ashe-li

24 mods across 1 repository, 2 stars between them.

agents

01

ashe-li/agent-skills

Skill Claude CodeCodex

An index of agent definitions in a repository, including guides for triage, document review, document updates, and test-driven development (TDD), a practice of writing tests before implementation.

2 4d ago A 75 tokens

complexity-triage

02

ashe-li/agent-skills

Agent

A task-sizing step that labels work as small, medium, or needing multiple sessions before detailed planning begins.

2 4d ago A 80 tokens

doc-reviewer

03

ashe-li/agent-skills

Agent

A document and plan review agent that checks whether requirements are covered, the work is practical, supported by industry or community evidence, and safe.

2 4d ago A 100 tokens

doc-updater

04

ashe-li/agent-skills

Agent

A documentation-updating agent that scans recent code changes, or a specified range of changes, and updates affected files such as README files, documentation, and code maps. It returns a change manifest for review.

2 4d ago A 81 tokens

tdd-guide

05

ashe-li/agent-skills

Agent

A guide to test-driven development, or TDD: writing a test that fails, adding code to make it pass, and then improving the code. It is intended to be used before new features or bug fixes and includes an 80% code-coverage threshold.

2 4d ago A 71 tokens

curation

06

ashe-li/agent-skills

Skill Claude CodeCodex

A retrospective cleanup process for previously learned skills.

2 4d ago A 56 tokens

design

07

ashe-li/agent-skills

Skill Claude CodeCodex

A development-planning skill that inventories available resources and uses a planning agent to create a detailed implementation plan as a Markdown file in plans/active/.

2 4d ago A 50 tokens

evidence-check

08

ashe-li/agent-skills

Skill Claude CodeCodex

An independent process for checking evidence behind a technical decision or practice across research, industry standards, best practices, and community opinions, including opposing views.

2 4d ago A 101 tokens

evidence-gate

09

ashe-li/agent-skills

Skill Claude CodeCodex

A fact-checking gate for reports produced by coding workflows such as pull-request and security reviews.

2 4d ago A 134 tokens

figma-verify

10

ashe-li/agent-skills

Skill Claude CodeCodex

A visual checking process for comparing Figma designs with local web implementations. Figma is a tool for creating interface designs, while a screenshot diff compares images to find visual changes.

2 4d ago A 179 tokens

handoff

11

ashe-li/agent-skills

Skill Claude CodeCodex

A skill that creates a self-contained handoff prompt summarizing a conversation’s goal, progress, decisions, and unfinished work.

2 4d ago A 53 tokens

learn-eval-deep

12

ashe-li/agent-skills

Skill Claude CodeCodex

A quality-checking skill for evaluating one learned skill with three tests: structure, when it activates, and what happens when parts are removed.

2 4d ago B 77 tokens

notion-plan

13

ashe-li/agent-skills

Skill Claude CodeCodex

A workflow that reads requirements from a Notion page and connects them to a design implementation plan. Notion is a collaborative app for storing documents and project information.

2 4d ago A 29 tokens

plan-archive

14

ashe-li/agent-skills

Skill Claude CodeCodex

A procedure for moving completed plans from an active folder to a completed folder, while recording verification results and the completion time.

2 4d ago A 45 tokens

plan-run

15

ashe-li/agent-skills

Skill Claude CodeCodex

A Python state machine that follows the dependency graph in a plan.md file. A dependency graph shows which tasks must be completed before others can start.

2 4d ago A 87 tokens

ashe-li/agent-skills

Skill Claude CodeCodex

A skill for operating web browsers with Playwright while keeping a person involved. It can pause before important actions that need human approval.

2 4d ago A 62 tokens

pr-evidence-comment

17

ashe-li/agent-skills

Skill Claude CodeCodex

A pull-request acceptance workflow that checks a preview, captures screenshots, visually reviews them, and posts pass-or-fail evidence as a comment.

2 4d ago A 248 tokens

pr

18

ashe-li/agent-skills

Skill Claude CodeCodex

A workflow for finishing repository work and opening or updating a pull request. A pull request is a proposed code change that others can review before it is merged.

2 4d ago A 39 tokens

ship-ticket

19

ashe-li/agent-skills

Skill Claude CodeCodex

An automated workflow that takes one or more Notion work-ticket links and works each ticket in its own code workspace. It checks how to reproduce the problem, investigates the cause, applies a fix, opens a pull request, and reports the results.

2 4d ago A 102 tokens

triage

20

ashe-li/agent-skills

Skill Claude CodeCodex

A skill for managing learned skills, including deciding which ones to retire, restore, or query. It uses results from removal experiments and a four-part analysis from skills-ecosystem-eval.

2 4d ago C 43 tokens

update

21

ashe-li/agent-skills

Skill Claude CodeCodex

A knowledge-base update workflow described in Chinese. It runs document updates, reviews, context organisation, and pattern extraction in sequence so changes from a work session can be recorded.

2 4d ago A 45 tokens

ashe-li/agent-skills

Skill Claude CodeCodex

An iterative skill for checking technical claims through several kinds of evidence, including academic research, industry standards, best practices, and community criticism. It uses repeated review rounds and two independent reviewers to reach a verdict.

2 4d ago A 113 tokens

verify-fix-loop

23

ashe-li/agent-skills

Skill Claude CodeCodex

A browser-testing workflow that repeatedly checks a web page, fixes failures, and checks it again using Playwright. Playwright is a tool for controlling a real browser in automated tests.

2 4d ago A 120 tokens

worktree

24

ashe-li/agent-skills

Skill Claude CodeCodex

A skill for managing Git worktrees throughout their lifecycle. A worktree is a separate working folder connected to the same Git repository.

2 4d ago A 34 tokens