Skip to main content
skill CX Codex

skill-pipeline — Claude Code skill: what it does, how to install

skill-pipeline sizes up a coding task, then decides which skills to switch on: nothing extra for a typo, planning plus checks and failure recovery for a big refactor.

no license 114 installs ★ 341 updated 2026-10-19

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add pskoett/pskoett-ai-skills --skill skill-pipeline -a claude-code
Open on GitHub

What skill-pipeline does

Think of it as the conductor. It writes nothing into the project itself; its output is routing. Every task gets a size first: typo, single-file fix, feature across a few files, big refactor, multi-session work, batch of tasks. A typo needs no skills at all. A small fix gets verify-gate and simplify-and-harden. Medium adds intent-framed-agent and session-context. Large runs the full sequence and suggests opening with /plan-interview.

One loop lives inside a session: frame the intent, pull bounded context, implement, check compile and tests, recover through self-healing when a command or build fails. The other loop spans sessions: learning-aggregator looks for repeats in .learnings/, self-improvement turns the human-approved ones into project instructions, eval-creator writes them as standing tests. The pre-flight-check hook brings earlier findings back at session start. Batch work is cut into bounded units with a gate after each. In CI, with CI=true or GITHUB_ACTIONS=true set, the pipeline switches to a headless pass over the files a PR touches.

The companion skills have to be there first. skill-pipeline dispatches to verify-gate, self-healing and the rest rather than replacing them, so routing with none of them installed goes nowhere. Edge cases sit in references/classification-rules.md.

What it helps with

  • split a large feature into bounded units with a gate after each
  • match the depth of checking to the size of the task
  • carry past fixes and findings into a fresh session
  • recover when a test or build breaks mid-task
  • turn recurring mistakes into a project rule

Example prompts for the agent

  • Classify this task and pull in the skills it needs — one file changed, but the logic is risky.
  • This will span several sessions: cut it into bounded units and gate each one.
  • Run the outer loop: pull patterns out of .learnings/ and propose what to promote.

How to install skill-pipeline

1Skills CLI (Vercel)

npx skills add pskoett/pskoett-ai-skills --skill skill-pipeline -a claude-code

2Manually: put the files in place

~/.claude/skills/skill-pipeline/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/skill-pipeline/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about skill-pipeline

How do I install skill-pipeline in Claude Code?

Run npx skills add pskoett/pskoett-ai-skills --skill skill-pipeline -a claude-code. The skill file lands at ~/.claude/skills/skill-pipeline/SKILL.md.

What does skill-pipeline do?

It judges how big a task is, then picks which skills to call and how deep to go. It produces no artifacts of its own; routing is the whole output.

Does it replace the other skills in the repository?

No. It calls them. verify-gate, self-healing, plan-interview and the rest still have to be installed separately, or the routing has nothing to hand off to.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set10

The whole set →
self-improvement-ci self-improvement-ci — a CI-only skill that groups recurring pull request check failures and proposes rules so the same breakage stops coming back. CX Codex +1 550installs simplify-and-harden simplify-and-harden is a Claude Code skill that reviews code after a task is complete: it simplifies and hardens the code, re-verifies changes and briefly documents non-obvious decisions while the agent remembers their intent. CX Codex +1 543installs plan-interview plan-interview — a skill for Claude Code, Codex, Cursor, GitHub Copilot, and other agents: runs a structured requirements interview across four domains before the agent reads any code. CX Codex +1 491installs intent-framed-agent The intent-framed-agent skill writes down what a coding session is supposed to achieve before edits start, then watches for work that wanders off. Handy on long refactors and feature builds. CX Codex +1 440installs simplify-and-harden-ci simplify-and-harden-ci — a skill that reviews pull requests inside CI: it scans changed files, posts findings, and can stop a merge. CX Codex +1 393installs context-surfing context-surfing monitors context coherence during extended coding sessions, saving state and performing clean handoffs before hallucinations ruin output. CX Codex +1 272installs self-healing self-healing — a skill for Claude Code and Codex helps an agent diagnose failures during a task and test its fix. It activates after a command, test, build, or lint run fails. CX Codex +1 109installs pskoett-ai-skills pskoett-ai-skills is a Claude Code plugin that adds checks to an agent's workflow: plan agreement, context control, code audits and saved lessons. ★ 341repo stars

Project sponsors

Companies that keep this analytics open