Zhang-Henry/CoEvoSkills

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification — COLM 2026

66Stars on the repository
86Mods indexed here, across every type
22d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Implement a Flink streaming job that analyzes Google cluster trace data to find the longest session (stage) of task SUBMIT events per finished job. Use when the task involves Flink session windows on cluster trace task/job events, session gap detection, or counting events in session windows keyed by job ID.

not rated 66 +1 22d ago A SkillSpector: pass 67 tokens original Apache-2.0

evo-flood-analysis

26

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Analyze USGS streamflow stations for flood events by comparing gage height data against NWS flood stage thresholds. Use when detecting flood days for USGS stations over a date range.

not rated 66 +1 22d ago A SkillSpector: pass 42 tokens original Apache-2.0

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Generates a community pulse report for a GitHub repository by querying the GitHub Search API for PRs and issues within a date range, computing merge statistics, identifying top contributors, classifying bug reports by label substring, and counting resolved bugs. Use when asked to produce a JSON summary of repository…

not rated 66 +1 22d ago A SkillSpector: pass 70 tokens original Apache-2.0

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Run and calibrate the General Lake Model (GLM) for lake temperature simulation. Use when task requires running GLM, computing RMSE against observations, and calibrating parameters to meet an RMSE threshold.

not rated 66 +1 22d ago A SkillSpector: pass 51 tokens original Apache-2.0

evo-gw-detection

29

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Gravitational wave detection using matched filtering with PyCBC. Loads .gwf data, conditions it, performs grid search over mass parameters for multiple approximants, and reports peak SNR per approximant.

not rated 66 +1 22d ago A SkillSpector: pass 48 tokens original Apache-2.0

evo-dc-dispatch

30

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Solve DC Optimal Power Flow with spinning reserves from MATPOWER-format network JSON. Produces economic dispatch report with generator outputs, reserves, line loadings, and operating margin.

not rated 66 +1 22d ago A SkillSpector: pass 41 tokens original Apache-2.0

evo-hvac-controller

31

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

HVAC PID temperature controller skill. Runs calibration, estimates first-order system parameters, tunes PID gains via IMC, executes closed-loop control, and computes performance metrics. Use for thermal control tasks with first-order plant dynamics.

not rated 66 +1 22d ago A SkillSpector: pass 50 tokens original Apache-2.0

evo-invoice-fraud

32

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Invoice fraud detection skill: extracts invoices from PDF, matches against vendor master and PO register, flags fraud using priority-ordered checks. Auto-calibrates fuzzy threshold and filters non-standard PO entries.

not rated 66 +1 22d ago A SkillSpector: pass 46 tokens original Apache-2.0

evo-jax-tasks

33

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Solve JAX numerical computing tasks from a problem.json manifest. Handles reductions, vmap, grad, scan, and jit tasks.

not rated 66 +1 22d ago A SkillSpector: pass 33 tokens original Apache-2.0

evo-receipt-ocr

34

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Extract dates and total amounts from scanned receipt images using OCR and write results to Excel. Use when processing receipt images for data extraction.

not rated 66 +1 22d ago A SkillSpector: pass 34 tokens original Apache-2.0

evo-ckd-harmonizer

35

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Harmonize clinical lab data with mixed units to US conventional units. Detects bimodal distributions from mixed unit systems, applies molecular-weight-based conversions, handles comma decimals and scientific notation.

not rated 66 +1 22d ago A SkillSpector: pass 46 tokens original Apache-2.0

evo-lake-warming

36

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Analyze lake surface water temperature trends and attribute warming to driver categories using Mann-Kendall trend test with year-based Sen slope, and per-category R-squared importance. All mappings derived at runtime.

not rated 66 +1 22d ago A SkillSpector: pass 46 tokens original Apache-2.0

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Extract display-mode LaTeX formulas from PDF research papers. Use when the task requires identifying all display-mode (own-line) formulas from a PDF, extracting them as LaTeX, cleaning tags/punctuation, detecting bracket mismatches and misspelled commands, and outputting original + fixed formulas in markdown format.

