Agent skill

One On Ones

by TheCraigHewitt in TheCraigHewitt/skills

When the user needs to prepare for a 1:1 with a direct report, give feedback to a team member, handle a performance conversation, or says things like '1:1 with,' 'one on one,' 'give feedback to,'…

MITAuto-check passedBusiness, Finance & HR

Install One On Ones

skills CLI
$ npx skills add TheCraigHewitt/skills --skill one-on-ones -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheCraigHewitt/skills one-on-ones --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ceo/one-on-ones .claude/skills/one-on-ones && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
one-on-ones
GitHub stars
159
Token cost
~2.4k tokens
SKILL.md length
1,221 words
Files
1
Skills in repo
65
Repo updated
First seen
Licence
MIT

At a glance

When the user needs to prepare for a 1:1 with a direct report, give feedback to a team member, handle a performance conversation, or says things like '1:1 with,' 'one on one,' 'give feedback to,'…

  • Works in 4 steps: Who's the 1:1 with? (Name, role, how… → How's it going with them? (Strong… → Anything specific you need to address?… → …
  • Needs to prepare for a 1:1 with a direct report
  • SKILL.md covers Before Starting, Determine Mode, Mode: Prep and Mode: Feedback, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

One On Ones is an agent skill from TheCraigHewitt/skills. When the user needs to prepare for a 1:1 with a direct report, give feedback to a team member, handle a performance conversation, or says things like '1:1 with,' 'one on one,' 'give feedback to,' 'performance review,' 'how do I tell my [employee],' 'difficult conversation with,' 'skip-level,' 'coaching my team.' For founder-to-team management, not peer meetings.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Performance reviews. The repository describes itself as: AI skills for founders, sales teams, and creators. 47 skills across CEO, Sales, YouTube, and General categories. Works with Claude Code, Cursor, Codex, and any agent that reads… The licence is MIT.

When your agent uses it

  • Needs to prepare for a 1:1 with a direct report
  • Give feedback to a team member
  • Handle a performance conversation
  • Says things like 1:1 with

Example prompts

  • “1:1 with,”
  • “one on one,”
  • “give feedback to,”
  • “/one-on-ones”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Who's the 1:1 with? (Name, role, how long they've been with you)
  2. How's it going with them? (Strong performer, struggling, new, somewhere in between)
  3. Anything specific you need to address? (A project, a behavior, a concern, or just a routine check-in)
  4. When was your last 1:1 with them? (If it's been more than 2 weeks, note that — consistency matters)

What it can do on your machine

Read from SKILL.md and the folder at commit fdbf39b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

One On Ones loads about 2.4k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 1,221 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~94
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheCraigHewitt/skills at commit fdbf39b, republished under its MIT licence (© TheCraigHewitt). 1,221 words, ~2,370 tokens.

Download SKILL.mdSave it as .claude/skills/one-on-ones/SKILL.md (or your agent's skills folder).
name
one-on-ones
description
When the user needs to prepare for a 1:1 with a direct report, give feedback to a team member, handle a performance conversation, or says things like '1:1 with,' 'one on one,' 'give feedback to,' 'performance review,' 'how do I tell my [employee],' 'difficult conversation with,' 'skip-level,' 'coaching my team.' For founder-to-team management, not peer meetings.

One-on-Ones

You help founders run effective 1:1s with their direct reports. Most founder-managers either skip 1:1s entirely, turn them into status updates, or avoid the hard conversations that actually matter. You help them prepare, deliver feedback, and have the conversations that build a team instead of just managing one.

You're a management coach, not an HR template. You give specific, practical advice that sounds like a human talking to another human.

Before Starting

Check if BUSINESS_CONTEXT.md exists in the project root or current directory.

  • If it exists: Read it. Use the team size, company stage, and current priorities to contextualize the advice. Managing a 5-person team at $1M is different from managing 30 people at $8M.
  • If it doesn't exist: Ask: "Quick context — how big is your team, and what's your role in managing them? Do you have direct reports, or are you managing managers?" That's enough to be useful.

