Skip to content
Agentmart
Submit a tool

ai-pipeline-patterns

Use when changing the AI workflow, embeddings, Qdrant integration, newsletter intake, relevance scoring, summarization, classification, Taskiq handoff, or…

Skill by webstackdev

IndexedAGPL-3.0★ 1
Write a review

Chalk Labs

Need help deploying ai-pipeline-patterns?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/webstackdev-ai-pipeline-patterns

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when changing the AI workflow, embeddings, Qdrant integration, newsletter intake, relevance scoring, summarization, classification, Taskiq handoff, or Anymail inbound processing. Trigger phrases include pipeline, relevance scoring, embeddings, Qdrant, newsletter intake, summarization, classification, OpenRouter, and review queue.

Use cases: data, marketing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ai-pipeline-patterns

What's inside

Skill name
ai-pipeline-patterns
Description
Use when changing the AI workflow, embeddings, Qdrant integration, newsletter intake, relevance scoring, summarization, classification, Taskiq handoff, or Anymail inbound processing. Trigger phrases include pipeline, relevance scoring, embeddings, Qdrant, newsletter intake, summarization, classification, OpenRouter, and review queue.
License
AGPL-3.0
Instructions
50 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# AI Pipeline Patterns Skill

Use this skill when working on the ingestion and AI processing pipeline.

## Scope

This skill covers the interaction between:

- `core/pipeline.py`
- `core/embeddings.py`
- `core/tasks.py`
- `core/newsletters.py`
- `core/newsletter_extraction.py`
- `core/signals.py`
- `core/views.py`
- related models, tests, and docs

## Rules

- Preserve the separation between persisted state, background execution, and vector storage.
- Keep Qdrant access inside the embedding layer unless there is a strong reason to expand that boundary.
- Keep newsletter intake routing and confirmation logic in the newsletter intake modules, not in unrelated views or serializers.
- Prefer explicit fallbacks when LLM or external-service calls can fail.
- Respect the current thresholds and routing semantics around relevance scoring, summarization eligibility, and review-queue creation unless the change intentionally redefines them.
- When changing provider behavior, preserve provider-agnostic boundaries where they already exist, such as Anymail for inbound and Django mail abstractions for outbound.
- Update docs when pipeline behavior changes in a way a new developer or operator would need to understand.

## Implementation Guidance

- For embedding or vector-search changes, start in `core/embeddings.py` and then verify the downstream callers in `core/pipeline.py` and `core/tasks.py`.
- For newsletter intake changes, start in `core/newsletters.py` or `core/signals.py` and follow the path through `NewsletterIntake`, `IntakeAllowlist`, and `process_newsletter_intake`.
- For project routing or user-facing confirmation behavior, verify both `core/views.py` and top-level URL registration.
- For AI-skill output changes, check how `SkillResult` rows are persisted and how admin or frontend surfaces consume them.

## Validation

- Prefer focused checks first:
  - `pytest core/tests/test_pipeline.py`
  - `pytest core/tests/test_tasks.py`
  - `pytest core/tests/test_newsletters.py`
  - `python manage.py check`
- If a change affects serializers, admin, or API surfaces too, expand validation to the nearest related test module.

## References

- `docs/DEVELOPER_GUIDE.md`
- `docs/RELEVANCE_SCORING.md`
- `docs/LOGGING.md`

From webstackdev/digest-engine, AGPL-3.0.

More from webstackdev/digest-engine

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
May 22, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
AGPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from webstackdev

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get ai-pipeline-patterns running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying ai-pipeline-patterns?

CallGet help
Cite this page

ai-pipeline-patterns skill. Agent Mart. https://agentmart.dev/skills/webstackdev-ai-pipeline-patterns (last updated 2026-10-24)