7xuanlu

25 mods in 4 plugins, 3 repositories, 90 stars between them.

eval-skew-reviewer

02

7xuanlu/wenlan

Agent Claude Code

Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND the seed liveness contract, so it can't ship "merged-but-inert". Use after changes touching ingest enrichment, a new…

not rated 79 5d ago A 90 tokens copy · 100% Apache-2.0

7xuanlu/wenlan

Agent Claude Code

Reviews Rust async code for tokio + libsql + axum concurrency hazards. Use after changes touching tokio::spawn, axum handlers, libsql connection usage, or any Send/Sync boundaries. Read-only — produces findings, does not edit.

not rated 79 5d ago A 59 tokens copy · 100% Apache-2.0

prove

04

7xuanlu/wenlan

Skill Claude Code

Per-surface verification loops for wenlan — daemon, cli, mcp, plugin, suite strength (mutation), behavior trace, weekly sweep. Routes to scripts; every check records evidence via attest. Deeper than the built-in verify skill — use prove for mutation audits, behavior tracing, and the weekly sweep; built-in /verify…

not rated 79 changed 1mo ago A SkillSpector: pass 74 tokens copy · 88% Apache-2.0

run-wenlan-app

05

7xuanlu/wenlan

Skill Claude Code

Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.

not rated 79 changed 1mo ago A SkillSpector: pass 71 tokens original Apache-2.0

run-wenlan

06

7xuanlu/wenlan

Skill Claude Code needs its repo

Build, launch, and stop the wenlan daemon (wenlan-server) for local dev and verification. Use when asked to run or restart the daemon, or before driving any surface (HTTP, CLI, MCP) against a live instance.

not rated 79 changed 1mo ago C 53 tokens original Apache-2.0

verify

07

7xuanlu/wenlan

Skill Claude Code

Drive/evidence recipe for verifying wenlan changes at their real surfaces (daemon HTTP, CLI, MCP stdio). The handle file the built-in verify protocol expects; launch primitives live in the run-wenlan skill, deeper machinery (mutation audit, behavior trace, weekly sweep) in the prove skill.

not rated 79 changed 1mo ago A SkillSpector: warn 63 tokens original Apache-2.0

wenlan

08

7xuanlu/wenlan

MCP server Claude CodeCodexCursor +2

MCP server "wenlan" as configured in 7xuanlu/wenlan. Launched with ./bin/wenlan-mcp-runner.sh.

not rated 79 5d ago A tokens not measured copy · 100% Apache-2.0

brief

09

7xuanlu/wenlan

Skill Claude CodeCodex

Read the current Space-owned project Brief from Wenlan for Codex. With an optional topic, appends separately labeled related context from the same Space. Invoked as /brief [topic] when resuming work or asking to catch up.

not rated 79 5d ago B SkillSpector: warn 50 tokens copy · 91% Apache-2.0

capture

10

7xuanlu/wenlan

Skill Claude CodeCodex

Save a durable memory to Wenlan from Codex. Use proactively when the user states a preference, makes a decision, corrects you, or shares a durable fact. Invoked as /capture .

not rated 79 5d ago B SkillSpector: warn 44 tokens copy · 92% Apache-2.0

curate

11

7xuanlu/wenlan

Skill Claude CodeCodex

Review pending Wenlan captures, revisions, or daemon refinements from Codex. Use for explicit audit walks after /brief or /handoff surfaces pending work. Invoked as /curate captures, /curate revisions, or /curate refinements.

not rated 79 5d ago A SkillSpector: pass 55 tokens copy · 97% Apache-2.0

distill

12

7xuanlu/wenlan

Skill Claude CodeCodex

Synthesize or refresh source-backed Wenlan pages from Codex. Invoked as /distill [target], /distill deep, or /distill rebuild .

not rated 79 5d ago B SkillSpector: warn 39 tokens copy · 89% Apache-2.0

forget

13

7xuanlu/wenlan

Skill Claude CodeCodex

Delete a Wenlan memory by exact id from Codex. Destructive and confirmation gated. Invoked as /forget .

not rated 79 5d ago A SkillSpector: pass 29 tokens copy · 89% Apache-2.0

handoff

14

7xuanlu/wenlan

Skill Claude CodeCodex

End a Codex work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /handoff.

not rated 79 5d ago B SkillSpector: warn 41 tokens copy · 94% Apache-2.0

help

15

7xuanlu/wenlan

Skill Claude CodeCodex

Show a one-screen Codex reference for the Wenlan plugin. Use when the user asks for Wenlan help, command list, invokes /help, or explicitly asks about import progress.

not rated 79 5d ago A SkillSpector: pass 39 tokens original Apache-2.0

lint

16

7xuanlu/wenlan

Skill Claude CodeCodex

Lint Wenlan memory quality and hygiene, check vocabulary, or resolve every finding into a ready repair, review item, system action, or blocker.

not rated 79 5d ago B 31 tokens copy · 92% Apache-2.0

pages

17

7xuanlu/wenlan

Skill Claude CodeCodex

List or open distilled Wenlan pages from Codex by delegating to the local wenlan pages CLI. Invoked as /pages [query].

not rated 79 5d ago A SkillSpector: pass 33 tokens copy · 100% Apache-2.0

recall

18

7xuanlu/wenlan

Skill Claude CodeCodex

Search Wenlan's local memory from Codex by query. Targeted lookup, not session orientation. Invoked as /recall .

not rated 79 5d ago B SkillSpector: warn 32 tokens copy · 86% Apache-2.0

setup

19

7xuanlu/wenlan

Skill Claude CodeCodex

Frictionless Wenlan setup for Codex. Detects a missing local runtime, installs or repairs it, and verifies the plugin to MCP to local runtime round-trip. Run when the user says "set up wenlan", "is wenlan working", or "fix wenlan".

not rated 79 changed 11d ago C 59 tokens original Apache-2.0

ultrapowers

20

7xuanlu/ultrapowers

Plugin Claude Code

Bundles 1 skill, 1 agent, 2 hooks · 105 tokens together

A dynamic build workflow for Claude Code: hand it a goal and it plans the work into tasks, builds each one test-first, reviews every step, and (with --thorough) loops a critic that adds tasks until nothing's left to fix, then hands back a branch ready for your review. Built on and complements superpowers by Jesse…

not rated 10 3mo ago A tokens not measured copy · 88% MIT

boule

21

7xuanlu/boule

Plugin Claude Code

Bundles 4 skills, 2 agents · 136 tokens together

Lean, research-backed multi-LLM council with debiased judging (position-swap, verbosity-norm, stake-free judge).

not rated 1 1mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: