Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Fjob Email To Senior

ASecurity

Drafts an email or chat message to a senior colleague with the point and the ask first, a subject line that names the ask, a clear deadline and a tone check against what you meant. Use for "run fjob-email-to-senior", "email to my director", "how do I word this to a senior person", "make this email shorter", "rewrite my message to my boss", "bottom line up front", "does this sound rude", "chase a senior colleague politely", part of the Nail Your First Job with Claude Pack by Polar Bear.

2 stars
0 votes
0 copies
0 views
Added 10/5/2026
ai-agents

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill fjob-email-to-senior --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fjob Email To Senior?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Fjob Email To Senior
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-fjob-email-to-senior/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-fjob-email-to-senior)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: fjob-email-to-senior
description: Drafts an email or chat message to a senior colleague with the point and the ask first, a subject line that names the ask, a clear deadline and a tone check against what you meant. Use for "run fjob-email-to-senior", "email to my director", "how do I word this to a senior person", "make this email shorter", "rewrite my message to my boss", "bottom line up front", "does this sound rude", "chase a senior colleague politely", part of the Nail Your First Job with Claude Pack by Polar Bear.
---

# Email to a Senior Colleague

## When To Use
You rewrote a two-line email to a director five times and it still opens with "Sorry to bother you". Use this for any one-off message upward: a question, a request for a decision, a heads-up. It answers one question: will the reader know what you need from them within the first line?

## When Not To Use
For the routine Friday report, use Weekly Update to Your Manager. When two people want your time on the same day, use Priority Clash Reply, which builds the trade-off first. A two-word reply to a quick question needs no method at all.

## Inputs
- Your bullet points: what you need, from whom, by when, and why it matters
- Who the reader is (role, how well they know you) and the channel (email or chat)
- Your current draft, if you have one, and any thread it answers
If you have none of this, I start from one sentence on what you need and mark the output as a first draft.

## Approach
Bottom line up front, as set out in US Army Regulation 25-50, puts the point and the ask in the first line, then only the context the reader needs. Plain English, as the Plain English Campaign's free guides describe it, keeps the sentences short and the verbs active. The judgment is cutting: new starters bury the ask under three paragraphs of apology, and a busy reader skims, misses it and answers a different question, or none.

## Workflow
1. Ask at most three questions: what does your employer's AI policy allow for this, and which Claude account are you in (work-provided or personal); what exactly do you need the reader to do, and by when; is this bad news or sensitive? If the message holds client or internal detail, run Data Check Before You Paste first and write with [placeholders] you fill in your mail app.
2. Write the bottom line: one or two sentences with the point and the ask ("Could you approve [item] by [date]?"). If you cannot write it, you are not ready to send; say so.
3. Add the minimum context: only what the reader needs to act, in two or three short sentences. Move the history to a link or cut it.
4. State the deadline and what happens if there is no answer ("If I have not heard by [date], I will [default]").
5. Write a subject line that names the ask ("Decision needed by [date]: [topic]"). Size to the channel: a chat message is two or three lines, an email fits on one screen.
6. Plain English pass: short sentences, everyday words, active verbs; cut hedges such as "just", "I was wondering if" and "sorry" that hide the ask. For bad news or a sensitive topic, keep one line of context before the point and say why.
7. Tone check: I say back in one line what the message sounds like ("direct and polite", "a bit apologetic"). You compare it with what you meant, and change your words, not just mine.

## Output Format
```markdown
# Email to a Senior Colleague
**To:** [role] · **Channel:** [email / chat] · **Policy check:** [what your policy allows, account used]
**Subject:** [Decision needed by date: topic]

[Bottom line: the point and the ask, one or two sentences]

[Minimum context, two or three sentences]

[Deadline, and what happens if there is no answer]

[Sign-off in your usual style]

## Tone check
- What it sounds like: [one line]
- What you meant: [your words]
- Placeholders to fill before sending: [list]
## Decision
You decide whether, when and how to send it. The reader decides on the ask by [date].
```

## Done When
- The ask is in the first two sentences and the subject line names it.
- There is a date, and a default if nobody answers.
- The length fits the channel and every placeholder is listed.
- You have compared the tone check with what you meant.

## Quality Bar
- Drafted from your bullet points in your voice; Claude never writes as if it were you in a live conversation.
- No apology for existing; one "thanks" is enough.
- Facts and dates come only from what you gave; anything unsure stays as a [placeholder].
- Bad news is not softened until it disappears: the point stays in the message.
- You read, check and send it; Claude never sends in your name.

## Next
Run fjob-meeting-notes (Meeting Notes and Actions) to capture the meeting this message sets up.

## About the makers

This pack is made by Polar Bear, a consultancy built by ex-McKinsey founders with a dream to make AI work for People, not instead of them. We help our clients build people systems and AI-first ways of working, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

Attribution

polar-bear-orgpolar-bear-org
View sourceSee grades on GitHubMore from polar-bear-org →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →