Not in the top 1,000 by GitHub stars
scarletkc/agents
Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/antigravity-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/ask-to-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/codex-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/devin-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/grok-cli/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/marketing-copy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/product-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/scoped-change/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/talk-like-scarletkc/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/ux-writing/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Instructions only → After Network or broad shell
3be29ae86c2e → 8e149b335e96
- 3 description: "Judgment rules for user-facing text and docs: CLI and diagnostic output, error and help text, README and docs structure, code comments, titles, and generated reports, decks, or exports. Use when writing or changing any user-visible string, when adding or restructuring docs or deciding which page owns a fact, when a page is about to record a version, a deployment state, or a value the code already owns, when a comment, title, or artifact could carry the reasoning or an abandoned option behind the change, when a behavior change needs its copy sites swept, or when reviewing a diff that touches copy or docs."
+ 3 description: "Judgment for text read by someone who wasn't there when it was written: user-facing output, error and help text, docs, comments, and generated deliverables. Use when that text is the substance of the work or under review."
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/worktree-pr/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
skills/x-content/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
3be29ae86c2e → 8e149b335e96
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 3be29ae86c2e
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 8e149b335e963954e9c4bafba00eedbd7de060ed
git clone --filter=blob:none --no-checkout https://github.com/scarletkc/agents.git .hotskills/scarletkc-agents && git -C .hotskills/scarletkc-agents checkout --detach 8e149b335e963954e9c4bafba00eedbd7de060ed
# Copy each selected skill directory from .hotskills/scarletkc-agents into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/scarletkc/agents.git .hotskills/scarletkc-agents && git -C .hotskills/scarletkc-agents checkout --detach 8e149b335e963954e9c4bafba00eedbd7de060ed
# Copy each selected skill directory from .hotskills/scarletkc-agents into .agents/skills/<skill-name>/227GitHub stars
0stars in 7 days
12skills in this repository
3commits in 30 days
Heat
1.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- antigravity-cli
skills/antigravity-cli - ask-to-plan
skills/ask-to-plan - codex-cli
skills/codex-cli - devin-cli
skills/devin-cli - grok-cli
skills/grok-cli - marketing-copy
skills/marketing-copy - product-writing
skills/product-writing - scoped-change
skills/scoped-change - talk-like-scarletkc
skills/talk-like-scarletkc - ux-writing
skills/ux-writing - worktree-pr
skills/worktree-pr - x-content
skills/x-content
How it works
antigravity-cli
When your agent uses it
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent. Includes a background client for task progress, follow-up prompts, conversation recovery, cancellation, and visible failures.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,334 tokensWhen the skill is activated
Reference documents
1,331 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Assign and follow up
- Configuration and permissions
- Check results and recover
Scripts executed separately
scripts/agent_task_runtime.pyscripts/agy.py
Files
SKILL.mdcore6,323 bytesSKILL.mdcore6,323 bytesSKILL.mdcore6,323 bytesSKILL.mdcore6,323 bytesreferences/client.mddoc6,033 bytesscripts/agent_task_runtime.pyruns9,974 bytesscripts/agy.pyruns27,786 bytes
Read SKILL.md
# Antigravity CLI
Use the installed `agy` CLI as an external coding agent. The bundled client
returns a task ID immediately and keeps a background worker available for
follow-ups. It runs each turn with official streaming JSON input/output and
resumes the exact Antigravity conversation on the next turn. Waiting for the
process and stderr to finish makes permission denials and partial-output
timeouts visible; each follow-up incurs CLI startup time.
Delegate when the user requests Antigravity or another agent can add value
that you can verify. Keep routine work with the supervising agent when the
extra startup and review time would outweigh that benefit.
Antigravity CLI must already be installed and authenticated. Runask-to-plan
When your agent uses it
Guide a user from an unclear idea to an actionable plan through the agent harness's native ask tool and clickable choices. Use when the user wants a guided requirements interview, step-by-step questions, help deciding what to build, or a button-led path from goals to scope, solution, and technology choices. Do not turn an ordinary implementation request or a single clarification into an interview.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
1,924 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Use the harness's actual ask tool
- Make each question easy to answer
- Narrow from outcomes to implementation
- Derive the technical choices
- Carry decisions forward
- Converge and deliver the plan
Files
SKILL.mdcore9,792 bytes
Read SKILL.md
# Ask to Plan
Help the user discover what they want by making one useful decision at a time.
Move from broad outcomes to concrete requirements and then an implementable
plan. The user should be able to make progress by choosing buttons, including
when they have no idea yet or do not know technical terms.
The default deliverable is a plan. Starting this interview or accepting a
solution does not itself request implementation. If the user later asks to
build it, carry the settled requirements into that work.
## Use the harness's actual ask tool
Identify the native structured-question tool exposed in the current session,codex-cli
When your agent uses it
When handing work to the Codex CLI earns its cost, and how to size the run: second-model review, bounded implementation hand-offs, sandbox permissions, model and reasoning effort. Use when the user asks for Codex or `codex exec`, when a change is complex or high-stakes enough that an independent reviewer would change the outcome, or when a delegated run needs its model, effort, or permissions chosen. For agents other than Codex itself.
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
2,639 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to reach for it
- When to keep it
- Choosing the model
- Choosing the effort
- Running it
- Reading the result back
Files
SKILL.mdcore11,268 bytes
Read SKILL.md
# Codex CLI
Codex is a second agent on the same machine, with its own model behind it.
That is the entire reason to reach for it: a model that did not write the code
has no memory of intending it to work. Everything below follows from that one
asymmetry — who wrote it, who reads it, and how much thinking each step is
worth paying for.
This skill is for the supervising agent, not for Codex. If you *are* Codex,
this does not apply — calling yourself buys nothing but a second opinion from
the same mind. Claude Code is the intended caller.
It also assumes the machine is already set up: `codex` on `PATH`, the user
logged in, and whatever MCP servers and tools they want available configureddevin-cli
When your agent uses it
Delegate bounded coding tasks to the local Devin CLI over ACP from a supervising agent such as Claude Code or Codex. Use when the user asks to hand work to Devin, when an independent implementation, port, review, or investigation can run in parallel with your own work, or when an earlier Devin session needs a follow-up. Includes a blocking run helper with single-use permission answers, a deny policy, progress summaries, and session resume.
What it loads into context
Frontmatter
158 tokensAlways available to the agent
SKILL.md
1,802 tokensWhen the skill is activated
Reference documents
1,053 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Run a task
- Write the brief
- Isolate and integrate
- Permissions
- Model and effort
- Monitor
- Follow-ups
- Verify before accepting
Scripts executed separately
scripts/devin_acp.py
Files
SKILL.mdcore7,594 bytesSKILL.mdcore7,594 bytesreferences/protocol.mddoc4,002 bytesscripts/devin_acp.pyruns28,990 bytes
Read SKILL.md
# Devin CLI
Devin CLI is a separate coding agent on the same machine. `devin acp` speaks
the Agent Client Protocol over stdio; the bundled helper
[scripts/devin_acp.py](scripts/devin_acp.py) drives one turn, answers
permission requests from a local policy, and records everything in a run
directory. It uses only the Python standard library (3.10+). Resolve the
script relative to this installed skill, not the project being worked on.
Devin must already be installed and signed in. Signing in opens a browser,
so the user does it with `devin auth login`; the helper never authenticates
and never changes Devin's configuration. If `devin` is missing, signed out,
or out of quota, report that and the work that remains instead of quietly
doing the task yourself.grok-cli
When your agent uses it
Delegate bounded tasks to Grok Build from a supervising agent such as Codex. Use when the user asks Grok to investigate, review, implement, or provide another perspective, or when a distinct coding agent would materially help. Includes a background ACP client for progress, follow-up prompts, permissions, and cancellation.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
1,250 tokensWhen the skill is activated
Reference documents
1,086 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Delegate a task
- Configuration and permissions
- Supervise the result
Scripts executed separately
scripts/acp_client.pyscripts/agent_task_runtime.pyscripts/grok.pyscripts/windows_job.py
Files
SKILL.mdcore5,851 bytesSKILL.mdcore5,851 bytesSKILL.mdcore5,851 bytesSKILL.mdcore5,851 bytesreferences/client.mddoc4,936 bytesscripts/acp_client.pyruns3,783 bytesscripts/agent_task_runtime.pyruns9,974 bytesscripts/grok.pyruns20,980 bytesscripts/windows_job.pyruns134 bytes
Read SKILL.md
# Grok CLI
Use Grok Build as a separate coding agent on the same machine. The bundled
client launches `grok agent --no-leader stdio`, keeps its ACP session open,
and returns a task ID immediately. This is an external task: it does not
appear in Codex's native `spawn_agent` tree or inherit its conversation.
Grok Build must already be installed and configured. Use the project's
Python 3.12+ interpreter to run [scripts/grok.py](scripts/grok.py); the
client uses only the standard library. If the project has no interpreter,
`uv run --python 3.12 <script> ...` also works. Resolve the script relative
to this installed skill, not the repository being investigated.
## Delegate a taskmarketing-copy
When your agent uses it
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be disclosed publicly, keeping claims traceable to shipped changes, and writing a headline that carries information instead of hype. Use when drafting or revising anything aimed at people who do not use the product yet, and when deciding whether a link, key, price, or unreleased detail can appear in public copy.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
1,105 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Disclosure comes first
- Claims stay traceable
- Writing for someone who has never seen it
- Naming across languages
Files
SKILL.mdcore5,052 bytes
Read SKILL.md
# Marketing Copy
Outbound copy reaches people who have no product context and no reason to
finish reading. It is also the surface where a disclosure mistake is
permanent: a post can be deleted, a screenshot of it cannot. Both facts push
the same way, toward concrete claims a reader can check.
This covers copy aimed outward. Product-internal strings and documentation
follow
[`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md);
matching the author's personal voice is
[`talk-like-scarletkc`](https://github.com/scarletkc/agents/blob/main/skills/talk-like-scarletkc/SKILL.md).
## Disclosure comes firstproduct-writing
When your agent uses it
Write, edit, or review UI copy, CLI messages, help text, code comments, and technical documentation covering product behavior, errors, status, setup, compatibility, or technical results.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
1,913 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Work from the task
- Interface copy, errors, and help
- Status and diagnostic output
- Documentation and technical explanations
- Comments and standalone artifacts
- Claims and evidence
- Review and verification
Files
SKILL.mdcore9,698 bytesSKILL.mdcore9,698 bytesSKILL.mdcore9,698 bytesevals/evals.jsonasset15,160 bytes
Read SKILL.md
# Product Writing
Help the reader understand what is happening and what they can do next.
## Work from the task
Use only the sections relevant to the requested copy. Preserve the user's
meaning, terminology, audience, and requested format. Follow existing product
conventions where they help readers recognize controls, commands, and states.
A wording task does not itself authorize changes to product behavior or a
reorganization of the documentation.
Ground behavioral claims in supplied facts, the relevant implementation or
specification, or an observed result. When a fact cannot be verified, identifyscoped-change
When your agent uses it
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Use when scope is ambiguous, a diff touches neighboring surfaces, required dependent edits are unclear, or a proposed compatibility layer, migration, fallback, flag, abstraction, or parallel implementation may exceed the request.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
1,164 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Outside the boundary
- Inside the boundary
- When the boundary is unclear
- Order of work
Files
SKILL.mdcore5,401 bytes
Read SKILL.md
# Scoped Change
A change has one correct size and the request defines it. Overshooting and
undershooting are the same failure — a boundary that was never located —
and they fail differently: unrequested edits surface in review or in
production, missing edits surface as the user finding them. Locate the
boundary first, then be exhaustive inside it and inert outside it.
When the boundary is corrected mid-task, the result reads as though the
corrected scope were the only one there had ever been. A title, comment, or
rationale that keeps the dropped option alive re-imports the overshoot the
correction just removed, and the reader pays for it twice; what belongs in a
deliverable is
[`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md).talk-like-scarletkc
When your agent uses it
按 scarletkc 本人的自然表达习惯代写、改写、润色和翻译文本，适用于推文、评论、聊天消息、模型或工具体验文、项目介绍、GitHub 文本和正式通信。用户要求撰写可直接使用的成稿、去除 AI 腔，或在翻译中保留本人语气和立场时使用，无需明确点名本 skill。单纯的事实问答、技术分析、代码审查和任务讨论不触发。
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
2,820 tokensWhen the skill is activated
Reference documents
8,919 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 声音
- 删掉 AI 痕迹
- 场景
- 工作流程
- 资源
- 维护
Scripts executed separately
scripts/lint_style.py
Files
SKILL.mdcore10,032 bytesevals/evals.jsonasset35,941 bytesreferences/dialogue-samples.mddoc24,481 bytesreferences/persona.mddoc1,417 bytesreferences/surface-profiles.mddoc3,937 bytesscripts/lint_style.pyruns6,199 bytes
Read SKILL.md
# Talk Like scarletkc
让文字读起来像 scarletkc 本人写的。她的文字像一个有情绪、有明确判断的开发者
在实时分享自己的发现，先说结论或感受，再补原因，不写空洞背景，也不为了显得
完整而总结。
按任务分两种做法。用户给了要说的话，让你换成她的口吻，是改写语气，包括润色、
整体改写、翻译和局部修改：原意、事实、立场和情绪强度都照原样，只改怎么说。
用户给了素材或主题，让你写一条，是起草：不要只把素材转述一遍，可以主动加角度、
态度、反应、吐槽、类比和反问，把话说得更有劲。两种做法都不编造可核对的事实。
本 skill 只管声音，也就是措辞、节奏、语气和标点。X 帖文选什么讲、第一句放
什么、要不要分楼，交给
[`x-content`](https://github.com/scarletkc/agents/blob/main/skills/x-content/SKILL.md)。ux-writing
When your agent uses it
Judgment for text read by someone who wasn't there when it was written: user-facing output, error and help text, docs, comments, and generated deliverables. Use when that text is the substance of the work or under review.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
3,626 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Status output & diagnostics
- Error messages
- Documentation
- Facts that go stale
- The final state, not the path to it
- Sync sweep for behavior changes
- Testing copy
Files
SKILL.mdcore16,224 bytesSKILL.mdcore16,224 bytesSKILL.mdcore16,224 bytes
Read SKILL.md
# UX Writing & Docs
User-visible text is product behavior and carries the same quality bar as
code. Every rule below is distilled from a real defect caught in review, and
keeps its counter-example because the reasoning is the point. When in doubt,
re-read the output as the user who just hit the problem.
## Status output & diagnostics
- **Report effective values, not stored ones.** A status display answers
"what will happen when I run this", so resolve values exactly the way the
runtime does, including environment variables and layered config.
*Counter-example: a config viewer printed "API key set: no" while an env
var held the key the next run would actually use.*worktree-pr
When your agent uses it
Decide whether a task deserves its own git worktree and, if chosen, run it end to end: branch from the integration branch rather than the current tree, keep the main working copy untouched while the task runs, compare the result against the untouched baseline before declaring it done, and prepare it for a pull request instead of merging. Use when a request says to do the work in a new worktree or branch, when a change is large or risky enough that the main tree should stay usable, when several tasks need to run in parallel on one repository, when a result has to be diffed against current behavior, and when deciding where screenshots, builds, and other artifacts produced in a worktree should end up.
What it loads into context
Frontmatter
217 tokensAlways available to the agent
SKILL.md
1,011 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Deciding
- Running
- Before declaring it done
- Landing
Files
SKILL.mdcore4,696 bytes
Read SKILL.md
# Worktree & PR
A worktree buys two things: the main working copy stays usable while the task
runs, and the untouched copy remains available as a baseline to compare
against. Both are worth real setup cost, and neither applies to every change.
This covers the isolation mechanics. How large the change itself should be is
[`scoped-change`](https://github.com/scarletkc/agents/blob/main/skills/scoped-change/SKILL.md),
and it applies inside a worktree exactly as it does anywhere else.
