Agent skill

Ceos Trust

by bradfeld in bradfeld/ceos

A skill your agent uses when building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox

MITAuto-check passed

Install Ceos Trust

skills CLI
$ npx skills add bradfeld/ceos --skill ceos-trust -a claude-code

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

GitHub CLI
$ gh skill install bradfeld/ceos ceos-trust --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/bradfeld/ceos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ceos-trust .claude/skills/ceos-trust && 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
ceos-trust
GitHub stars
156
Token cost
~6.6k tokens
SKILL.md length
3,313 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox

  • Works in 12 steps: Determine Which Exercise → Check Readiness → Read Participants → …
  • Building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox
  • SKILL.md covers When to Use, Context, Process and Output Format, plus 2 more sections
  • Calls git

What it does

Ceos Trust is an agent skill from bradfeld/ceos. Use when building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox

Its SKILL.md is about 6.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: EOS (Entrepreneurial Operating System) skills for Claude Code. Run your business on EOS with AI. The licence is MIT.

When your agent uses it

  • Building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox

Example prompts

  • “/ceos-trust”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Determine Which Exercise
  2. Check Readiness
  3. Read Participants
  4. Provide Facilitation Guide
  5. Record Outcomes
  6. Save
  7. Load All Records
  8. Build Progression Table
  9. Flag Staleness
  10. Cross-Reference Checkup Trust Score
  11. Load All Records
  12. Display History Table

What it can do on your machine

Read from SKILL.md and the folder at commit bdd5f01. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Ceos Trust loads about 6.6k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 3,313 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~6.6k

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 bradfeld/ceos at commit bdd5f01, republished under its MIT licence (© bradfeld). 3,313 words, ~6,594 tokens.

Download SKILL.mdSave it as .claude/skills/ceos-trust/SKILL.md (or your agent's skills folder).
name
ceos-trust
description
Use when building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox
file-access
data/trust/, templates/trust-exercise.md, data/accountability.md, data/checkups/
tools-used
Read, Write, Glob

ceos-trust

Facilitate the 10 Trust Builder exercises from the EOS Toolbox, progressing from low to high vulnerability. Acts as a facilitation guide — providing instructions, timing, debrief questions, and recording outcomes — rather than trying to replicate exercises digitally. Teams typically do one exercise per quarter, building deeper trust over time. Drawn from Patrick Lencioni's "Five Dysfunctions of a Team" framework.

Not for: People evaluation (use ceos-people), organizational health assessment (use ceos-checkup), or performance conversations (use ceos-quarterly). The Trust Builders are team-level exercises focused on vulnerability-based trust, not individual assessment.

When to Use

  • "Build team trust" or "trust building exercise"
  • "Run the next trust exercise" or "facilitate trust builders"
  • "What trust exercise is next?" or "trust exercise schedule"
  • "Show trust exercise history" or "review trust progression"
  • "Personal histories exercise" or any specific exercise name
  • "How is our team trust?" or "trust level check"
  • "Quarterly trust exercise" or "team bonding exercise"
  • Any discussion about vulnerability-based trust, team bonding, or the EOS Trust Builders

Context

Finding the CEOS Repository

Search upward from the current directory for the .ceos marker file. This file marks the root of the CEOS repository.

If .ceos is not found, stop and tell the user: "Not in a CEOS repository. Clone your CEOS repo and run setup.sh first."

Sync before use: Once you find the CEOS root, run git -C <ceos_root> pull --ff-only --quiet 2>/dev/null to get the latest data from teammates. If it fails (conflict or offline), continue silently with local data.

