@skills · Owner

Agent skills by ulpi-io

60 skills indexed from github.com/ulpi-io. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• ast-grep · Skill · 4 stars

  Search code by SYNTAX SHAPE, not by text — matching structures grep and regex can't reliably express — with the `ast-grep` CLI: parse to an AST and match w

• branch-review-before-pr · Skill · 4 stars

  Gate a branch before it becomes a PR — catch the STRUCTURAL defects tests miss, not style: read the full diff against the default base, run a two-pass chec

• browse · Skill · 4 stars

  Drive a REAL browser and native apps the way a user would — not fetch raw HTML — through the persistent `browse` CLI: one long-lived headless Chromium (plu

• browse-aeo · Skill · 4 stars

  Score a page for how well AI answer engines can CITE it — Answer Engine Optimization, not classic rankings — by pulling structured data, meta, headings, an

• browse-config · Skill · 4 stars

  Generate camoufox configuration for the `browse` CLI by INTERVIEW, not hand-edited JSON — an AskUserQuestion-guided flow that turns a chosen preset (stealt

• browse-geo · Skill · 4 stars

  Track brand and domain VISIBILITY across AI search engines over a whole query set — Generative Engine Optimization monitoring, not a one-page audit — sweep

• browse-qa · Skill · 4 stars

  Turn a ticket, URL, or plain-language spec into an executed QA run AND reusable regression flows — scenarios and evidence, not ad-hoc clicking — by decompo

• browse-seo · Skill · 4 stars

  Run a full on-page technical SEO audit from a LIVE render — real rendered signals, not source guesses — extracting meta tags, heading hierarchy, structured

• browse-stealth · Skill · 4 stars

  Reach sites that BLOCK ordinary automation — the same navigate/inspect/interact/report loop as the `browse` skill, but on browse's camoufox runtime: a hard

• bugfix · Skill · 4 stars

  Fix a CONFIRMED bug at its root cause, smallest correct change only — reproduce before you touch code: write a failing reproducer, diagnose the first broke

• bugfix-crate · Skill · 4 stars

  Work a Rust crate's recorded issue file to green — one finding at a time, disciplined and sequential: for each finding, write the failing regression test f

• build-dmg · Skill · 4 stars

  Build a distributable macOS DMG from an Xcode project via the bundled local helper — archive → export → package into one signed artifact. Resolves the proj

• claude-review · Skill · 4 stars

  Get an INDEPENDENT second-opinion review from a separate Claude agent in a read-only worktree — findings only, never edits to your working copy. Reads the

• code-simplify · Skill · 4 stars

  Reduce a change's complexity WITHOUT altering behavior — lower cognitive load, not line count: read the target plus its callers and tests, take a baseline

• codemap · Skill · 4 stars

  Discover code by MEANING and DEPENDENCY structure, not by matching text — with the `codemap` CLI: hybrid vector+BM25 semantic search, symbol lookup, incomi

• codex-review · Skill · 4 stars

  Get an INDEPENDENT second opinion from the OpenAI Codex CLI — a separate reviewer runtime run over the real diff, not Claude reviewing its own work. Verifi

• commit · Skill · 4 stars

  Create one or more intentional git commits from the working tree — grounded in the REAL diff, never a guessed message over blind staging. Reads `git diff H

• cost-estimate · Skill · 4 stars

  Estimate what a codebase, branch diff, or single commit would COST to build — evidence-driven, not a guess: measure the real scope with the helper scripts

• create-pr · Skill · 4 stars

  Open a GitHub pull request that matches what the branch ACTUALLY changed — validated against the real base, not the branch name or an optimistic summary. R

• create-tests-extract · Skill · 4 stars

  Move a bulky inline test block out of its source file WITHOUT weakening it — same coverage, same private access: read the source and its inline tests, pick

• docker · Skill · 4 stars

  Write and change container infrastructure the way THIS project already builds and ships it, not by generic defaults — a Docker reference carrying the real

• find-agents · Skill · 4 stars

  Discover, install, and manage AI agents across 43+ coding CLIs and IDEs from ONE source — auto-translated to each client's native format, not hand-ported —

• find-bugs · Skill · 4 stars

  Hunt REAL bugs and security holes in the current branch diff — verified, not a raw model dump: map each changed file's attack and defect surface, run the s

• frontend-design-ui-ux · Skill · 4 stars

  Produce a distinctive, LOCKED design language plus an implementation-ready UX/UI spec, written to `.ulpi/design/`: a per-brief visual identity (palette, ty

• git-merge-expert · Skill · 4 stars

  Run a git merge, PR merge, conflict resolution, or rollback safely — readiness-checked and BACKED UP before anything touches shared history. Assesses branc

• git-merge-expert-worktree · Skill · 4 stars

  Run merges and conflict resolution inside a dedicated git worktree so the MAIN tree is never touched — isolation is the whole point. Lists existing worktre

• go-live-audit · Skill · 4 stars

  Author and run a project-TAILORED pre-launch audit as a bounded multi-agent workflow — a real launch verdict, not a checklist skim: fill the bundled workfl

• hand-over-to-kiro · Skill · 4 stars

  Delegate an implementation task to the Kiro CLI and report exactly what it changed — verified against a git baseline, never on kiro's SELF-REPORT. Gathers

• kiro-review · Skill · 4 stars

  Get an INDEPENDENT second opinion from the Kiro CLI run strictly READ-ONLY — a separate reviewer runtime over the real diff, with no write access to the re

• laravel · Skill · 4 stars

  Write and change Laravel the way THIS project already does it, with Laravel 13 as the recommended baseline for new applications and explicit compatibility

