zszz3

33 mods across 2 repositories, 605 stars between them.

aihot

01

zszz3/AgentRecall

Skill Codex

A Chinese-language information service for current AI news, selected stories, hot topics, daily reports, and papers. It retrieves fresh results from AIHOT’s public read-only API rather than relying on remembered information.

not rated 594 +4 today A 110 tokens copy · 94% MIT

brainstorming

02

zszz3/AgentRecall

Skill Claude CodeCodex

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

not rated 594 +4 changed 1mo ago A 37 tokens copy · 94% MIT

dsh-code-review

03

zszz3/AgentRecall

Skill Claude CodeCodex

Review a branch or pull request for correctness, lifecycle, security, compatibility, and missing behavior using the target repository's own instructions and live base/head rather than DeepSeek Harness-specific commands.

not rated 594 +4 today A SkillSpector: pass 42 tokens original MIT

zszz3/AgentRecall

Skill Claude CodeCodex

Find evidence-backed opportunities to remove dead, duplicated, speculative, over-built, or hand-rolled code without treating complexity, tests, or unused-looking symbols as proof by themselves.

not rated 594 +4 today A SkillSpector: pass 42 tokens original MIT

dsh-prose-standard

05

zszz3/AgentRecall

Skill Claude CodeCodex

Write, review, or trim technical prose in Markdown, JSDoc, comments, prompts, diagnostics, and visible strings while preserving complete contracts and removing repetition or authoring-session narration.

not rated 594 +4 today A SkillSpector: pass 43 tokens original MIT

zszz3/AgentRecall

Skill Claude CodeCodex

Audit or rewrite repository prose that exposes authoring-session reasoning, review history, dead draft references, change narration, or unsupported planning residue while preserving every durable technical fact.

not rated 594 +4 today A SkillSpector: pass 43 tokens original MIT

grill-me

07

zszz3/AgentRecall

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on a design, or says "grill me".

not rated 594 +4 today A SkillSpector: warn 50 tokens original MIT

one-bite-teaching

08

zszz3/AgentRecall

Skill Claude CodeCodex

First dig out what actually matters in a project or system from real sources, then teach it one small point at a time, pausing for confirmation after each. Use when the user wants to genuinely understand a codebase/system (not get a summary), is preparing to explain their own work (e.g. interview prep on a resume)…

not rated 594 +4 today A SkillSpector: pass 106 tokens original MIT

resume-optimization

09

zszz3/AgentRecall

Skill Claude Code

Resume structure, achievement bullet formulas, ATS optimization, and job-targeted tailoring for software engineers. Use when reviewing resumes, crafting achievement bullets, extracting keywords from job descriptions, or tailoring content for specific roles.

not rated 594 +4 today A SkillSpector: warn 45 tokens original MIT

zszz3/AgentRecall

Skill Claude CodeCodex

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

not rated 594 +4 today A 21 tokens copy · 97% MIT

zszz3/AgentRecall

Skill Claude CodeCodex

Use when implementing any feature, bug fix, refactor, or behavior change. Write a failing behavioral test first, verify the failure, then write the minimum production code needed to pass.

not rated 594 +4 today B SkillSpector: warn 41 tokens original MIT

zszz3/AgentRecall

Skill Claude CodeCodex

Use immediately before claiming work is complete, fixed, passing, or ready to merge. Requires fresh verification evidence for every success claim.

not rated 594 +4 today A SkillSpector: pass 31 tokens original MIT

zszz3/AgentRecall

Skill Claude CodeCodex

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

not rated 594 +4 today A 51 tokens copy · 83% MIT

frontend-design

14

zszz3/AgentRecall

Skill Claude CodeCodex

Use when building or substantially reshaping a user interface, page, website, dashboard, or interactive frontend.

not rated 594 +4 today A SkillSpector: pass 24 tokens original MIT

handoff

15

zszz3/AgentRecall

Skill Claude CodeCodex

Use when pausing a long task, changing sessions or runtimes, or preparing another agent to continue unfinished work.

not rated 594 +4 today A SkillSpector: pass 26 tokens original MIT

paper-writing

16

zszz3/AgentRecall

Skill Claude CodeCodex

A writing assistant for academic papers and related documents, such as theses, conference papers, literature reviews, and research plans. It helps shape the question, structure the argument, organize evidence, and revise the text.

not rated 594 +4 today A SkillSpector: pass 20 tokens original MIT

zszz3/AgentRecall

Skill Claude CodeCodex

A personal finance planning guide that organizes income, spending, debt, savings, risks, and future goals. It provides educational planning, not licensed financial, tax, legal, or investment advice.

not rated 594 +4 today A SkillSpector: pass 20 tokens original MIT

zszz3/AgentRecall

Skill Claude Code

A skill that specializes in conducting thorough code reviews. Provide task description, MR summary, and diff command (DO NOT provide specific code changes. Provide command to get diffs like 'git add . && git diff HEAD --relative -- ".go" ".yaml"') to begin review.

not rated 594 +4 today A SkillSpector: pass 63 tokens original MIT

skill-creator

19

zszz3/AgentRecall

Skill Claude CodeCodex

Use when creating, packaging, reviewing, or improving an Agent Skill for Codex, Claude, Trae, or another SKILL.md-compatible runtime.

not rated 594 +4 today C 34 tokens original MIT

feishu-tech-diagram

20

zszz3/AgentRecall

Skill Codex needs its repo

Use when a Lark/Feishu technical document needs an editable architecture diagram, flowchart, sequence diagram, state model, data relationship, Agent workflow, development process, reliability view, learning map, roadmap, or decision visualization.

not rated 594 +4 today A SkillSpector: pass 52 tokens original MIT

zszz3/AgentRecall

Skill Codex

Use when drafting, restructuring, or reviewing a Chinese technical tutorial whose concept order is hard to follow, code lacks context, diagrams are missing or misplaced, implementation scopes are mixed, facts are version-sensitive, or prose sounds machine-generated.

not rated 594 +4 today A SkillSpector: pass 52 tokens original MIT

brainstorming

22

zszz3/multi-agent-chat

Skill Claude CodeCodex

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

not rated 11 3mo ago A 37 tokens

zszz3/multi-agent-chat

Skill Claude CodeCodex

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

not rated 11 3mo ago A 51 tokens

frontend-design

24

zszz3/multi-agent-chat

Skill Claude CodeCodex

Use when building or substantially reshaping a user interface, page, website, dashboard, or interactive frontend.

not rated 11 3mo ago A 24 tokens

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: