菜单
Skill for the Self-Improvement Agent (SIA) harness contract. Use when validating task public/private layouts, generation artifact trees, evaluation runners, fixture replay loops, or opt-in live Meta→Target→Feedback cycles in template projects.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Skill for the core infrastructure module providing logging, configuration, exception handling, progress tracking, checkpoints, retry logic, pipeline execution, performance monitoring, security, file operations, and multi-project orchestration. Use when setting up logging, loading config, handling errors, running pipelines, or monitoring performance.
Skill for the documentation infrastructure module providing figure management, image handling, markdown integration, and API glossary generation. Use when managing research figures, inserting images into manuscripts, auto-numbering figures, or generating API documentation.
Skill for the LLM infrastructure module providing local Large Language Model integration via Ollama. Covers client initialization, prompt templates, output validation, manuscript review generation, conversation context, and CLI usage. Use when querying LLMs, generating manuscript reviews, validating LLM outputs, or managing Ollama models.
Python CLI and menu orchestration for pipeline runs — project slug validation, interactive picker, PipelineRunner wrapping PipelineExecutor, per-stage logs, secure pipeline wrapper. Use when extending run.sh behavior, fixing menu/CLI routing, or testing discovery helpers.
Skill for the project management infrastructure module providing multi-project discovery, structure validation, and metadata extraction. Use when discovering active projects, validating project directory structure, or extracting project configuration metadata.
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub Pages / Cloudflare Pages / Netlify, multi-target long-horizon archival (IPFS Pinata, Web3.Storage, Software Heritage), a central platform registry, and publication readiness validation. Use when publishing research, generating citations, minting DOIs, distributing Python packages, deploying documentation sites, or preparing archival submissions.
| name | infrastructure-sia |
| description | Skill for the Self-Improvement Agent (SIA) harness contract. Use when validating task public/private layouts, generation artifact trees, evaluation runners, fixture replay loops, or opt-in live Meta→Target→Feedback cycles in template projects. |
Deterministic harness for Meta → Target → Feedback generation loops with public/private task splits. Implements contracts inspired by hexo-ai/sia; does not vendor upstream code.
uv run python -m infrastructure.sia.cli validate projects/templates/template_sia/tasks/mini_classify
uv run python -m infrastructure.sia.cli inspect-run RUN_SUMMARY_JSON [--json]
uv run python scripts/pipeline/stage_02_analysis.py --project templates/template_sia
from infrastructure.sia import (
RunConfig,
TaskLayout,
load_agent_execution,
run_evaluation,
run_sia_loop,
validate_task_dir,
)
Each task directory exposes:
data/public/ — agent-visible inputs
data/public/task.md — required task description (validate_task_dir hard-fails if absent)data/public/evaluate.py — writes results.json with metric_name, metric_value, n_samplesdata/private/ — evaluation-only labelsreference/ — baseline target agent (reference/reference_target_agent.py required)projects/templates/template_sia/ runs
fixture replay by default (live=False). Pass --live-sia on
scripts/run_sia_loop.py for opt-in Ollama-backed feedback (not CI) — the
feedback note is illustrative, not applied; live mode performs no code mutation
and uses no sandbox, so cross-generation improvement is shown only via fixtures.