Key Files
FilePurpose
data/trust/Exercise records — one file per completed exercise
templates/trust-exercise.mdTemplate for recording exercise outcomes
data/accountability.mdTeam composition for participant suggestions (read-only — use ceos-accountability to modify)
data/checkups/Organizational Checkup scores for trust cross-reference (read-only — use ceos-checkup to modify)
The 10 Exercises
#ExerciseVulnerabilityTime BoxDescription
1Personal HistoriesLow30-45 minEach team member shares personal background (hometown, family, first job, hobbies)
2DISC/Kolbe ProfilesLow45-60 minShare and discuss personality/working style assessment results
3Lifeline ExerciseMedium45-60 minMap significant life events on a timeline, share with the team
4One ThingMedium20-30 minEach person shares one thing the team doesn't know about them
5Feedback RoundMedium45-60 minStructured positive and constructive feedback for each team member
6Strengths SpotlightMedium30-45 minEach person identifies their top strengths, team validates and adds
7Conflict NormsMedium-High45-60 minEstablish how the team will handle disagreement and conflict
8Accountability PartnersMedium-High30-45 minPair up for mutual accountability check-ins between meetings
9Team Effectiveness DebriefHigh60-90 minRate and discuss how the team works together as a unit
10Vulnerability CircleHigh30-60 minShare a current struggle, fear, or area where you need help
Vulnerability Levels
LevelExercisesWhat It Means
Low1-2Safe sharing — factual information, low personal risk
Medium3-6Personal sharing with moderate risk — life events, feedback, strengths
Medium-High7-8Navigating conflict and accountability — requires existing trust
High9-10Deep vulnerability — honest assessment of team and personal struggles
Exercise Record Format

Each completed exercise is a markdown file at data/trust/YYYY-MM-DD-exercise-slug.md with YAML frontmatter:

yaml
date: "2026-02-16"
exercise_number: 1
exercise_name: "Personal Histories"
participants: ["Brad Feld", "Daniel"]
facilitator: "Brad Feld"
duration_minutes: 35
vulnerability_level: low
status: complete

File naming: YYYY-MM-DD-exercise-slug.md — date prefix for chronological ordering, exercise slug identifies the type.

Exercise Slug Reference
#ExerciseSlug
1Personal Historiespersonal-histories
2DISC/Kolbe Profilesdisc-kolbe-profiles
3Lifeline Exerciselifeline-exercise
4One Thingone-thing
5Feedback Roundfeedback-round
6Strengths Spotlightstrengths-spotlight
7Conflict Normsconflict-norms
8Accountability Partnersaccountability-partners
9Team Effectiveness Debriefteam-effectiveness-debrief
10Vulnerability Circlevulnerability-circle

Process

Mode: Facilitate

Use when guiding the team through the next Trust Builder exercise. This is the primary mode — one exercise per session.

Step 1: Determine Which Exercise

Read all files from data/trust/ via Glob("data/trust/*.md"). Parse YAML frontmatter to find completed exercises by exercise_number.

Determine the next exercise in sequence (lowest number not yet completed).

  • No exercises completed: Start with #1 Personal Histories.
  • Some completed: Recommend the next in sequence.
  • All 10 completed: "All 10 Trust Builder exercises are complete! Consider starting Cycle 2 — repeating exercises builds deeper trust each time. Recommend starting again with #1 Personal Histories."

Display the recommendation:

Next Trust Builder: #N [Name]
Vulnerability level: [low/medium/high]
Time box: [N-N] minutes
Last exercise: #[N-1] [Name] on [date]

Ready to facilitate?
Step 2: Check Readiness

For medium or higher vulnerability exercises (3+): "This is a [level]-vulnerability exercise. Ensure the team has completed the earlier exercises and the environment feels psychologically safe."

For exercise #2 (DISC/Kolbe Profiles): "Note: Participants should have completed their DISC and/or Kolbe assessments before this exercise. Has everyone taken their assessments?"

For exercise #5 (Feedback Round): "Note: This exercise involves giving and receiving direct feedback. Remind the team that feedback should be specific, actionable, and delivered with positive intent."

For exercise #7+ (Medium-High and High): "This exercise requires a foundation of trust from earlier exercises. If the team hasn't built that foundation, consider revisiting exercises 1-6 first."

Step 3: Read Participants

Read data/accountability.md to identify leadership team members. Suggest them as participants.

"Who is participating? (Default: leadership team from Accountability Chart)"

Allow the user to confirm or modify the participant list.

Step 4: Provide Facilitation Guide

Display the exercise-specific facilitation guide based on the exercise number. Each exercise follows this structure:

Purpose → Setup → Steps → Time Management → Debrief Questions


Exercise 1: Personal Histories

Purpose: Break down barriers by sharing personal backgrounds. This is the foundation — it humanizes teammates beyond their work roles.

