{"id":51041872,"url":"https://github.com/voidful/alchemistplaybook","last_synced_at":"2026-06-22T11:02:07.571Z","repository":{"id":365591679,"uuid":"1266774244","full_name":"voidful/AlchemistPlaybook","owner":"voidful","description":"Evidence-based training recipe skill for model tuning","archived":false,"fork":false,"pushed_at":"2026-06-18T01:42:44.000Z","size":135,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-18T03:23:44.803Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/voidful.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-06-12T00:06:28.000Z","updated_at":"2026-06-18T01:42:48.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/voidful/AlchemistPlaybook","commit_stats":null,"previous_names":["voidful/alchemistplaybook"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/voidful/AlchemistPlaybook","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FAlchemistPlaybook","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FAlchemistPlaybook/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FAlchemistPlaybook/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FAlchemistPlaybook/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/voidful","download_url":"https://codeload.github.com/voidful/AlchemistPlaybook/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/voidful%2FAlchemistPlaybook/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34645688,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-22T02:00:06.391Z","response_time":106,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-22T11:02:06.693Z","updated_at":"2026-06-22T11:02:07.560Z","avatar_url":"https://github.com/voidful.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Alchemist Playbook\n\nEvidence-based training-recipe skill for model training and tuning. The skill\nturns published training recipes into a practical diagnostic workflow for\npretraining, SFT, DPO/RLHF/RLVR, LoRA/QLoRA, and speech training runs.\n\n## Contents\n\n- `alchemist-playbook/` - source skill directory.\n- `alchemist-playbook.skill` - packaged skill archive.\n- `alchemist-playbook-workspace/` - evaluation workspace and iteration output.\n- `AGENTS.md` - original project instruction.\n\n## Use\n\nInstall or import `alchemist-playbook.skill` in a Codex environment that accepts\nskill archives, or inspect `alchemist-playbook/SKILL.md` directly for the\nworkflow and routing table.\n\nFor quantitative estimates, use:\n\n```bash\npython alchemist-playbook/scripts/estimate.py batch --gpus 8 --micro 4 --seq 4096 --accum 8\npython alchemist-playbook/scripts/estimate.py lr --params 8e9 --stage sft\n```\n\n## Validation\n\nThe packaged archive contains the skill source, references, helper script, and\ntraining templates. The workspace includes a first evaluation iteration for\nrecipe debugging and config review tasks.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Falchemistplaybook","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvoidful%2Falchemistplaybook","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvoidful%2Falchemistplaybook/lists"}