## Deciding
Consider a worktree when at least one holds: the task is large enough that a
half-finished state would block other work, several tasks need to progress onx-content
When your agent uses it
为 X（Twitter）寻找值得发的素材、筛选选题、撰写和改进帖文或串，并从读者视角重读，改善吸引力、阅读连贯性和真实讨论空间。用户问 X 最近有什么可以发、想写一条有流量的帖文，或反馈 X 帖文太复杂、读不下去时使用。只调整个人语气或忠实翻译已有文本时不触发。
What it loads into context
Frontmatter
158 tokensAlways available to the agent
SKILL.md
564 tokensWhen the skill is activated
Reference documents
2,902 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 按请求进入
- 工作重点
Files
SKILL.mdcore2,083 bytesevals/evals.jsonasset41,411 bytesreferences/discovery.mddoc3,548 bytesreferences/writing.mddoc7,108 bytes
Read SKILL.md
# X Content
## 按请求进入
- 找素材或选题：读 [寻找素材](references/discovery.md)。
- 写帖文、写串或改稿：读 [写作与读者重读](references/writing.md)。
素材已经足够时直接写；涉及最新事实或证据缺口时再核对相关来源。
## 工作重点
1. 从用户要求、已有稿件和当前上下文确认面向谁、想讲什么、希望读者得到
什么。已有信息足够就直接继续，只询问会影响选题或成稿的缺失信息。
2. 区分来源事实、作者观点、个人实测和待证实推断，不编造经历、数据和事实。
起草时不只是转述素材，可以替作者找角度、补态度和反应，不必先问；立场是你Skills included
- antigravity-cli
- ask-to-plan
- codex-cli
- devin-cli
- grok-cli
- marketing-copy
- product-writing
- scoped-change
- talk-like-scarletkc
- ux-writing
- worktree-pr
- x-content
Repository facts
- License
- Apache-2.0
- Created
- Jul 12, 2026
- Last pushed
- Nov 2, 2026
- Forks
- 14
- Open issues
- 1
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 11 notes
skills/antigravity-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/antigravity-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/antigravity-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/devin-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/grok-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/grok-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/grok-cli/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/product-writing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/product-writing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ux-writing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ux-writing/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 76 network referencesin 18 files: codex-cli/SKILL.md:5 x-content/evals/evals.json:73 marketing-copy/SKILL.md:5 and 15 more
- No hidden or obfuscated text
- 6 instruction override signalsin 2 files: antigravity-cli/SKILL.md:82 antigravity-cli/scripts/agy.py:602
- 8 executable scriptsin 8 files: antigravity-cli/scripts/agent_task_runtime.py:1 antigravity-cli/scripts/agy.py:1 devin-cli/scripts/devin_acp.py:1 and 5 more
- 6 references to secretsin 2 files: antigravity-cli/scripts/agy.py:37 grok-cli/scripts/grok.py:32
- No requests to vote in Hot
Show all 96 signals by file
skills/antigravity-cli/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Delegate work to Antigravity CLI, inspect progress and tool failures, and continue the same conversation across follow-up tasks." - Network accessline 7
source: https://github.com/scarletkc/agents - Instruction override signalline 82
interactive AGY session to establish the required permissions, following the original authorization. Do not repeatedly submit a blocked operation with unchanged permissions. The helper exposes `--dangerously-skip-permissions` - Instruction override signalline 83
original authorization. Do not repeatedly submit a blocked operation with unchanged permissions. The helper exposes `--dangerously-skip-permissions` only as an explicit override; do not use it merely to avoid an approval. - Instruction override signalline 84
unchanged permissions. The helper exposes `--dangerously-skip-permissions`
skills/antigravity-cli/references/client.md
- Network accessline 104
Protocol references: [Headless mode](https://www.antigravity.google/docs/cli/headless/), - Network accessline 105
[permissions](https://www.antigravity.google/docs/cli/permissions/), and - Network accessline 106
[installation and authentication](https://antigravity.google/docs/cli/install/).
skills/antigravity-cli/scripts/agent_task_runtime.py
- Executable scriptline 1
Executable file
skills/antigravity-cli/scripts/agy.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 37
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 545
[Credential-related source omitted] - Instruction override signalline 602
) start.add_argument( "--dangerously-skip-permissions", - Instruction override signalline 603
start.add_argument( "--dangerously-skip-permissions", action="store_true", - Instruction override signalline 604
"--dangerously-skip-permissions",
skills/ask-to-plan/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Turn a rough idea into clear goals, requirements, a solution, and an actionable plan through guided questions and native choices." - Network accessline 7
source: https://github.com/scarletkc/agents
skills/codex-cli/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Reach for the Codex CLI when a task is hard enough to earn it: second-model review, bounded hand-offs, sandbox permissions, and a model and effort matched to the di - Network accessline 7
source: https://github.com/scarletkc/agents - Network accessline 55
whether *you* understand the change — if you cannot write it, delegating it just moves the confusion downstream. What "bounded" means is [`scoped-change`](https://github.com/scarletkc/agents/blob/main/skills/scoped-change/SKILL.md), - Network accessline 56
just moves the confusion downstream. What "bounded" means is [`scoped-change`](https://github.com/scarletkc/agents/blob/main/skills/scoped-change/SKILL.md), and it binds Codex exactly as it binds you: pass the boundary along in the - Network accessline 57
[`scoped-change`](https://github.com/scarletkc/agents/blob/main/skills/scoped-change/SKILL.md), - Network accessline 75
release notes need the taste and the context of the session that has been talking to the user, and they survive delegation badly. See [`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md). - Network accessline 76
talking to the user, and they survive delegation badly. See [`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md). - **Anything you cannot check afterwards.** Delegating work you have no way - Network accessline 77
[`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md).
skills/devin-cli/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Hand bounded tasks to Devin CLI over ACP, keep its permissions single-use, watch progress, and resume the same session for follow-ups." - Network accessline 7
source: https://github.com/scarletkc/agents
skills/devin-cli/references/protocol.md
- Network accessline 80
Protocol reference: [ACP prompt turn](https://agentclientprotocol.com/protocol/v1/prompt-turn).
skills/devin-cli/scripts/devin_acp.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/grok-cli/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Delegate work to Grok Build, keep its session for follow-ups, and inspect results while the supervising agent continues working." - Network accessline 7
source: https://github.com/scarletkc/agents
skills/grok-cli/references/client.md
- Network accessline 86
its own tools. It handles permission requests and rejects unsupported client methods rather than leaving them waiting indefinitely. Protocol references: [Grok ACP](https://docs.x.ai/build/cli/headless-scripting) and - Network accessline 87
client methods rather than leaving them waiting indefinitely. Protocol references: [Grok ACP](https://docs.x.ai/build/cli/headless-scripting) and [ACP prompt turns](https://agentclientprotocol.com/protocol/v1/prompt-turn). - Network accessline 88
references: [Grok ACP](https://docs.x.ai/build/cli/headless-scripting) and - Network accessline 89
[ACP prompt turns](https://agentclientprotocol.com/protocol/v1/prompt-turn).
skills/grok-cli/scripts/acp_client.py
- Executable scriptline 1
Executable file
skills/grok-cli/scripts/agent_task_runtime.py
- Executable scriptline 1
Executable file
skills/grok-cli/scripts/grok.py
skills/grok-cli/scripts/windows_job.py
- Executable scriptline 1
Executable file
skills/marketing-copy/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Write outbound promo copy that stays truthful, discloses only what may be public, and earns attention without hype." - Network accessline 7
source: https://github.com/scarletkc/agents - Network accessline 18
This covers copy aimed outward. Product-internal strings and documentation follow [`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md); - Network accessline 19
follow [`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md); matching the author's personal voice is - Network accessline 20
[`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md); - Network accessline 22
[`talk-like-scarletkc`](https://github.com/scarletkc/agents/blob/main/skills/talk-like-scarletkc/SKILL.md).
skills/product-writing/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Write accurate product copy and useful technical docs." - Network accessline 7
source: https://github.com/scarletkc/agents
skills/product-writing/evals/evals.json
- Network accessline 182
"id": 15, "name": "field-level-origin-claims", "prompt": "Correct this configuration display: 'Endpoint settings (from environment): URL=https://api.example.com; API key=configured'. The URL comes from the config file. Only the - Network accessline 183
"name": "field-level-origin-claims", "prompt": "Correct this configuration display: 'Endpoint settings (from environment): URL=https://api.example.com; API key=configured'. The URL comes from the config file. Only the key comes from a - Network accessline 184
"prompt": "Correct this configuration display: 'Endpoint settings (from environment): URL=https://api.example.com; API key=configured'. The URL comes from the config file. Only the key comes from an environment variable. Keep both facts vis
skills/scoped-change/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Hold a change to the size the request defines: no unrequested surfaces, no speculative layers, no half-applied edits." - Network accessline 7
source: https://github.com/scarletkc/agents - Network accessline 22
correction just removed, and the reader pays for it twice; what belongs in a deliverable is [`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md). - Network accessline 24
[`ux-writing`](https://github.com/scarletkc/agents/blob/main/skills/ux-writing/SKILL.md).
skills/talk-like-scarletkc/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Write and translate in scarletkc's natural voice without generic AI phrasing." - Network accessline 7
source: https://github.com/scarletkc/agents - Network accessline 22
本 skill 只管声音，也就是措辞、节奏、语气和标点。X 帖文选什么讲、第一句放 什么、要不要分楼，交给 [`x-content`](https://github.com/scarletkc/agents/blob/main/skills/x-content/SKILL.md)。 - Network accessline 23
什么、要不要分楼，交给 [`x-content`](https://github.com/scarletkc/agents/blob/main/skills/x-content/SKILL.md)。 两个一起用时，内容取舍听 x-content，怎么说听这里。规则只作用于代写、改写和 - Network accessline 24
[`x-content`](https://github.com/scarletkc/agents/blob/main/skills/x-content/SKILL.md)。 - Network accessline 138
规范版本在 https://github.com/scarletkc/agents 的 `skills/talk-like-scarletkc/`。
skills/talk-like-scarletkc/scripts/lint_style.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/ux-writing/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Review user-facing copy and documentation for clarity, consistency, facts that do not go stale, and no leftover intermediate state." - Network accessline 7
source: https://github.com/scarletkc/agents
skills/worktree-pr/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Optionally run a task in its own worktree: branch from the integration branch, compare against the baseline, and prepare it for a PR." - Network accessline 7
source: https://github.com/scarletkc/agents - Network accessline 17
This covers the isolation mechanics. How large the change itself should be is [`scoped-change`](https://github.com/scarletkc/agents/blob/main/skills/scoped-change/SKILL.md), - Network accessline 18
[`scoped-change`](https://github.com/scarletkc/agents/blob/main/skills/scoped-change/SKILL.md),
skills/x-content/SKILL.md
- Network accessline 5
metadata: author: scarletkc source: https://github.com/scarletkc/agents - Network accessline 6
author: scarletkc source: https://github.com/scarletkc/agents summary: "Find worthwhile X topics and write posts that earn attention and keep readers engaged." - Network accessline 7
source: https://github.com/scarletkc/agents
skills/x-content/evals/evals.json
- Network accessline 73
"id": 6, "name": "discover-fresh-evidence-and-reader-fit", "prompt": "Use x-content to suggest up to three X topics for people using AI coding tools. This is an offline exercise on 2026-04-12; use only these complete fictional s - Network accessline 74
"name": "discover-fresh-evidence-and-reader-fit", "prompt": "Use x-content to suggest up to three X topics for people using AI coding tools. This is an offline exercise on 2026-04-12; use only these complete fictional sources. A: http - Network accessline 75
"prompt": "Use x-content to suggest up to three X topics for people using AI coding tools. This is an offline exercise on 2026-04-12; use only these complete fictional sources. A: https://example.org/patchpad/release-24, published April 11, - Network accessline 87
"id": 7, "name": "discovery-with-inaccessible-primary-source", "prompt": "Use x-content to find something worth posting for developers from these results. This is an offline fictional exercise; there is no access to X or a live - Network accessline 88
"name": "discovery-with-inaccessible-primary-source", "prompt": "Use x-content to find something worth posting for developers from these results. This is an offline fictional exercise; there is no access to X or a live browser. A sear - Network accessline 89
"prompt": "Use x-content to find something worth posting for developers from these results. This is an offline fictional exercise; there is no access to X or a live browser. A search snippet from https://example.org/snippet claims a new mod - Network accessline 114
"id": 9, "name": "localized-final-edit-preserves-thread-and-links", "prompt": "Use x-content for one correction to my fictional X thread, and give the final complete version. Main: NotePilot 2.3 切到本机模式后，可能要重新说一遍自己的偏好。 Reply: 在线和 - Network accessline 115
"name": "localized-final-edit-preserves-thread-and-links", "prompt": "Use x-content for one correction to my fictional X thread, and give the final complete version. Main: NotePilot 2.3 切到本机模式后，可能要重新说一遍自己的偏好。 Reply: 在线和本机是两套偏好，不会自动同步。 - Network accessline 116
"prompt": "Use x-content for one correction to my fictional X thread, and give the final complete version. Main: NotePilot 2.3 切到本机模式后，可能要重新说一遍自己的偏好。 Reply: 在线和本机是两套偏好，不会自动同步。 Sources reply: NotePilot release notes https://example.org/notep
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 84 facts