Setup: Gather the team in a comfortable setting. No notes needed. Go around the table.

Steps:

  1. Each person shares (3-5 minutes per person):
    • Where did you grow up?
    • How many siblings do you have?
    • What was your first job?
    • What's a unique hobby or interest?
    • What's something most people don't know about you?
  2. After each person shares, allow brief reactions (no extended discussion)
  3. Complete the full round before moving to debrief

Time Management: 3-5 min per person + 10 min debrief. For a team of 6: ~40 minutes total.

Debrief Questions:

  1. What surprised you about someone's background?
  2. Did you discover something in common with a teammate?
  3. How does knowing this personal context change how you might work together?

Exercise 2: DISC/Kolbe Profiles

Purpose: Understand each other's working styles to improve communication and reduce friction.

Setup: All participants must have completed their DISC and/or Kolbe assessments beforehand. Print or display results.

Steps:

  1. Each person shares their profile (3-5 minutes):
    • Their dominant DISC style (D, I, S, or C)
    • Their Kolbe MO (if available)
    • "Here's what this means about how I work best..."
    • "Here's what might frustrate me or slow me down..."
  2. After all have shared, discuss as a team:
    • Where do profiles complement each other?
    • Where might profiles clash?
    • What accommodations could help?

Time Management: 5 min per person + 15-20 min group discussion.

Debrief Questions:

  1. Which profile differences explain past friction?
  2. How can we use this knowledge to communicate better?
  3. What's one thing you'll do differently knowing your teammates' styles?

Exercise 3: Lifeline Exercise

Purpose: Build deeper understanding by sharing the significant events that shaped who you are.

Setup: Give each person a blank piece of paper. Draw a horizontal line (the lifeline) from birth to present. Mark significant events above the line (positive) and below the line (negative/challenging).

Steps:

  1. Silent preparation (5-10 minutes): Each person maps their lifeline
  2. Each person presents their lifeline (5-8 minutes):
    • Walk through the major events chronologically
    • Explain why each event was significant
    • Share how it shaped who you are today
  3. After each presentation, team members may ask one clarifying question (optional)
  4. No judgment, no advice — just listening

Time Management: 10 min prep + 8 min per person + 10 min debrief.

Debrief Questions:

  1. What common themes did you notice across lifelines?
  2. How does understanding someone's life journey affect your empathy for them?
  3. What did it feel like to share? What did it feel like to listen?

Exercise 4: One Thing

Purpose: A quick exercise to build on existing trust by sharing something new and personal.

Setup: Simple round-table format. No preparation needed.

Steps:

  1. Each person shares one thing the team doesn't know about them (2-3 minutes each)
    • Can be personal, professional, quirky, or meaningful
    • The "one thing" should feel slightly vulnerable — beyond surface-level facts
  2. Brief reactions allowed after each share
  3. Keep it light but genuine

Time Management: 3 min per person + 5 min debrief.

Debrief Questions:

  1. What was the hardest part about choosing your "one thing"?
  2. Did anyone's share change your perception of them?
  3. What does this exercise tell you about the team's comfort level?

Exercise 5: Feedback Round

Purpose: Practice giving and receiving honest feedback in a structured, safe format.

Setup: Each person will give feedback to every other team member. Prepare by thinking about one strength and one area for growth per person.

Steps:

  1. Go person by person — one person is the "focus" at a time
  2. Each team member shares for the focus person:
    • "Your greatest strength that helps the team is..."
    • "One area where I think you could grow is..."
  3. The focus person listens without responding (except to say "thank you")
  4. After all feedback is given, the focus person may ask ONE clarifying question
  5. Move to the next focus person

Time Management: For a team of N, each round takes ~3 min × (N-1) people giving feedback + 2 min transition. Total: roughly 5-8 min per focus person.

Debrief Questions:

  1. What feedback surprised you the most?
  2. Was it harder to give or receive feedback?
  3. What's one piece of feedback you want to act on this quarter?
  4. How can we make giving feedback a more regular practice?

