agent-voice
Disclose that a message is agent-written, and keep it plain and concise.
Skill by William Duyck
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fuzzyfox-agent-voice
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-voice
What's inside
- Skill name
agent-voice- Description
- Disclose that a message is agent-written, and keep it plain and concise. Use before posting any conversational message on the operator's account — a PR review comment or reply, an issue thread, a Slack message.
- License
- MIT
- Metadata
- author: William Duyck · version: 1.0
- Instructions
- 58 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Posting through the operator's own credentials stamps **their** name and avatar on the message. The platform has no bot badge to offer, so a reader — human or agent — reads it as the operator writing by hand. ## Where this applies **Conversation**: anywhere a person might reply. Review comments and the replies under them, issue and PR comment threads, Slack. The test is whether there is someone on the other end. Commits and tickets are artifacts, not conversation, and carry their own conventions. Leave them alone. ## The marker The marker **leads** the message, so it is read before the substance rather than discovered after it. Anywhere GitHub-flavoured markdown renders: ```md > [!NOTE] > 🤖 Posted by <model>, acting on behalf of <operator>. ``` **Name yourself.** `<model>` is the model actually writing — Claude Opus 5, ChatGPT, Gemini, Grok — named specifically enough that a reader knows what produced the message and can weigh it accordingly. **Resolve `<operator>` from the platform itself** — whatever it offers for identifying the authenticated account, in the form that platform addresses them by. A guessed handle can credit the wrong person. Where callouts do not render, one italic line at the top saying the same thing. Two cases skip it. The platform may have already said it — a bot account, a GitHub App, an agent identity the UI badges — and repeating it is noise. And the operator may waive it for a given message, by saying so. ## Plain prose A human and an agent will both read this thread. Write once for both: literal, specific, and structured so the point survives a skim. Open on the decision — what changed, or why nothing did. Give the reason once, in as few sentences as carry it, and link the commit or line rather than narrating the diff back. Disagree in the same voice: say plainly that you are not making the change, and give the reasoning that stands behind it. Say when you are unsure, and name what would settle it. Reach for a diagram, table, or code block whenever the shape of the thing is the point — a sequence someone has to hold in their head, a before and after, a set of cases. Both readers get there faster through the picture than through the paragraph describing it. Substance is the whole message. The appreciation preamble, the restatement of the comment being answered, and the closing summary each cost a reader a pass over the thread and tell them nothing.
From fuzzyfox/skills, MIT.
More from fuzzyfox/skills
- 0.569score
babysit
William Duyck
Babysit a pull request to approval: watch CI and the automated reviewers, action or push back on each comment, push fixes, keep watching until the bots have…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
session-usage
fuzzyfox
Headroom left in the Claude subscription windows — percent consumed and time-to-reset.
SkillBFreshness: B★ 4Claude Code +9 - 0.524score
mailbox
William Duyck
Inter-agent mailbox for sending a handoff to another agent session and picking up replies.
SkillCFreshness: C★ 4Claude Code +9 - 0.524score
quickchart
William Duyck
Generate chart images for markdown documents using the QuickChart API.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
commit
William Duyck
Commit staged changes as a Gitmoji-prefixed Conventional Commit.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
desert-mode
fuzzyfox
Ruthless token-minimization mode plus a "token police" prompt check.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
dispatch
William Duyck
Dispatch work to another agent through the mailbox to a named existing peer, or to a new agent wired to reply to you.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
changelog
William Duyck
Generate a markdown changelog for the changes between a fixed point and HEAD, enriched with issue-tracker context.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
open-pr
William Duyck
Open, publish, or raise a GitHub pull request.
SkillCFreshness: C★ 4Claude Code +9 - 0.516score
spawn
William Duyck
Spawn a fresh agent session from the current one — hand the conversation off into a new tmux window that continues the work one-way, with no channel back.
SkillCFreshness: C★ 4Claude Code +9 - 0.514score
handback
William Duyck
Return your work to the parent agent that spawned you.
SkillCFreshness: C★ 4Claude Code +9 - 0.494score
review
William Duyck
Review the changes since a fixed point along three independent axes — Standards (does the code follow this repo's documented conventions and avoid known…
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 10, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- MIT
- Repository
- github.com/fuzzyfox/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from William Duyck
- 0.569score
babysit
William Duyck
Babysit a pull request to approval: watch CI and the automated reviewers, action or push back on each comment, push fixes, keep watching until the bots have…
SkillBFreshness: B★ 4Claude Code +9 - 0.524score
mailbox
William Duyck
Inter-agent mailbox for sending a handoff to another agent session and picking up replies.
SkillCFreshness: C★ 4Claude Code +9 - 0.524score
quickchart
William Duyck
Generate chart images for markdown documents using the QuickChart API.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
commit
William Duyck
Commit staged changes as a Gitmoji-prefixed Conventional Commit.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
dispatch
William Duyck
Dispatch work to another agent through the mailbox to a named existing peer, or to a new agent wired to reply to you.
SkillCFreshness: C★ 4Claude Code +9 - 0.519score
changelog
William Duyck
Generate a markdown changelog for the changes between a fixed point and HEAD, enriched with issue-tracker context.
SkillCFreshness: C★ 4Claude Code +9
Cite this page
agent-voice skill. Agent Mart. https://agentmart.dev/skills/fuzzyfox-agent-voice (last updated 2026-10-24)