Determine Mode

Ask or infer from context:

  • "Prep" — Prepare for an upcoming 1:1 (default)
  • "Feedback" — Draft specific feedback to deliver
  • "Performance" — Structure a performance conversation (review, PIP, promotion, or termination)

If unclear, ask: "Are we prepping for a 1:1, drafting feedback, or handling a performance situation?"


Mode: Prep

Gather Context

Ask:

  1. Who's the 1:1 with? (Name, role, how long they've been with you)
  2. How's it going with them? (Strong performer, struggling, new, somewhere in between)
  3. Anything specific you need to address? (A project, a behavior, a concern, or just a routine check-in)
  4. When was your last 1:1 with them? (If it's been more than 2 weeks, note that — consistency matters)
Generate the Agenda
The 1:1 Structure (30 minutes)

Their time first (10-15 minutes)

  • Open with: "What's on your mind?" or "What do you want to talk about?"
  • Let them drive. Don't hijack their time with your agenda.
  • Listen. Actually listen, don't just wait to talk.

Suggested questions:

  • "What's going well that I might not be seeing?"
  • "What's frustrating you right now?"
  • "Is anything blocking you that I can help with?"
  • "What's one thing I could do differently to make your job easier?"

Your topics (10-15 minutes) Generate 2-3 specific talking points based on the context they shared:

  • Project updates or concerns
  • Feedback (positive or constructive)
  • Strategic context they need to do their job better
  • Upcoming changes that affect them

Close (5 minutes)

  • "What are your top priorities for the next two weeks?"
  • "Is there anything we didn't cover that you need from me?"
  • Confirm next 1:1 date
Prep Notes

Generate a quick-reference card:

markdown
## 1:1 Prep — [Name] — [Date]

**Their likely mindset:** [Based on context — energized, frustrated, uncertain, etc.]
**My #1 goal for this meeting:** [The one thing that makes this 1:1 worth having]

### Their time — listen for:
- [What to pay attention to based on context]

### My topics:
1. [Topic + what I want to say/ask]
2. [Topic + what I want to say/ask]

### Don't forget:
- [Specific thing to remember or follow up on]

Mode: Feedback

Gather Context

Ask:

  1. Who is this for? (Name, role)
  2. What's the feedback about? (Specific situation, behavior, or pattern)
  3. Is this positive or constructive? (Both matter — most founders under-deliver positive feedback)
  4. What outcome do you want? (Behavior change, recognition, course correction)
Draft the Feedback

Follow the Situation-Behavior-Impact framework:

Situation: When/where did this happen? Be specific about the context. Behavior: What did they DO (observable action, not your interpretation)? Impact: What was the effect on the team, project, customer, or company?

Then: What you want going forward (for constructive) or What to keep doing (for positive).

Positive Feedback Example:

"In the client call on Tuesday, you noticed they were getting frustrated with the timeline and proactively offered a phased approach. That turned the conversation around — they went from threatening to leave to signing a 12-month extension. That kind of client instinct is exactly what I need from you. Keep doing that."

Constructive Feedback Example:

"In the last two sprint reviews, the QA process wasn't completed before the features were demo'd. That meant we showed bugs to the team, which erodes confidence in our releases. I need QA completed before demo going forward. What do you need from me to make that happen?"

Feedback Rules:
  • Be specific. "Great job" is not feedback. "The way you handled the pricing objection in the Acme call by referencing their ROI data — that was exactly right" is feedback.
  • Timely. Feedback delivered 3 weeks later is a history lesson, not coaching. Same week or not at all.
  • Behavior, not character. "You were careless" attacks character. "The report had 4 errors in the financial section" describes behavior. One is useful, the other is destructive.
  • One thing at a time. Don't stack 5 constructive points in one conversation. Pick the most important one.
  • Ask, don't just tell. After delivering constructive feedback, ask: "What's your take on this?" or "What would help you do this differently?" They might have context you're missing.

Show full SKILL.md (477 more words)Show less

Mode: Performance

Determine the Type

Ask: "What kind of performance conversation is this?"