Exercise 6: Strengths Spotlight

Purpose: Reinforce what each person does best and ensure the team leverages individual strengths.

Setup: Each person prepares a list of their top 3-5 personal strengths before the session.

Steps:

  1. Each person presents their self-identified strengths (2-3 minutes)
  2. Team members respond:
    • Validate: "I agree — I see that strength when you..."
    • Add: "I'd also add [strength] because..."
    • Reframe: "I'd describe it slightly differently as..."
  3. Record the final agreed-upon strengths list for each person

Time Management: 5-7 min per person + 10 min debrief.

Debrief Questions:

  1. Were your self-identified strengths aligned with how the team sees you?
  2. What strength did a teammate identify that you hadn't considered?
  3. How can we better leverage each person's strengths in our daily work?

Exercise 7: Conflict Norms

Purpose: Establish explicit agreements for how the team will handle disagreement, preventing unhealthy conflict patterns.

Setup: Whiteboard or shared document. This is a group discussion, not individual sharing.

Steps:

  1. Discuss current conflict patterns (10-15 minutes):
    • "When we disagree, what typically happens?"
    • "What works well about how we handle conflict?"
    • "What doesn't work?"
  2. Brainstorm conflict norms (15-20 minutes):
    • How do we raise disagreements? (In the room, not in the hallway)
    • How do we ensure everyone speaks? (Round-table before open discussion)
    • How do we resolve impasses? (Leader decides after hearing all views)
    • What's off-limits? (Personal attacks, relitigating decided issues)
  3. Agree on 5-7 specific norms (10-15 minutes)
  4. Write them down — these become the team's conflict agreement

Time Management: 45-60 minutes for the full exercise.

Debrief Questions:

  1. Which norm will be hardest for the team to follow?
  2. What will we do when someone breaks a norm?
  3. How will we revisit these norms to make sure they're working?

Exercise 8: Accountability Partners

Purpose: Create peer-to-peer accountability relationships that supplement the formal meeting structure.

Setup: Pair team members. Consider pairing people who don't work closely together or who have complementary strengths.

Steps:

  1. Discuss the concept (5 minutes): Accountability partners check in between L10s to help each other stay on track with Rocks, To-Dos, and personal development
  2. Form pairs (5-10 minutes): Each pair commits to:
    • A weekly 15-minute check-in (phone, video, or in-person)
    • What they'll cover: Rock progress, To-Do completion, one personal goal
    • How they'll hold each other accountable (direct, constructive)
  3. Each pair shares their plan with the team (2-3 minutes per pair)
  4. Set a review date (e.g., end of quarter) to assess whether the partnerships are working

Time Management: 30-45 minutes total.

Debrief Questions:

  1. What do you hope to get from your accountability partner?
  2. What makes you nervous about this level of accountability?
  3. How will you handle it if your partner isn't following through?

Exercise 9: Team Effectiveness Debrief

Purpose: Honestly assess how the team functions as a unit — what's working, what isn't, and what needs to change.

Setup: Each person independently rates the team on 5 dimensions (1-5 scale) before the session:

  1. Trust — Do we feel safe being vulnerable?
  2. Conflict — Do we engage in productive disagreement?
  3. Commitment — Do we align behind decisions?
  4. Accountability — Do we hold each other to standards?
  5. Results — Are we focused on collective outcomes?

(These map to Lencioni's Five Dysfunctions pyramid.)

Steps:

  1. Share individual ratings (go around, no discussion yet) — 10 minutes
  2. Identify the biggest gaps (where ratings diverge most) — 10 minutes
  3. Deep-dive on the lowest-scoring dimension:
    • What specific behaviors drive the low score?
    • What would a "5" look like?
    • What's one thing we could change this quarter?
  4. Repeat for the second-lowest dimension if time allows
  5. Agree on 2-3 team commitments

Time Management: 60-90 minutes. This is the most substantive exercise.

Debrief Questions:

  1. Were you surprised by anyone else's ratings?
  2. Which dimension do you personally need to work on most?
  3. What's the single most important thing we can improve as a team?
  4. How will we measure whether we've improved by next quarter?

Exercise 10: Vulnerability Circle

Purpose: The deepest trust exercise — each person shares a current struggle, fear, or area where they need support.

Setup: This exercise requires strong existing trust. Ensure exercises 1-9 have been completed. Set the tone: "This is a safe space. What's shared here stays here. Our only job is to listen and support."

Steps:

  1. Set ground rules (5 minutes):
    • No fixing, no advice (unless asked)
    • No judgment
    • Confidentiality — nothing leaves this room
    • It's OK to pass (but encouragement to try)
  2. Each person shares (5-8 minutes):
    • "The thing I'm struggling with most right now is..."
    • "What I'm most afraid of is..."
    • "Where I need help from this team is..."
  3. After each share, the team responds:
    • Brief acknowledgment: "Thank you for sharing that"
    • One supportive statement (optional): "I relate because..." or "I want you to know..."
  4. Complete the full circle before debrief

Time Management: 5-8 min per person + 15 min debrief. For a team of 6: ~50-60 minutes.

Debrief Questions:

  1. How did it feel to share at this level?
  2. What did you learn about the team's capacity for support?
  3. How has our trust level changed from Exercise 1 to now?
  4. What do we want to commit to as a team going forward?

Show full SKILL.md (866 more words)Show less
Step 5: Record Outcomes

After the exercise is complete, ask the user for:

  1. Key takeaways: "What were the main insights or outcomes from this exercise?" (3-5 bullet points)
  2. Facilitation notes: "How did the exercise go? Any observations about the process?"
  3. Debrief notes: "How did the debrief discussion go?"
  4. Follow-up actions: "Any action items that came out of this?" (optional)
  5. Duration: "How long did the exercise take?"

Create a new file from templates/trust-exercise.md at data/trust/YYYY-MM-DD-exercise-slug.md. Fill in all frontmatter fields and body sections.

Step 6: Save

Show the complete file before writing. Ask: "Save this trust exercise record?"

After saving, display:

Exercise #N [Name] complete!

Progression: N/10 exercises completed
Next: #[N+1] [Name] ([vulnerability level])
Recommended timing: Next quarter (~90 days)

Trust exercises build on each other. The next exercise
will go deeper — schedule it for your next quarterly session.

Mode: Schedule

Use when checking which exercises have been completed, what's next, and whether the team is on cadence.

Step 1: Load All Records

Read all files from data/trust/ via Glob("data/trust/*.md"). Parse YAML frontmatter.

If no files exist: "No trust exercises recorded yet. Start with Exercise #1: Personal Histories using Facilitate mode."

Step 2: Build Progression Table
Trust Builders — Progression
━━━━━━━━━━━━━━━━━━━━━━━━━━━

| # | Exercise | Level | Status | Date | Participants |
|---|----------|-------|--------|------|-------------|
| 1 | Personal Histories | Low | ✓ Done | 2026-01-15 | Brad, Daniel |
| 2 | DISC/Kolbe Profiles | Low | ✓ Done | 2026-04-10 | Brad, Daniel |
| 3 | Lifeline Exercise | Medium | → Next | — | — |
| 4 | One Thing | Medium | Pending | — | — |
| ... | ... | ... | ... | ... | ... |
| 10 | Vulnerability Circle | High | Pending | — | — |

Progress: 2/10 exercises (20%)
██████░░░░░░░░░░░░░░░░░░ 20%
Step 3: Flag Staleness

Calculate days since most recent exercise.

  • > 120 days: "⚠️ [N] days since last trust exercise. Recommended cadence is quarterly (~90 days). Consider scheduling the next exercise."
  • 90-120 days: "The next trust exercise is due soon — last one was [N] days ago."
  • < 90 days: No flag.
Step 4: Cross-Reference Checkup Trust Score

Optionally read data/checkups/ for the most recent organizational checkup. Look for Question 11 score (leadership trust question).

  • Score < 3.0: "📊 Checkup Question 11 (leadership trust) scored [X]/5. The Trust Builders exercises can help improve this. Consider prioritizing the next exercise."
  • Score ≥ 3.0: Mention the score but no urgent recommendation.

If no checkup data exists, skip this step silently.


