# Infrastructure Sia

> 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.

- **Type:** Skill
- **Install:** `agentstack add skill-docxology-template-sia`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [docxology](https://agentstack.voostack.com/s/docxology)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [docxology](https://github.com/docxology)
- **Source:** https://github.com/docxology/template/tree/main/infrastructure/sia
- **Website:** https://doi.org/10.5281/zenodo.19139090

## Install

```sh
agentstack add skill-docxology-template-sia
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# SIA Harness

Deterministic harness for Meta → Target → Feedback generation loops with
public/private task splits. Implements contracts inspired by
[hexo-ai/sia](https://github.com/hexo-ai/sia); does not vendor upstream code.

## Commands

```bash
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/02_run_analysis.py --project templates/template_sia
```

## Public API

```python
from infrastructure.sia import (
    RunConfig,
    TaskLayout,
    load_agent_execution,
    run_evaluation,
    run_sia_loop,
    validate_task_dir,
)
```

## Task layout

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_samples`
- `data/private/` — evaluation-only labels
- `reference/` — baseline target agent (`reference/reference_target_agent.py` required)

## Exemplar project

[`projects/templates/template_sia/`](../../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.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [docxology](https://github.com/docxology)
- **Source:** [docxology/template](https://github.com/docxology/template)
- **License:** Apache-2.0
- **Homepage:** https://doi.org/10.5281/zenodo.19139090

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-docxology-template-sia
- Seller: https://agentstack.voostack.com/s/docxology
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.