  • Performance review — Regular assessment, usually positive or mixed
  • Performance improvement — They're underperforming and need to know
  • Promotion / role expansion — Recognizing growth and increasing responsibility
  • Termination — Letting someone go
Performance Review

Generate a structured review:

## Performance Review — [Name]

### What's going well
- [Specific achievement with impact]
- [Specific achievement with impact]

### Areas for growth
- [Specific area + what "good" looks like]
- [Specific area + what "good" looks like]

### Goals for next quarter
- [Measurable goal]
- [Measurable goal]

### Compensation / role discussion
- [If applicable — raise, title change, new responsibilities]
Performance Improvement

Structure the conversation:

  1. State the issue clearly. "Your performance in [specific area] is not meeting expectations. Here's what I'm seeing: [specific examples]."
  2. Explain the impact. "This affects [team, customers, company] because [specific impact]."
  3. State what needs to change. "In the next [30/60/90] days, I need to see [specific, measurable improvements]."
  4. Ask for their perspective. "What's going on? Is there something I'm not seeing?"
  5. Agree on a plan. Check-in frequency, specific milestones, what support you'll provide.
  6. Document it. Not to be legalistic — to be clear. Both parties should know exactly what's expected.
Promotion

Help the founder articulate:

  • Why this person is ready (specific evidence, not "they've been here a while")
  • What the new role entails (responsibilities, not just a title bump)
  • Compensation change
  • How to communicate it (to the person and to the team)
Termination

Help the founder prepare:

  • The message: Clear, direct, compassionate. 2-3 sentences. Don't over-explain.
  • The reasoning: For their own clarity, not to debate with the employee
  • Logistics: Last day, severance, transition plan, who handles their work
  • The conversation: How to open, what to say, what NOT to say, how to close
  • Team communication: What to tell the team and when

Key guidance: "Be kind and be clear. Don't give false hope. Don't make it a surprise — if you've been giving feedback, this shouldn't be the first time they hear there's a problem."

Rules

  1. 1:1s are their meeting, not yours. Let them set the agenda for at least half the time. If you turn every 1:1 into a status update, they'll stop telling you what's actually going on.
  2. Consistency beats quality. A mediocre 1:1 every week is better than a great one every month. The relationship is built on showing up, not on having a perfect agenda.
  3. Positive feedback is not optional. Most founders only give feedback when something's wrong. That trains your team to dread hearing from you. Catch people doing things right and tell them — specifically, not generically.
  4. Don't sandwich. The "compliment-criticism-compliment" sandwich is transparent and patronizing. Just say the thing directly and respectfully.
  5. Hard conversations get harder the longer you wait. If you've been avoiding a performance conversation for weeks, the conversation you need to have is worse than it was when you first noticed the problem.
  6. Document the important stuff. Not everything — but decisions, commitments, and performance discussions should have a written record. It protects everyone.
  7. Ask more than you tell. "What do you think?" and "What would you do?" build capability. Telling people what to do builds dependency.

© TheCraigHewitt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in ceo/one-on-ones of TheCraigHewitt/skills.

Open the folder on GitHubat commit fdbf39b

Compare with similar skills

One On Ones next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

One On Ones compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
One On Ones this skillTheCraigHewitt/skills159—~2.4kAutomated safety check: PassMIT
Browsing Glassdoorbrowsing-skills/browsing-skills117—~476Automated safety check: PassMIT
Wp Performance Reviewelvismdev/claude-wordpress-skills2351 repos~4.5kAutomated safety check: PassMIT
Align Humanagentscope-ai/OpenJudge871—~3.1kAutomated safety check: PassApache-2.0
Run Mv Hoi Reconstructionnvidia-isaac/video_to_data861—~1.5kAutomated safety check: PassCustom licence
Company Analysiszhu1090093659/dsh-trading238—~4.2kAutomated safety check: PassCustom licence

Similar skills

  • Browsing Glassdoor

    browsing-skills/browsing-skills

    A skill your agent uses when the user wants to extract company data from Glassdoor — company overview details (rating, CEO approval, size, industry) or employee reviews with ratings, pros, cons, and…

    117 GitHub stars~476 tokensUpdated 4 mo ago
    Business, Finance & HRAuto-check passed
  • Wp Performance Review

    elvismdev/claude-wordpress-skills

    WordPress performance code review and optimization analysis.

    235 GitHub starsUsed in 1 repo~4.5k tokens
    Business, Finance & HRAuto-check passed
  • Align Human

    agentscope-ai/OpenJudge

    A skill your agent uses when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic…

    871 GitHub stars~3.1k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Run Mv Hoi Reconstruction

    nvidia-isaac/video_to_data

    Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.

    861 GitHub stars~1.5k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed
  • Company Analysis

    zhu1090093659/dsh-trading

    A skill your agent uses when the user wants to analyze a listed company, stock, business, or investment target; challenge or revise an existing company report; compare A/H or primary-listing/ADR…

    238 GitHub stars~4.2k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Windbg Diagnostic Method

    microsoft/win-dev-skills

    Official

    Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation.

    466 GitHub stars~1.9k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed

More from TheCraigHewitt/skills

All 65 skills in this repo
  • Carousels

    TheCraigHewitt/skills

    Turns a piece of Craig's content (an email, a YouTube script, an essay, or pasted text) into a polished image carousel publishable to both LinkedIn and Instagram from one set of 1080x1350 slides.

    159 GitHub stars~2.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Audience Research

    TheCraigHewitt/skills

    When the user wants to understand their YouTube audience, mine viewer psychology, analyze demographics, or find content-market fit signals.

    159 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Brain Dump

    TheCraigHewitt/skills

    Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work.

    159 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Channel Audit

    TheCraigHewitt/skills

    When the user wants a full YouTube channel health check, growth diagnosis, strategic review, or wants to identify why their channel is stalling.

    159 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Channel Strategy

    TheCraigHewitt/skills

    When the user wants to define or refine their YouTube channel strategy, niche positioning, content pillars, or growth plan.

    159 GitHub stars~2.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Cold Call

    TheCraigHewitt/skills

    When the user wants to write cold call scripts, handle phone objections, plan dial blocks, or craft voicemails.

    159 GitHub stars~5k tokensUpdated 4 mo ago
    Auto-check passed

Questions about One On Ones

What does One On Ones do?

When the user needs to prepare for a 1:1 with a direct report, give feedback to a team member, handle a performance conversation, or says things like '1:1 with,' 'one on one,' 'give feedback to,'…. One On Ones is an agent skill from TheCraigHewitt/skills.' For founder-to-team management, not peer meetings.

When should I use One On Ones?

One On Ones fits situations like: needs to prepare for a 1:1 with a direct report; give feedback to a team member; handle a performance conversation; says things like 1:1 with.

How do I install One On Ones in Claude Code?

Run `npx skills add TheCraigHewitt/skills --skill one-on-ones -a claude-code`. Or copy the skill folder (ceo/one-on-ones in TheCraigHewitt/skills) into .claude/skills/one-on-ones in your project. Claude Code loads it when a task matches its description.

How do I install One On Ones in Codex?

Run `npx skills add TheCraigHewitt/skills --skill one-on-ones -a codex`. Or copy the skill folder (ceo/one-on-ones in TheCraigHewitt/skills) into .agents/skills/one-on-ones in your project. Codex loads it when a task matches its description.

Can I use One On Ones in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheCraigHewitt/skills --skill one-on-ones -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/one-on-ones, .gemini/skills/one-on-ones, .github/skills/one-on-ones and .opencode/skills/one-on-ones in your project.

What does One On Ones need to run?

SKILL.md names no scripts, command-line tools or credentials: One On Ones is instructions for the agent only.

Does One On Ones access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is One On Ones safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does One On Ones use?

One On Ones is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does One On Ones use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to One On Ones?

Skills that share tags, products or a category with One On Ones: Browsing Glassdoor (browsing-skills/browsing-skills, 117 stars), Wp Performance Review (elvismdev/claude-wordpress-skills, 235 stars), Align Human (agentscope-ai/OpenJudge, 871 stars) and Run Mv Hoi Reconstruction (nvidia-isaac/video_to_data, 861 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains One On Ones?

TheCraigHewitt (a GitHub user) maintains it in TheCraigHewitt/skills, which has 159 GitHub stars. The repository holds 65 skills in this directory. The repository was last updated on May 22, 2026.

Source: TheCraigHewitt/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.