Mode: Review

Use when reviewing the history of trust exercises — dates, participants, key takeaways, and progression over time.

Step 1: Load All Records

Read all files from data/trust/ via Glob("data/trust/*.md"). Parse YAML frontmatter.

If no files exist: "No trust exercises recorded yet. Start with Exercise #1: Personal Histories using Facilitate mode."

Step 2: Display History Table

Show all completed exercises chronologically:

Trust Builders — Exercise History
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| Date | # | Exercise | Level | Duration | Participants | Key Takeaway |
|------|---|----------|-------|----------|-------------|-------------|
| 2026-01-15 | 1 | Personal Histories | Low | 35 min | Brad, Daniel | Discovered shared background in... |
| 2026-04-10 | 2 | DISC/Kolbe Profiles | Low | 50 min | Brad, Daniel | Brad is high-D, Daniel is high-I... |
Step 3: Show Progression Summary
Progression Summary:
  Completed: N/10 exercises
  Current cycle: 1 (exercises 1-10)
  Exercises by vulnerability level:
    Low (1-2): N completed
    Medium (3-6): N completed
    Medium-High (7-8): N completed
    High (9-10): N completed
  Avg time between exercises: [N] days
  Total time invested: [N] minutes across [N] exercises
Step 4: Show Cycle Status

If all 10 exercises are complete:

🎉 Cycle 1 Complete!

All 10 Trust Builder exercises have been completed.
Consider starting Cycle 2 — repeating exercises builds deeper trust.
Many teams report that exercises hit differently the second time around,
especially as the team evolves and new members join.

If the team has completed multiple cycles, show cycle-over-cycle comparison.

Step 5: Drill Down

Ask: "Want to view the full record for a specific exercise?"

If yes, read and display the complete file for the requested exercise.

Output Format

Facilitate: Exercise-specific facilitation guide with purpose, setup, steps, time management, and debrief questions. Outcome record shown before save. Post-exercise summary with next exercise recommendation.

Schedule: Progression table showing all 10 exercises with completion status, staleness warnings, and checkup trust score cross-reference. Visual progress bar.

Review: Chronological history table with dates, exercises, levels, durations, and key takeaways. Progression summary by vulnerability level. Cycle status.

Guardrails

  • Always show the complete file before writing. Never save an exercise record without displaying it and getting approval.
  • Don't auto-invoke other skills. When trust results suggest running a checkup or updating people evaluations, mention the option but let the user decide. Say "Would you like to run an organizational checkup?" rather than doing it automatically.
  • Sensitive data warning. On first use in a session, remind the user: "Trust exercise records contain personal sharing and vulnerability-based feedback. This repo should be private."
  • Respect the vulnerability progression. Do not recommend skipping ahead to high-vulnerability exercises if earlier exercises haven't been completed. If the team attempts exercise 7+ without completing 1-6, warn: "Exercises 7-10 require a foundation of trust from earlier exercises. Consider completing exercises [missing numbers] first."
  • Facilitation guide, not digital exercise. The skill provides instructions and records outcomes — the actual exercises happen in person or in a live meeting. Don't try to simulate the exercises by asking participants to type their responses.
  • Don't pressure sharing. The exercises involve vulnerability. If a participant wants to pass, that's acceptable. Note it in the record but don't push.
  • One exercise per session. Each facilitation session covers one exercise. Don't try to run multiple exercises in sequence — each needs time to land emotionally.
  • Confidentiality reminder. For exercises 7+ (medium-high and high vulnerability), remind the team: "What's shared in this exercise stays within the team."

