Updated 1mo ago
by OpenLAIR
OpenSkill
Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)
95 GitHub stars (95)
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | +1 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | −1 |
| Oct 16 | 0 |
- 30 skills (30 skills found in its SKILL.md files)
- 3 forks (3 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add OpenLAIR/OpenSkill
Asks which skills and agents to install. Just one: npx skills add OpenLAIR/OpenSkill --skill skill-creator — add -g for every project.
Claude Code
git clone https://github.com/OpenLAIR/OpenSkillcp -r "OpenSkill/.claude/skills/skill-creator" ~/.claude/skills/
Copies the skill-creator skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add OpenLAIR/OpenSkill
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 169 files.
-
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
.claude/skills/skill-creator/SKILL.md on GitHub (opens in a new tab) -
evo-3d-scan-calc
Complete pipeline for binary STL parsing, connected component extraction, volume computation, material density lookup, and mass calculation with JSON output.
tasks-evolved/3d-scan-calc/environment/skills/evo-3d-scan-calc/SKILL.md on GitHub (opens in a new tab) -
evo-mass-report-output
Orchestrates the full pipeline from STL parsing to JSON mass report output. Coordinates parsing, component analysis, volume computation, unit conversion, and mass calculation.
tasks-evolved/3d-scan-calc/environment/skills/evo-mass-report-output/SKILL.md on GitHub (opens in a new tab) -
evo-mesh-geometry-analysis
Performs connected component analysis on triangle meshes using BFS with vertex adjacency and computes mesh volume via the signed tetrahedron method. Handles unit conversion and mass calculation.
tasks-evolved/3d-scan-calc/environment/skills/evo-mesh-geometry-analysis/SKILL.md on GitHub (opens in a new tab) -
evo-stl-binary-parser
Parses binary STL files using Python's struct module, extracting triangle vertices, normals, and the 2-byte attribute byte count (used as Material ID). Provides filtering by Material ID and density table parsing.
tasks-evolved/3d-scan-calc/environment/skills/evo-stl-binary-parser/SKILL.md on GitHub (opens in a new tab) -
evo-adaptive-cruise-control
Complete Adaptive Cruise Control simulation system with PID controllers, single-loop ACC architecture (cruise/follow/emergency modes), TTC safety, Euler integration simulation, and full I/O pipeline.
tasks-evolved/adaptive-cruise-control/environment/skills/evo-adaptive-cruise-control/SKILL.md on GitHub (opens in a new tab) -
evo-azure-bgp-oscillation-route-leak
Analyzes Azure Virtual WAN multi-hub BGP topologies to detect route oscillation (preference cycles) and valley-free route leak violations (Gao-Rexford model), then evaluates proposed solutions against domain-specific resolution criteria.
tasks-evolved/azure-bgp-oscillation-route-leak/environment/skills/evo-azure-bgp-oscillation-route-leak/SKILL.md on GitHub (opens in a new tab) -
evo-bibtex-parser
Parses BibTeX files using bibtexparser 1.4.2 and cleans LaTeX/BibTeX artifacts from fields like title, author, year, DOI, and venue. Produces a normalized list of citation dictionaries ready for verification.
tasks-evolved/citation-check/environment/skills/evo-bibtex-parser/SKILL.md on GitHub (opens in a new tab) -
evo-citation-scorer
Compares parsed BibTeX citation metadata against API results using fuzzy string matching and multi-factor scoring to classify citations as real or fake, then outputs the final JSON report.
tasks-evolved/citation-check/environment/skills/evo-citation-scorer/SKILL.md on GitHub (opens in a new tab) -
evo-citation-verifier
Queries external academic APIs (CrossRef, Semantic Scholar, DBLP, doi.org) to verify whether a citation exists. Implements robust HTTP sessions with retry logic, exponential backoff, and rate limiting.
tasks-evolved/citation-check/environment/skills/evo-citation-verifier/SKILL.md on GitHub (opens in a new tab) -
evo-civ6-adjacency-rules
Encodes all Civ6 Gathering Storm district adjacency bonus rules, placement validity, population limits, and civ-specific modifiers.
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-adjacency-rules/SKILL.md on GitHub (opens in a new tab) -
evo-civ6-map-parser
Parses .Civ6Map SQLite database files to extract map dimensions, terrain, features, resources, and river edge data. Provides hex coordinate utilities for odd-r pointy-top hex grid.
