Source

ycs77/skills

37 skills · 579 combined installs

Skills from this source

#
Skill
Source
8W Activity
Installs
1
commit-message Generates concise, intent-driven Git commit messages in imperative mood. Use when the user asks to create, write, dra…
ycs77/skills
52
2
github-release-notes Generate GitHub release notes for the upcoming version, following the Keep a Changelog 1.1.0 spec.
ycs77/skills
28
3
shadcn-vue Component usage patterns for shadcn-vue — a Vue component distribution system built on Reka UI and Tailwind CSS. Cove…
ycs77/skills
28
4
ycs77-vue This skill should be used when applying project-specific opinionated Vue 3 conventions. It covers SFC block order (te…
ycs77/skills
28
5
write-social-post 撰寫像在通訊群組跟同溫層分享一個發現的社群貼文——把文章、趨勢、開源專案、技術工具寫成有觀點、有判斷、口語自然的分享文…
ycs77/skills
25
6
grill-me A relentless interview to sharpen a plan or design.
ycs77/skills
18
7
grill-with-docs A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
ycs77/skills
18
8
handoff Compact the current conversation into a handoff document for another agent to pick up.
ycs77/skills
18
9
improve-codebase-architecture Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one y…
ycs77/skills
18
10
prototype Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state mode…
ycs77/skills
18
11
scan-repo GitHub 開源專案安?
ycs77/skills
18
12
scan-skill 當使用者想審查 AI Agent skill 目錄的安全風險時使用,例如「掃描 skill」、「安全審查」、「檢查技能安全性」、「scan skil…
ycs77/skills
18
13
tdd Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refact…
ycs77/skills
18
14
ask-matt Ask which skill or flow fits your situation. A router over the skills in this repo.
ycs77/skills
14
15
code-review Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code…
ycs77/skills
14
16
codebase-design Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find…
ycs77/skills
14
17
diagnosing-bugs Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports …
ycs77/skills
14
18
domain-modeling Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous la…
ycs77/skills
14
19
grilling Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, o…
ycs77/skills
14
20
implement Implement a piece of work based on a spec or set of tickets.
ycs77/skills
14
21
research Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Us…
ycs77/skills
14
22
setup-matt-pocock-skills Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc la…
ycs77/skills
14
23
teach Teach the user a new skill or concept, within this workspace.
ycs77/skills
14
24
to-spec Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis …
ycs77/skills
14
25
to-tickets Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edge…
ycs77/skills
14
26
triage Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write…
ycs77/skills
14
27
wayfinder Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue …
ycs77/skills
14
28
to-questionnaire Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
ycs77/skills
13
29
wait-what Stop. That last message did not land — re-pitch it.
ycs77/skills
13
30
wizard Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning inf…
ycs77/skills
13
31
writing-for-agents Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
ycs77/skills
13
32
caveman Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keepi…
ycs77/skills
5
33
diagnose Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument…
ycs77/skills
5
34
write-a-skill Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to …
ycs77/skills
5
35
zoom-out Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a …
ycs77/skills
5
36
write
ycs77/skills
4
37
writing-great-skills Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
ycs77/skills
2