- Network access in the frontmatter of the SKILL.mdantigravity-cli/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mdantigravity-cli/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mdantigravity-cli/SKILL.md:7Low confidence
- Instruction override signal in prose of the SKILL.mdantigravity-cli/SKILL.md:82High confidence
- Instruction override signal in prose of the SKILL.mdantigravity-cli/SKILL.md:83High confidence
- Instruction override signal in prose of the SKILL.mdantigravity-cli/SKILL.md:84High confidence
- Network access in prose of documentationantigravity-cli/references/client.md:104Low confidence
- Network access in prose of documentationantigravity-cli/references/client.md:105Low confidence
- Network access in prose of documentationantigravity-cli/references/client.md:106Low confidence
- Executable script in a comment of a file that runsantigravity-cli/scripts/agent_task_runtime.py:1Low confidence
- Executable script in code of a file that runsantigravity-cli/scripts/agy.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueantigravity-cli/scripts/agy.py:37Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueantigravity-cli/scripts/agy.py:41Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueantigravity-cli/scripts/agy.py:545Low confidence
- Instruction override signal in code of a file that runsantigravity-cli/scripts/agy.py:602Low confidence
- Instruction override signal in code of a file that runsantigravity-cli/scripts/agy.py:603Low confidence
- Instruction override signal in code of a file that runsantigravity-cli/scripts/agy.py:604Low confidence
- Network access in the frontmatter of the SKILL.mdask-to-plan/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mdask-to-plan/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mdask-to-plan/SKILL.md:7Low confidence
- Network access in the frontmatter of the SKILL.mdcodex-cli/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mdcodex-cli/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mdcodex-cli/SKILL.md:7Low confidence
- Network access in prose of the SKILL.mdcodex-cli/SKILL.md:55Low confidence
- Network access in prose of the SKILL.mdcodex-cli/SKILL.md:56Low confidence
- Network access in prose of the SKILL.mdcodex-cli/SKILL.md:57Low confidence
- Network access in prose of the SKILL.mdcodex-cli/SKILL.md:75Low confidence
- Network access in prose of the SKILL.mdcodex-cli/SKILL.md:76Low confidence
- Network access in prose of the SKILL.mdcodex-cli/SKILL.md:77Low confidence
- Network access in the frontmatter of the SKILL.mddevin-cli/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mddevin-cli/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mddevin-cli/SKILL.md:7Low confidence
- Network access in prose of documentationdevin-cli/references/protocol.md:80Low confidence
- Executable script in code of a file that runsdevin-cli/scripts/devin_acp.py:1High confidence
- Network access in the frontmatter of the SKILL.mdgrok-cli/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mdgrok-cli/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mdgrok-cli/SKILL.md:7Low confidence
- Network access in prose of documentationgrok-cli/references/client.md:86Low confidence
- Network access in prose of documentationgrok-cli/references/client.md:87Low confidence
- Network access in prose of documentationgrok-cli/references/client.md:88Low confidence
- Network access in prose of documentationgrok-cli/references/client.md:89Low confidence
- Executable script in prose of a file that runsgrok-cli/scripts/acp_client.py:1Low confidence
- Executable script in a comment of a file that runsgrok-cli/scripts/agent_task_runtime.py:1Low confidence
- Executable script in code of a file that runsgrok-cli/scripts/grok.py:1High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuegrok-cli/scripts/grok.py:32Low confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuegrok-cli/scripts/grok.py:36Low confidence
- Access to secrets in code of a file that runsgrok-cli/scripts/grok.py:107High confidence
- Executable script in prose of a file that runsgrok-cli/scripts/windows_job.py:1Low confidence
- Network access in the frontmatter of the SKILL.mdmarketing-copy/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mdmarketing-copy/SKILL.md:6Low confidence
and 34 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path CLAUDE.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/antigravity-cli/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/antigravity-cli/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/antigravity-cli/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/antigravity-cli/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