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-map-parser/SKILL.md on GitHub (opens in a new tab) -
evo-civ6-placement-optimizer
Searches for optimal city center and district placements to maximize total adjacency bonuses in Civ6 scenarios.
tasks-evolved/civ6-adjacency-optimizer/environment/skills/evo-civ6-placement-optimizer/SKILL.md on GitHub (opens in a new tab) -
evo-pdf-field-inspector
Inspects PDF AcroForm fields - enumerates field names, types, values, and checkbox on-states. Essential for discovering exact internal field keys before filling.
tasks-evolved/court-form-filling/environment/skills/evo-pdf-field-inspector/SKILL.md on GitHub (opens in a new tab) -
evo-pdf-form-filler
Fills PDF AcroForm fields (text and checkboxes) using pypdf, sets NeedAppearances flag, and writes the output PDF. Handles checkbox state detection and proper value updates.
tasks-evolved/court-form-filling/environment/skills/evo-pdf-form-filler/SKILL.md on GitHub (opens in a new tab) -
evo-crystallography-fraction-format
Converts floating-point fractional coordinates to clean rational fraction strings with bounded denominators (<=12), handling edge cases like near-zero/near-one wrapping and integer values.
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-fraction-format/SKILL.md on GitHub (opens in a new tab) -
evo-crystallography-wyckoff-analysis
Parses CIF files using pymatgen, performs space group symmetry analysis via SpacegroupAnalyzer, and extracts Wyckoff position letters, multiplicities, and representative atom fractional coordinates from the symmetrized structure.
tasks-evolved/crystallographic-wyckoff-position-analysis/environment/skills/evo-crystallography-wyckoff-analysis/SKILL.md on GitHub (opens in a new tab) -
evo-network-stats-computation
Computes all network statistics from extracted packet features and writes to CSV.
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-network-stats-computation/SKILL.md on GitHub (opens in a new tab) -
evo-pcap-feature-extraction
Reads PCAP via Scapy PcapReader, extracts per-packet features into numpy arrays.
tasks-evolved/dapt-intrusion-detection/environment/skills/evo-pcap-feature-extraction/SKILL.md on GitHub (opens in a new tab) -
evo-d3v6-stock-visualization
Generates the complete visualization.js file implementing a D3.js v6 force-simulation bubble chart with sector clustering, an interactive data table, tooltips, legends, and bidirectional click-based highlighting between chart and table.
tasks-evolved/data-to-d3/environment/skills/evo-d3v6-stock-visualization/SKILL.md on GitHub (opens in a new tab) -
evo-web-scaffold-generator
Python utility that creates the output directory structure, copies input data, downloads d3.v6.min.js locally, and writes the index.html and style.css files for the stock visualization dashboard.
tasks-evolved/data-to-d3/environment/skills/evo-web-scaffold-generator/SKILL.md on GitHub (opens in a new tab) -
evo-dialogue-dotgen
Generates Graphviz DOT visualization files from parsed dialogue graph structures using the graphviz 0.20.3 Python API.
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-dotgen/SKILL.md on GitHub (opens in a new tab) -
evo-dialogue-output
Serializes dialogue graph to JSON file and generates Graphviz DOT visualization. Handles UTF-8 encoding, DOT node styling by type, and edge labeling.
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-output/SKILL.md on GitHub (opens in a new tab) -
evo-dialogue-parser
Parses dialogue script text into intermediate section structures using regex, then builds a validated JSON graph schema with typed nodes and edges. Handles section headers, speaker lines, numbered choices with optional tags, and edge targets.
tasks-evolved/dialogue-parser/environment/skills/evo-dialogue-parser/SKILL.md on GitHub (opens in a new tab) -
evo-egomotion-dynamic-analysis
For consecutive sampled frame pairs, computes sparse optical flow, estimates camera egomotion via partial affine transform, and detects dynamic objects via homography-based motion compensation and frame differencing.
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-egomotion-dynamic-analysis/SKILL.md on GitHub (opens in a new tab) -
evo-output-serialization
Serializes egomotion labels to JSON with frame-interval keys and binary masks to NPZ in CSR sparse format using only NumPy.
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-output-serialization/SKILL.md on GitHub (opens in a new tab) -
evo-video-sampling
Extracts frames from an MP4 video file at a specified target FPS using sequential reading. Returns sampled grayscale frames and their original frame indices.
tasks-evolved/dynamic-object-aware-egomotion/environment/skills/evo-video-sampling/SKILL.md on GitHub (opens in a new tab) -
evo-seismic-data-io
Loads MiniSEED waveform data and CSV station metadata, groups traces by station for 3-component processing, and provides station coordinate lookups.
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-data-io/SKILL.md on GitHub (opens in a new tab) -
evo-seismic-phase-association
Associates phase picks from multiple stations into earthquake events using temporal clustering (DBSCAN) and travel-time validation with a uniform velocity model, then outputs event catalog as CSV.
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-association/SKILL.md on GitHub (opens in a new tab) -
evo-seismic-phase-picking
Runs SeisBench deep learning models (PhaseNet/EQTransformer) on grouped station waveforms to produce P and S phase picks with timestamps and probabilities.
tasks-evolved/earthquake-phase-association/environment/skills/evo-seismic-phase-picking/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.