Inno Prepare Resources

inno-prepare-resources

Canonical Summary

Loads the evaluation instance, searches GitHub for related repositories, builds a dataset description, queries the Prepare Agent for reference codebases, and downloads arXiv paper sources. Covers both Idea mode and Plan mode (the only diff...

Trigger Rules

Use this skill when the user request matches its research workflow scope. Prefer the bundled resources instead of recreating templates or reference material. Keep outputs traceable to project files, citations, scripts, or upstream evidence.

Resource Use Rules

• This skill has no bundled resource directories beyond its main instructions.

Execution Contract

• Resolve every relative path from this skill directory first.
• Prefer inspection before mutation when invoking bundled scripts.
• If a required runtime, CLI, credential, or API is unavailable, explain the blocker and continue with the best manual fallback instead of silently skipping the step.
• Do not write generated artifacts back into the skill directory; save them inside the active project workspace.

Upstream Instructions

Inno Prepare Resources

Inputs

Read from instance.json. Path values are absolute when the project is created by Dr. Claw; use as-is. If relative (e.g. hand-edited), resolve with path.join(project_path, value).

Outputs

Cache file outputs

Every intermediate result must be persisted as a JSON file under Ideation/references/logs/. The directory layout follows:

Ideation/references/logs/
├── load_instance.json                  ← written by orchestrator
├── github_search.json
├── download_arxiv_source_by_title.json
└── prepare_agent.json

Ideation/references/logs/load_instance.json is written by the orchestrator before this skill runs — do not overwrite it.

Tool cache format (tools/*.json)

Each tool output file records the function call arguments and result:

{
  "name": "<tool_name>",
  "args": { ... },
  "result": <result_value>
}

github_search.json — written after Step 2:

{
  "name": "github_search",
  "args": {
    "metadata": {
      "source_papers": [ ... ],
      "task_instructions": "...",
      "date_limit": "YYYY-MM-DD"
    }
  },
  "result": "<concatenated github_result string>"
}

download_arxiv_source_by_title.json — written after Step 6:

{
  "name": "download_arxiv_source_by_title",
  "args": {
    "paper_list": ["paper title 1", "paper title 2"],
    "references_path": "<instance.Ideation.references if absolute, else path.join(project_path, instance.Ideation.references)>"
  },
  "result": "<download result log string>"
}

Agent cache format (agents/*.json)

Each agent output file records the final context variables (no conversation messages):

{
  "context_variables": {
    "references_path": "<use instance.Ideation.references as-is if absolute, else path.join(project_path, ...)>",
    "code_references_path": "<use instance.Experiment.code_references as-is if absolute, else path.join(project_path, ...)>",
    "datasets_path": "<use instance.Experiment.datasets as-is if absolute, else path.join(project_path, ...)>",
    "date_limit": "YYYY-MM-DD",
    "prepare_result": {
      "reference_codebases": ["repo1", "repo2"],
      "reference_paths": ["Experiment/code_references/repo1", "Experiment/code_references/repo2"],
      "reference_papers": ["paper title 1", "paper title 2"]
    }
  }
}

prepare_agent.json — written after Step 4–5. Contains the final context_variables with prepare_result holding reference_codebases, reference_paths, and reference_papers.

Step-by-step Instructions

Step 1 — Load the evaluation instance

Call load_instance(instance.instance, task_level) — when created by Dr. Claw, instance.instance is already absolute; otherwise resolve with path.join(project_path, instance.instance).

This reads the instance JSON and returns an EvalMetadata object containing:

• source_papers — list of dicts, each with reference, rank, type, justification, usage
• task_instructions — the task description text (from the field named by task_level)
• date_limit — the publication date of the target paper (fetched from arXiv via the instance url); defaults to "2024-01-01" if metadata cannot be retrieved

Write date_limit into context_variables["date_limit"].

Note: Ideation/references/logs/load_instance.json should already exist — it was written by the orchestrator. If not, write it now following the tool cache format.

Graceful handling: If the instance JSON was constructed by the orchestrator and has no url or an empty source_papers list, use a sensible default date_limit and continue — do not raise an error.

Step 2 — Search GitHub for related repositories

Call github_search(metadata).

Iterate over every entry in metadata["source_papers"]. For each paper, use its reference (title) as the search query and call the GitHub Search Repositories API:

GET https://api.github.com/search/repositories?q=<paper_title>&per_page=10&page=1

From each result item, extract:

• name: {owner}/{repo}
• description: repository description
• link: html_url

Format each paper's results as a human-readable block:

Here are some of the repositories I found on GitHub:
    Name: owner/repo
    Description: ...
    Link: https://github.com/owner/repo

Concatenate all papers' results into a single github_result string, using a ****************************** separator between papers.

Rate-limit handling: wait ~2 seconds between consecutive GitHub API calls to avoid HTTP 403 throttling. The last paper does not need a delay.

Fallback when source_papers is empty: use keywords extracted from task_instructions as the search query instead, and perform a single GitHub search call to find relevant repositories.

Save → Ideation/references/logs/github_search.json