• laravel-filament · Skill · 4 stars

  Build Filament admin panels on the v5 API surface THIS project targets, not deprecated v3 patterns — a reference carrying the current namespaces and conven

• launch-analytics · Skill · 4 stars

  Instrument a launch so the traffic spike is ATTRIBUTABLE, not a vanity number — one consistent UTM scheme on every launch link, the conversion funnel (visi

• launch-copy · Skill · 4 stars

  Draft the copy a launch needs, in multiple angles, all bound to the REAL product — never generic placeholders. Produces taglines/headlines, one-liners, sho

• launch-hacker-news · Skill · 4 stars

  Prepare and run a Hacker News "Show HN" launch end to end — HN is STRICTER than every other channel: it **forbids all vote mobilization** (no supporter wav

• launch-linkedin · Skill · 4 stars

  Prepare and run a product/company launch on LinkedIn end to end — the launch link goes in the FIRST COMMENT, not the post body, and you never edit the post

• launch-outreach · Skill · 4 stars

  Build and notify a launch's supporter audience with paste-ready, platform-COMPLIANT outreach — the messages you send to PEOPLE, never the on-listing copy.

• launch-product-hunt · Skill · 4 stars

  Prepare and run a Product Hunt launch end to end — COMPLIANT promotion ONLY: never vote manipulation, rings, bought/incentivized votes, or "please upvote".

• launch-x · Skill · 4 stars

  Prepare and run a product launch on X (formerly Twitter) end to end — the external link goes in a REPLY, not the main tweet, so reach isn't penalized. Grou

• lokei · Skill · 4 stars

  Put local dev surfaces behind trusted HTTPS `.test` domains — real certs and DNS, not localhost:port — with the `lokei` CLI: framework-aware `run`, public

• map-project · Skill · 4 stars

  Refresh a SINGLE app's durable AI context — a thin `CLAUDE.md` router over discovered reference docs so future sessions start knowing the repo without payi

• map-project-monorepo · Skill · 4 stars

  Refresh a Cargo WORKSPACE or package monorepo's durable AI context — a self-contained `CLAUDE.md` per member that Claude lazy-loads, plus a thin project-wi

• nestjs · Skill · 4 stars

  Build NestJS the way THIS project's module architecture already does it, not by framework defaults — a reference carrying the real module boundaries and de

• nextjs · Skill · 4 stars

  Build or review a Next.js App Router surface against the project's installed framework version and established architecture. Covers pages, layouts, async r

• nodejs · Skill · 4 stars

  Write Node.js and Bun backend code the way THIS project already does it, not by generic defaults — a TypeScript-first reference that detects the runtime an

• normalize-agent-for-claude · Skill · 4 stars

  Convert a local AGENT.md into a Claude Code optimized agent — an AUDIT-then-rewrite that ties every change to real Claude agent-runtime behavior, not taste

• normalize-skill-for-claude · Skill · 4 stars

  Convert a local skill into a Claude Code optimized shape — an AUDIT-then-rewrite that ties every change to real Claude skill-runtime behavior, treating FRO

• plan-founder-review · Skill · 4 stars

  Gate an implementation plan BEFORE agents execute it — catch phantom paths and false reuse, not typos: read the full plan markdown and its companion JSON,

• plan-to-task-list-with-dag · Skill · 4 stars

  Turn a request into a SCHEDULABLE task DAG — atomic tasks with real dependencies, not planning prose: challenge scope and pick a planning mode with the use

• pr-retro · Skill · 4 stars

  Read a feature branch's merge-readiness from its actual git data — measured metrics, not vibes: collect raw git output for the branch vs base, compute bran

• review-crate · Skill · 4 stars

  Deep-audit ONE Rust crate end to end — read every file, don't sample: enumerate and read the whole crate, run its `cargo test`, check the existing `.ulpi/i

• run-parallel-agents-feature-build · Skill · 4 stars

  Run 3+ genuinely INDEPENDENT build tasks concurrently on Claude Code's real parallel agent runtime — throughput without file conflicts or fake orchestratio

• run-parallel-agents-feature-debug · Skill · 4 stars

  Diagnose and fix 3+ genuinely INDEPENDENT failures concurrently on Claude Code's real parallel agent runtime — without splitting one root cause into confli

• rust · Skill · 4 stars

  Write and change Rust the way THIS workspace already does it, NOT by generic defaults — a systems-programming reference carrying the real crate boundaries,

• secrets · Skill · 4 stars

  Manage local service credentials WITHOUT ever exposing their values — the `secrets` CLI adds, rotates, lists, enables, disables, and inspects encrypted int

• ship-playbook · Skill · 4 stars

  Take one feature request from prompt to reviewed, audited delivery in a SINGLE autonomous pass — one runnable Workflow that plans, reviews the plan, builds

• skills · Collection · 4 stars
• start · Skill · 4 stars

  Route the start of substantive work to the right execution path — a lightweight INTERNAL intake pass, not a user-facing command and not a universal constit

• update-agent-learnings · Skill · 4 stars

  Propagate ONE validated learning from this session into durable AGENT guidance — extract the smallest useful rule, classify its scope (Global / Claude Code

• update-claude-learnings · Skill · 4 stars

  Propagate ONE validated learning about Claude Code behavior from this session into the project's CLAUDE.md — the MAIN-AGENT memory Claude loads every sessi

• update-skill-learnings · Skill · 4 stars

  Propagate ONE validated learning about SKILL design or quality from this session into the central skill-learnings file — extract the smallest useful patter

Browse the @skills marketplace