Delegate

Use when a coding request contains work you can write a tight spec for and verify from a diff: boilerplate, scaffolding, repetitive edits, test stubs and docstrings, but equally a whole module from a clear contract, a real multi-file refactor, a non-trivial first-draft implementation or a clear-spec bug fix. Offloads it to a headless worker via the delegate CLI, then reviews the git diff. Do not route by hand: name no backend and the worker runs free ($0) and escalates to deepseek itself. The gate is a good spec, not low difficulty. Keeps design, tricky debugging, security-sensitive code, deep

1 starsSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add aayushpokhrel1/delegation-pipeline --skill delegate

Manual install

git clone --depth 1 https://github.com/aayushpokhrel1/delegation-pipeline.git /tmp/delegation-pipeline
mkdir -p ~/.claude/skills
cp -r /tmp/delegation-pipeline/skills/delegate ~/.claude/skills/delegate

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# delegate

Hand work to a cheap or free model worker so the paid Claude session spends its usage on
thinking, not typing. Not just mechanical work: anything you can specify precisely and check
from a diff, up to a whole module or a real refactor. The worker
(`~/.claude/bin/delegate`) is a zero-dependency
Python agent over any OpenAI-compatible endpoint. It can read, search, and edit files in the
current repo. It **cannot** run shell or git, by design: you review the resulting `git diff`
and commit.

Installing this plugin is enough: a `SessionStart` hook writes the `~/.claude/bin/delegate`
launcher pointing at the plugin's own copy. `install.sh` / `install.ps1` are only for working
on a clone, where the launcher points at your checkout instead. A backend still needs setup,
either a local OmniRoute gateway for `free` or an API key for a remote tier. See the
[README](https://github.com/aayushpokhrel1/delegation-pipeline) for backends and keys.

## When to use

The gate is whether you can write a tight, verifiable spec, NOT how hard the task is.

**Do not route by hand. Name no backend.** `delegate "<task>"` runs on `free` ($0) and
escalates once to `deepseek` by itself if `free` cannot be reached. Measured on
`bench/tasks.json` (2026-10-01): reviewing a `free` diff costs the same as reviewing a paid
one (85.4% vs 85.6% median savings), so `free` is not the lower-quality tier, only the less

Read the full skill on GitHub

Details

Skill name: delegate
Repository: aayushpokhrel1/delegation-pipeline
Path: skills/delegate/SKILL.md
License: MIT
Repo updated: 27 October 2026
Listed in: karanb192/awesome-claude-skills

FAQ

What does the Delegate skill do?

How do I install the Delegate skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add aayushpokhrel1/delegation-pipeline --skill delegate. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Delegate popular?

It lives in aayushpokhrel1/delegation-pipeline, which has 1 GitHub stars and 0 forks, and is included in 1 curated skill list.

Related skills

Apitube News API

apitube/news-api-skills

Query the APITube News API — authenticate, search and filter worldwide news articles by keyword, entity, sentiment, source, country and date, and parse the JSON response. Use when an agent needs live or historical news data, media monitoring, or news for a RAG pipeline.

Software DevelopmentIn 2 lists

What Could Break

stas4000/what-could-break

Find what a change could break outside its own diff, then prove the one fact that makes it safe by running real code instead of writing an essay. Use before any multi-file edit or an edit to a shared path (API payload, config, stored data, a client other apps read, a prompt or policy file), when asked 'what could this break' or 'blast radius of X', for a small diff you do not trust, or when a task asserts something about existing code ('X already handles Y', 'just make X public') before you design against that assertion.

Software DevelopmentIn 1 list

Deacon Install

heydeacon/skills

Install the Deacon support widget on a website or web app: place one script tag on every page, tell Deacon who is signed in, and confirm from the command line that a real page has loaded it. Use when asked to install Deacon, add its snippet or embed code, or set it up on a site.

Software DevelopmentIn 1 list

Runapi CLI

runapi-ai/cli-skill

Use the RunAPI CLI for one-off artifacts and results, or RunAPI's standard x402 REST flow for wallet-funded Task calls without an API key. Use when an agent needs to discover models or prices, create a paid Task, poll its result, or run a supported CLI service. Use an SDK for app or production integration.

Software DevelopmentIn 1 list

Simmer Tennis Live Gate

livetennisapi/simmer-tennis-live-gate

Gate Simmer/Polymarket tennis market entries on the live match state (score, who is serving, break-point flag, retirement/walkover/suspension) from the Live Tennis API. Observe-only — it returns a trade/no-trade decision and a suggested size; it places no orders. Modeled line-for-line on simmer-sdk's regime_gate_skill.py. Use when a tennis strategy should not fire into a break point or a stopped match.

Software DevelopmentIn 1 list

Punchcard

Maksim-Burtsev/punchcard

Architecture-level design review of a code change: module boundaries, dependency direction, data model, error paths, cost of the next change — never naming, formatting, or anything a linter catches. Use when the user invokes /punchcard, says 'punchcard review', or asks for any design, architecture, or structural review of a diff, branch, merge request, or PR. Do not use for general correctness/bug review, style feedback, or whole-repo audits.

Software DevelopmentIn 1 list

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.