AGENT SKILL

self-improvement-ci

CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
self-improvement-ci
description
CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks, emits structured learning candidates, and proposes durable prevention rules without interactive prompts. Use when: you want automated learning capture in CI/headless pipelines.

02 资源文件 1

03 SKILL.md 正文

Self-Improvement CI

Install

gh skill install pskoett/pskoett-skills self-improvement-ci

Fallback using the Agent Skills CLI:

npx skills add pskoett/pskoett-skills/skills/self-improvement-ci

Purpose

Run self-improvement in CI without interactive chat loops:

  • Inspect PR check results and CI failures
  • Ingest learning candidates from simplify-and-harden-ci
  • Deduplicate recurring patterns by stable pattern_key
  • Emit promotion-ready suggestions for agent context/system prompts

Use self-improvement for interactive/local sessions.

Context Limitation (Important)

CI agents do not have peak task context from the original implementation session. Use this skill to aggregate recurring patterns across runs, not to infer nuanced one-off intent.

Implications:

  • Favor stable pattern_key recurrence signals over single-run conclusions
  • Require recurrence thresholds before promotion
  • Route uncertain or high-impact recommendations to interactive review

Prerequisites

  1. GitHub Actions enabled for the repository
  2. GitHub CLI authenticated (gh auth status)
  3. gh-aw installed for authoring/validation:
gh extension install github/gh-aw

CI Contract

The CI skill must:

  1. Read only PR-scoped data (checks, workflow outcomes, existing learning entries)
  2. Avoid direct code modifications in CI
  3. Emit machine-readable learning output
  4. Recommend promotion only when recurrence thresholds are met

Output Schema

self_improvement_ci:
  source:
    pr_number: 123
    commit_sha: "abc123"
  candidates:
    - pattern_key: "harden.input_validation"
      source: "simplify-and-harden-ci"
      recurrence_count: 3
      first_seen: "2026-02-01"
      last_seen: "2026-02-20"
      severity: "high"
      suggested_rule: "Validate and bound-check external inputs before use."
      promotion_ready: true
  summary:
    candidates_total: 4
    promotion_ready_total: 1
    followup_required: true

Recurrence and Promotion Rules

  • Track recurrence by pattern_key
  • Default threshold for promotion:
    • recurrence_count >= 3
    • seen in >= 2 distinct tasks/runs
    • within a 30-day window
  • Promotion targets:
    • CLAUDE.md
    • AGENTS.md
    • .github/copilot-instructions.md
    • SOUL.md / TOOLS.md when using openclaw workspace memory

Authoring Workflow (gh-aw)

Example-only templates live in references/workflow-example.md. Keep examples outside .github/workflows until you explicitly decide to enable CI automation.

When ready:

  1. Copy the template into .github/workflows/self-improvement-ci.md
  2. Customize tool access, outputs, and policy thresholds
  3. Validate:
gh aw compile --validate --strict
  1. Trigger test run manually:
gh aw run self-improvement-ci --push

Integration with Other Skills

  • Pair with simplify-and-harden-ci to ingest simplify_and_harden.learning_loop.candidates
  • Feed promoted patterns back into self-improvement memory workflow for durable prevention rules

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1