distillation skills

36 tagged distillation, measured the same way as everything else here.

Browse within: Post-Training 17diffusers 17diffusion-models 17inference 17video-generation 17ai-skill 9agent-skill 8digital-immortality 7digital-twin 7LoRA 5fine-tuning 5llm-evaluation 5

add-model

01

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Manual /add-model workflow for implementing a FastVideo model or first-class component port after add-model-01-prep has staged reference code and weights. Organizes the port into numbered phases with conversion rules, component policies, parity gates, and handoff checks.

4.2k 2d ago A 55 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Re-seed the HF performance-tracking baseline for an intentional runtime, dependency, environment-caused benchmark shift, or reviewed v2 calibration using one or more reviewed normalized performance JSONs. Use when performance CI fails because metrics such as latency, throughput, component time, or peak memory changed…

4.2k 2d ago A 162 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Seed HF reference artefacts for a single newly-added SSIM test (pixel .mp4 for runtexttovideosimilaritytest-style tests, or latent .pt for runtexttolatentsimilaritytest-style tests). Runs the test on Modal L40S, downloads the generated artefacts via modal volume get, pauses for the user to verify (visual eyeball for…

4.2k 2d ago A 146 tokens original Apache-2.0

relic

04

Ylsssq926/relic.skill

Skill Claude CodeCodex

A system for turning people, pets, relationships, teams, places, moments, or other subjects into interactive digital profiles called Relics. It can also let users interact with existing profiles and includes separate steps for creating and protecting them.

75 2mo ago A 187 tokens original MIT

relic-talk

05

Ylsssq926/relic.skill

Skill Claude CodeCodex

A conversation mode for bringing a stored fictional or historical persona, called a Relic, into dialogue using its files, personality, memories, and interaction rules. It treats the result as a digital recreation, not the real person.

75 2mo ago A 44 tokens original MIT

relic-forge

06

Ylsssq926/relic.skill

Skill Claude CodeCodex

A guided process for turning material about a person, pet, relationship, team, place, moment, or object into a reusable digital profile called a Relic. It can work from conversations, photos, voice recordings, or a user's descriptions.

75 2mo ago A 82 tokens original MIT

aoye-perspective

07

cyber-immortal/cyber-figures

Skill Claude CodeCodex

A Chinese-language relationship consultation skill based on the methods and speaking style of 月老鳌烨, a marriage and dating adviser.

56 4mo ago A 160 tokens

听泉鉴宝

08

cyber-immortal/cyber-figures

Skill Claude CodeCodex

A Chinese-language skill for judging objects from photos or descriptions in the style of 听泉鉴宝, an object-appraisal personality.

56 4mo ago A 40 tokens

PersonaLingo

09

orzcls/PersonaLingo

Skill Claude CodeCodex

A guided tool for creating personalised IELTS speaking practice materials. IELTS is an English exam, and the tool turns a learner’s answers and conversation into a personal profile and a static study website.

33 2mo ago A 80 tokens original MIT

runyuan-wang/book-to-skill-distillation

Skill Claude CodeCodex

End-to-end workflow for rewriting a book, long PDF, EPUB, manual, course, guideline library, same-domain multi-book source pack, large database, or methodology into an agent-native LingTai / Agent Skill structure. Use when the task is not a summary, but a reusable skill/knowledge system: source triage…

9 2mo ago A 120 tokens

tune-data

11

rchaz/tunelab

Skill Claude CodeCodex

Build a training dataset for fine-tuning, distillation, or continued pretraining. Use when the user wants to turn logs/CSV/JSONL into fine-tuning data, label data with an LLM, distill a teacher model's outputs, generate synthetic training examples from nothing, chunk raw domain text for CPT, deduplicate a dataset…

6 1mo ago A 108 tokens original MIT

tune-decide

12

rchaz/tunelab

Skill Claude CodeCodex

The tunelab front door — decides whether a task needs fine-tuning at all, by running EXPERIMENTS on the user's data, not just interviewing. Use whenever the user wants to fine-tune, distill, or train a small/local model, cut their LLM API bill, replace frontier calls with something cheaper or faster, build a…

6 1mo ago A 210 tokens original MIT

tune-eval

13

rchaz/tunelab

Skill Claude CodeCodex

Evaluate a fine-tuned, distilled, or continued-pretrained model with held-out test discipline — the honest scoreboard at the end of the tunelab pipeline. Pre-registers the acceptance bar and metric set BEFORE results exist, runs the untouched test split through base and tuned models, scores classification (accuracy…

6 1mo ago A 207 tokens original MIT

anyone-skill

14

acnlabs/anyone-skill

Skill Claude CodeCodex

Distill anyone into a runnable OpenPersona skill pack — real or fictional, personal or public, living or historical. Collects chat logs, documents, and public content, extracts a 4-dimension persona, and generates a portable OpenPersona pack via skills/open-persona. Use when asked to distill, clone, or create a…

3 4mo ago B 79 tokens