data_pipeline

Name: data_pipeline
Author: sherlock0717

Apply these instructions to files under: - scripts/ - config/ - prompts/ - schemas/

by sherlock0717(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Instruction file imported from sherlock0717/AI_agent_bootstrap_pack_stage3 (.github/instructions/data_pipeline.instructions.md). Copyright stays with the author.

Data pipeline path-specific instructions

Apply these instructions to files under:

scripts/
config/
prompts/
schemas/

Rules

Never silently change CSV column names used downstream.
Keep input and output file arguments explicit.
Add failure logging for network or parse errors.
Prefer deterministic preprocessing in Python over AI-based cleaning when possible.
AI-generated labels must remain clearly separated from manual labels.
Any new JSONL output should contain stable IDs.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/sherlock0717-ai-agent-bootstrap-pack-stage3-data-pipelin-a118d3/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

sherlock0717-ai-agent-bootstrap-pack-stage3-data-pipelin-a118d3.ocm.jsonjson

{
  "ocm": "1",
  "id": "sherlock0717-ai-agent-bootstrap-pack-stage3-data-pipelin-a118d3",
  "kind": "skill",
  "name": "data_pipeline",
  "description": "Apply these instructions to files under: - scripts/ - config/ - prompts/ - schemas/",
  "publisher": "sherlock0717",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github-instructions"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Apply these instructions to files under: - scripts/ - config/ - prompts/ - schemas/"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-instructions",
      "repository": "https://github.com/sherlock0717/AI_agent_bootstrap_pack_stage3",
      "path": ".github/instructions/data_pipeline.instructions.md",
      "ref": "36f1e9adf73b20cd5cb0fe4b962366e7ef0ed4b2",
      "url": "https://github.com/sherlock0717/AI_agent_bootstrap_pack_stage3/blob/36f1e9adf73b20cd5cb0fe4b962366e7ef0ed4b2/.github/instructions/data_pipeline.instructions.md",
      "key": "sherlock0717/AI_agent_bootstrap_pack_stage3/.github/instructions/data_pipeline.instructions.md"
    }
  },
  "instructions": "# Data pipeline path-specific instructions\n\nApply these instructions to files under:\n- scripts/\n- config/\n- prompts/\n- schemas/\n\n## Rules\n- Never silently change CSV column names used downstream.\n- Keep input and output file arguments explicit.\n- Add failure logging for network or parse errors.\n- Prefer deterministic preprocessing in Python over AI-based cleaning when possible.\n- AI-generated labels must remain clearly separated from manual labels.\n- Any new JSONL output should contain stable IDs.",
  "cost": {
    "context_tokens": 125
  }
}

Fetch it by URL: GET /api/v1/registry/sherlock0717-ai-agent-bootstrap-pack-stage3-data-pipelin-a118d3/manifest?version=1.0.0

About

Data pipeline path-specific instructions

Rules

Use it

Manifest

Reviews