not rated 66 +1 22d ago A SkillSpector: pass 72 tokens original Apache-2.0

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Completes Lean 4 induction proofs for recursive sequence bounds. Use when a task requires proving an inequality about a recursively defined sequence (e.g., geometric series partial sums) in Lean 4 with the Math2001/Macbeth library tactics (simpleinduction, addarith, numbers, extra). Provides end-to-end proof…

not rated 66 +1 22d ago A SkillSpector: pass 80 tokens original Apache-2.0

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Normalize noisy bilingual manufacturing defect reason texts into standardized codebook entries. Derives all categories, keywords, and matching rules from supplied codebook files at runtime. Policy parameters are configurable.

not rated 66 +1 22d ago A SkillSpector: warn 43 tokens original Apache-2.0

evo-reflow-analysis

40

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Analyze reflow oven thermocouple data, MES logs, and test defects to answer questions about preheat ramp rates, TAL, peak temperature, conveyor speed, and best run selection per the handbook specifications.

not rated 66 +1 22d ago A SkillSpector: pass 47 tokens original Apache-2.0

evo-fjsp-repair

41

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Repair FJSP baseline schedules to eliminate downtime violations while respecting freeze, right-shift, and policy budget constraints. Use when given manufacturing scheduling tasks with instance.txt, downtime.csv, policy.json, and baselinesolution.json.

not rated 66 +1 22d ago A SkillSpector: pass 51 tokens original Apache-2.0

evo-mario-counter

42

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Extract keyframes from a Super Mario video, convert to grayscale, count coins/enemies/turtles using template matching with NMS and SQDIFF filtering, and output CSV results. Use when given a video file with template images for object counting.

not rated 66 +1 22d ago A SkillSpector: pass 55 tokens original Apache-2.0

evo-mars-clustering

43

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

DBSCAN hyperparameter grid search for Mars cloud clustering with Pareto frontier extraction. Use when optimizing DBSCAN parameters (minsamples, epsilon, shapeweight) to cluster citizen science annotations against expert labels.

not rated 66 +1 22d ago A SkillSpector: pass 47 tokens original Apache-2.0

evo-dubbing

44

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Multilingual video dubbing pipeline: TTS synthesis with Kokoro, temporal alignment to SRT windows, ITU-R BS.1770-4 loudness normalization, and video muxing. Use when tasked with dubbing a video from one language to another.

not rated 66 +1 22d ago A SkillSpector: pass 58 tokens original Apache-2.0

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Fill OOXML (.docx) templates by replacing {{PLACEHOLDER}} tokens with data from a JSON file. Handles placeholders split across XML runs, conditional sections (IF/ENDIF blocks), and processes all document parts including headers and footers.

not rated 66 +1 22d ago A SkillSpector: pass 58 tokens original Apache-2.0

evo-doc-organizer

46

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Organize heterogeneous documents (PDF, DOCX, PPTX) into subject-based folders using keyword-based text classification. Use when you need to sort documents into predefined categories based on their content.

not rated 66 +1 22d ago A SkillSpector: pass 44 tokens original Apache-2.0

evo-pdf-anonymizer

47

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Anonymize academic PDFs for blind peer review by redacting author names, affiliations, emails, arXiv IDs, venue info, acknowledgement names, and other identity-revealing content using PyMuPDF string-level redaction.

not rated 66 +1 22d ago A SkillSpector: pass 54 tokens original Apache-2.0

evo-parallel-tfidf

48

Zhang-Henry/CoEvoSkills

Skill Claude CodeCodex

Parallelize a sequential TF-IDF search engine using Python multiprocessing. Covers parallel index building (tokenization, TF, DF, IDF, inverted index, doc vectors) and parallel batch query search. Produces identical results to sequential with 1.5x+ indexing and 2x+ search speedup on 4 workers.

not rated 66 +1 22d ago A SkillSpector: pass 75 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: