ulpi-io/skills

5673

frontend-design-ui-ux Produce a distinctive, LOCKED design language plus an implementation-ready UX/UI spec, written to `.ulpi/design/`: a …

ulpi-io/skills

2.3K

2

laravel-filament Build Filament admin panels on the v5 API surface THIS project targets, not deprecated v3 patterns — a reference carr…

ulpi-io/skills

406

3

cost-estimate Estimate what a codebase, branch diff, or single commit would COST to build — evidence-driven, not a every source lin…

ulpi-io/skills

289

4

browse Drive a REAL browser and native apps the way a user would — not fetch raw HTML — through the persistent `browse` CLI:…

ulpi-io/skills

261

5

git-merge-expert Run a git merge, PR merge, conflict resolution, or rollback safely — readiness-checked and BACKED UP before anything …

ulpi-io/skills

169

6

code-simplify Reduce a change's complexity WITHOUT altering behavior — lower cognitive load, not line count: read the target plus i…

ulpi-io/skills

168

7

map-project Refresh a SINGLE app's durable AI context — a thin `CLAUDE.md` router over discovered reference docs so future sessio…

ulpi-io/skills

166

8

bugfix Fix a CONFIRMED bug at its root cause, smallest correct change only — reproduce before you touch code: write a failin…

ulpi-io/skills

164

9

nextjs Build or review a Next.js App Router surface against the project's installed framework version and established archit…

ulpi-io/skills

162

10

plan-founder-review Gate an implementation plan BEFORE agents execute it — catch phantom paths and false reuse, not typos: read the full …

ulpi-io/skills

161

11

find-bugs Hunt REAL bugs and security holes in the current branch diff — verified, not a raw model dump: map each changed file'…

ulpi-io/skills

159

12

plan-to-task-list-with-dag Turn a request into a SCHEDULABLE task DAG — atomic tasks with real dependencies, not planning prose: challenge scope…

ulpi-io/skills

158

13

branch-review-before-pr Gate a branch before it becomes a PR — catch the STRUCTURAL defects tests miss, not style: read the full diff against…

ulpi-io/skills

155

14

update-claude-learnings Propagate ONE validated learning about Claude Code behavior from this session into the project's CLAUDE.md — the MAIN…

ulpi-io/skills

155

15

codemap Discover code by MEANING and DEPENDENCY structure, not by matching text — with the `codemap` CLI: hybrid vector+BM25 …

ulpi-io/skills

154

16

map-project-monorepo Refresh a Cargo WORKSPACE or package monorepo's durable AI context — a self-contained `CLAUDE.md` per member that Cla…

ulpi-io/skills

153

17

update-agent-learnings Propagate ONE validated learning from this session into durable AGENT guidance — extract the smallest useful rule, cl…

ulpi-io/skills

153

18

commit Create one or more intentional git commits from the working tree — grounded in the REAL diff, never a guessed message…

ulpi-io/skills

151

19

git-merge-expert-worktree Run merges and conflict resolution inside a dedicated git worktree so the MAIN tree is never touched — isolation is t…

ulpi-io/skills

151

20

create-pr Open a GitHub pull request that matches what the branch ACTUALLY changed — validated against the real base, not the b…

ulpi-io/skills

148

21

update-skill-learnings Propagate ONE validated learning about SKILL design or quality from this session into the central skill-learnings fil…

ulpi-io/skills

148

22

nodejs Write Node.js and Bun backend code the way THIS project already does it, not by generic defaults — a TypeScript-first…

ulpi-io/skills

146

23

start Route the start of substantive work to the right execution path — a lightweight INTERNAL intake pass, not a user-faci…

ulpi-io/skills

144

24

pr-retro Read a feature branch's merge-readiness from its actual git data — measured metrics, not vibes: collect raw git outpu…

ulpi-io/skills

142

25

kiro-review Get an INDEPENDENT second opinion from the Kiro CLI run strictly READ-ONLY — a separate reviewer runtime over the rea…

ulpi-io/skills

141

26

claude-review Get an INDEPENDENT second-opinion review from a separate Claude agent in a read-only worktree — findings only, never …

ulpi-io/skills

140

27

run-parallel-agents-feature-debug Diagnose and fix 3+ genuinely INDEPENDENT failures concurrently on Claude Code's real parallel agent runtime — withou…

ulpi-io/skills

140

28

secrets Manage local service credentials WITHOUT ever exposing their values — the `secrets` CLI adds, rotates, lists, enables…

ulpi-io/skills

140

29

find-agents Discover, install, and manage AI agents across 43+ coding CLIs and IDEs from ONE source — auto-translated to each cli…

ulpi-io/skills

139

30

ast-grep Search code by SYNTAX SHAPE, not by text — matching structures grep and regex can't reliably express — with the `ast-…

ulpi-io/skills

138

31

browse-qa Turn a ticket, URL, or plain-language spec into an executed QA run AND reusable regression flows — scenarios and evid…

ulpi-io/skills

137

32

run-parallel-agents-feature-build Run 3+ genuinely INDEPENDENT build tasks concurrently on Claude Code's real parallel agent runtime — throughput witho…

ulpi-io/skills

137

33

laravel Write and change Laravel the way THIS project already does it, with Laravel 13 as the recommended baseline for new ap…

ulpi-io/skills

134

34

codex-review Get an INDEPENDENT second opinion from the OpenAI Codex CLI — a separate reviewer runtime run over the real diff, not…

ulpi-io/skills

133

35

build-dmg Build a distributable macOS DMG from an Xcode project via the bundled local helper — archive → export → package into …

ulpi-io/skills

127

36

update-claude-settings Generate or update Claude Code settings from the project's REAL stack, not a generic allowlist — `.claude/settings.lo…

ulpi-io/skills

127

37

lokei Put local dev surfaces behind trusted HTTPS `.test` domains — real certs and DNS, not `docker up` and `.test.yaml` mu…

ulpi-io/skills

124

38

rust Write and change Rust the way THIS workspace already does it, NOT by generic defaults — a systems-programming referen…

ulpi-io/skills

124

39

nestjs Build NestJS the way THIS project's module architecture already does it, not by framework defaults — a reference carr…

ulpi-io/skills

116

40

browse-stealth Reach sites that BLOCK ordinary automation — the same navigate/inspect/interact/report loop as the `browse` skill, bu…

ulpi-io/skills

114

41

docker Write and change container infrastructure the way THIS project already builds and ships it, not by generic defaults —…

ulpi-io/skills

111

42

normalize-skill-for-claude Convert a local skill into a Claude Code optimized shape — an AUDIT-then-rewrite that ties every change to real Claud…

ulpi-io/skills

111

43

normalize-agent-for-claude Convert a local AGENT.md into a Claude Code optimized agent — an AUDIT-then-rewrite that ties every change to real Cl…

ulpi-io/skills

110

44

bugfix-crate Work a Rust crate's recorded issue file to green — one finding at a time, disciplined and sequential: for each findin…

ulpi-io/skills

109

45

review-crate Deep-audit ONE Rust crate end to end — read every file, don't sample: enumerate and read the whole crate, run its `ca…

ulpi-io/skills

108

46

create-tests-extract Move a bulky inline test block out of its source file WITHOUT weakening it — same coverage, same private access: read…

ulpi-io/skills

106

47

browse-geo Track brand and domain VISIBILITY across AI search engines over a whole query set — Generative Engine Optimization mo…

ulpi-io/skills

101

48

browse-seo Run a full on-page technical SEO audit from a LIVE render — real rendered signals, not source guesses — extracting me…

ulpi-io/skills

100

49

browse-aeo Score a page for how well AI answer engines can CITE it — Answer Engine Optimization, not classic rankings — by pulli…

ulpi-io/skills

99

50

browse-config Generate camoufox configuration for the `browse` CLI by INTERVIEW, not hand-edited JSON — an AskUserQuestion-guided f…

ulpi-io/skills

98