Runcastle

8 workflows

Diff + log → PR description

PR Description Writer

v1.0.1

runcastle

A single Claude Code agent reads the diff and commit history of your branch against its base, then writes a complete, reviewer-ready PR_DESCRIPTION.md — summary, what changed, why, testing, risk, and a reviewer checklist — grounded entirely in the real diff.

claude-code · claude-sonnet-4-6
docker10
#pull-request#documentation#single-agent#git
npm installgit ls-files (re…Write & commit d…

Docs From Codebase

v1.0.1

runcastle

A single Claude Code agent reads your repository — a shell-expanded file map seeds it, and it can install and run the project — then writes and incrementally commits a real `docs/` set: a getting-started guide, an architecture overview, and per-module reference pages.

claude-code · claude-opus-4-8
docker00
#documentation#content#single-agent#loop
Write AIDA copy …Edit + tighten (…

Landing Page Copy (AIDA) + Edit

v1.0.1

runcastle

A mixed-provider copy pipeline: a Claude Code writer turns your product brief into full AIDA-structured landing page copy, then a Codex editor cuts fluff, makes claims concrete, and tightens headlines on the same warm branch, looping until it ships.

claude-code · claude-opus-4-8codex · gpt-5.4
docker00
#copywriting#landing-page#content#mixed-provider
Draft thread (Cl…Critique + rewri…

Launch Thread Writer + Critic

v1.0.1

runcastle

A Claude Code writer drafts an X/Twitter launch thread from your product brief, then a Codex critic tears it apart post-by-post — hook, clarity, specificity, CTA — rewriting the weak posts on the same warm branch until the thread is ready to ship.

claude-code · claude-opus-4-8codex · gpt-5.4
docker00
#marketing#social#copywriting#mixed-provider
npm installRefactor (Cl…npm test (ga…Adversarial …

Refactor with Adversarial Review

v1.0.1

runcastle

A Claude Code agent performs a refactor, a hard `npm test` gate proves nothing broke, then a Codex reviewer adversarially audits the change on the same warm branch — hunting regressions, weak tests, and shortcuts — fixing and looping until it approves.

claude-code · claude-sonnet-4-6codex · gpt-5.4
docker00
#refactor#review-pipeline#mixed-provider#codex
CSV -> analysis -> narrative

Weekly Metrics Narrative

v1.0.1

runcastle

A single Claude Code agent reads a metrics.csv, computes week-over-week deltas, and writes an executive narrative — what moved, why it likely moved, what to watch, and one recommended action — alongside a compact metrics table, to reports/weekly.md.

claude-code · claude-sonnet-4-6
docker00
#ops#metrics#reporting#single-agent
Read offer + ICP -> 5-touch s…

Cold Email Sequence Drafter

v1.0.1

runcastle

A single Claude Code agent reads your offer and ideal-customer notes and writes a complete 5-touch cold email sequence — subject-line options, tight bodies, send timing, one clear CTA per email, and personalization tokens ready to merge at send time.

claude-code · claude-opus-4-8
docker00
#marketing#email#outreach#single-agent
Search (xN)Synthesize reportFact-check (Code…

Deep Research Report

v1.0.1

runcastle

Fans out a searcher per sub-question to fetch and note public web sources, then an Opus synthesizer writes a fully cited report, then a Codex fact-checker adversarially verifies every claim against the notes and loops until the report holds up.

claude-code · claude-sonnet-4-6claude-code · claude-opus-4-8codex · gpt-5.4
docker00
#research#fan-out#citations#mixed-provider