement · Making done irreversible via push (no local state preservation, no U-turn after Stage 3)
Fix character encoding in filesskillEngineeringL2
zh-encoding-fix · Recovering garbled Chinese text after write/edit without losing original in backup
Select best output by behavior testingskillEngineeringL3
execution-grounded-selection · Code selection when semantic voting's 19-52pp improvement over output voting matters
Learn GSD commands and workflowsskillL1
gsd-guide · Reducing hesitation in GSD adoption by previewing what commands will do before running them
Install GitHub master skillskillEngineeringL2
install-github-master-skill · Distributing github-master skill via script-driven installation without manual folder copy
Route to correct GSD phase commandskillOpsL2
gsd-workflow · Translating "what should I work on" into specific GSD pipeline actions without requiring slash syntax
Convert polling to proactive executionskillEngineeringL3
gupp-propulsion · Preventing trained LLM passivity (wait-for-user bias) in autonomous multi-agent pipelines
Convert visual designs into build specsskillProductL2
image-to-mission · Capturing design energy from reference images into code without losing emergent (non-pixel) properties
Build animated digital magazine interfaceskillProductL3
deck-magazine-web · Magazine-editorial presentation where e-ink aesthetic + WebGL fluid effect beats standard slideshow
Review pull requests for quality and securityskillEngineeringL2
workflow-skill · Structured four-pass review (security/performance/correctness/maintainability) with optional GitHub posting
Generate intelligence briefings for planningskillOpsL3
intelligence-investigator · Surfacing actionable causal reasoning at planning meeting starts without manual synthesis
Manage Feishu bots and workflowsskillOpsL2
feishu · Bridging Feishu (Chinese teams) into Claude workflows without manual copy-paste