Integration Notes

Accountability Chart (ceos-accountability)
  • Direction: Read
  • What data: data/accountability.md — seat names, owners, team members
  • Purpose: Identifies leadership team members for participant suggestions during Facilitate mode. The accountability chart defines who should be in the room for trust exercises.
Organizational Checkup (ceos-checkup)
  • Direction: Read
  • What data: data/checkups/ — organizational health assessment scores
  • Purpose: Question 11 in the checkup measures leadership team trust. Low scores (< 3.0) suggest prioritizing Trust Builder exercises. Schedule mode cross-references the most recent checkup trust score.
Annual Planning (ceos-annual)
  • Direction: Related
  • What data: No direct data access
  • Purpose: Annual planning sessions often include a review of team trust and may trigger scheduling the next Trust Builder exercise. The trust exercise progression can inform annual planning discussions about team health.
Quarterly Planning (ceos-quarterly-planning)
  • Direction: Related
  • What data: No direct data access
  • Purpose: The quarterly cadence of trust exercises aligns naturally with quarterly planning. Review trust progression as part of the quarterly planning agenda. Schedule the next exercise if overdue.
Write Principle

Only ceos-trust writes to data/trust/. Other skills may reference trust exercise data for team health context, but do not modify exercise records.

© bradfeld, 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 skills/ceos-trust of bradfeld/ceos.

Open the folder on GitHubat commit bdd5f01

Compare with similar skills

Ceos Trust 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.

Ceos Trust compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ceos Trust this skillbradfeld/ceos156—~6.6kAutomated safety check: PassMIT
Vulnerability Scanningsickn33/agentic-awesome-skills47k1 repos~2.8kAutomated safety check: PassMIT
Performing Vulnerability Scanning With Nessusmukul975/Anthropic-Cybersecurity-Skills34k—~2.8kAutomated safety check: PassApache-2.0
Building Vulnerability Scanning Workflowmukul975/Anthropic-Cybersecurity-Skills34k—~3.2kAutomated safety check: PassApache-2.0
Performing Ot Vulnerability Assessment With Clarotymukul975/Anthropic-Cybersecurity-Skills34k—~3.1kAutomated safety check: PassApache-2.0
Cra Vulnerability Obligationsdavila7/claude-code-templates32k1 repos~4.5kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Vulnerability Scanning

    sickn33/agentic-awesome-skills

    Scan systems and dependencies for CVEs and security vulnerabilities.

    47k GitHub starsUsed in 1 repo~2.8k tokens
    SecurityAuto-check passed
  • Performing Vulnerability Scanning With Nessus

    mukul975/Anthropic-Cybersecurity-Skills

    Performs authenticated and unauthenticated vulnerability scanning using Tenable Nessus to identify known vulnerabilities, misconfigurations, default credentials, and missing patches across network…

    34k GitHub stars~2.8k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Building Vulnerability Scanning Workflow

    mukul975/Anthropic-Cybersecurity-Skills

    Builds a structured vulnerability scanning workflow using tools like Nessus, Qualys, and OpenVAS to discover, prioritize, and track remediation of security vulnerabilities across infrastructure.

    34k GitHub stars~3.2k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Performing Ot Vulnerability Assessment With Claroty

    mukul975/Anthropic-Cybersecurity-Skills

    Perform OT vulnerability assessments using the Claroty xDome platform for asset discovery, risk scoring, and vulnerability correlation, combining passive traffic-based identification and active safe…

    34k GitHub stars~3.1k tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Cra Vulnerability Obligations

    davila7/claude-code-templates

    A skill your agent uses when a user asks what the EU Cyber Resilience Act (CRA) means for their product, whether and when they must report a vulnerability or incident, or what a specific CVE…

    32k GitHub starsUsed in 1 repo~4.5k tokens
    SecurityAuto-check passed
  • Gathers security findings from Dependabot, GCP container scanning, Docker Scout and Linear security issues, then triages and remediates them across Warp's repos and images.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    SecurityAuto-check passed

More from bradfeld/ceos

All 23 skills in this repo
  • Ceos Accountability

    bradfeld/ceos

    A skill your agent uses when viewing, updating, or auditing the Accountability Chart — seats, owners, and roles

    156 GitHub stars~3.4k tokensUpdated 26 days ago
    Auto-check passed
  • Ceos Assistance

    bradfeld/ceos

    A skill your agent uses when managing daily operational delegation through The Stack and structured leader-assistant standups

    156 GitHub stars~3.9k tokensUpdated 26 days ago
    Auto-check passed
  • Ceos Calendar

    bradfeld/ceos

    A skill your agent uses when managing the rolling market calendar - conferences, launches, fundraising milestones, partner events, and team constraints

    156 GitHub stars~2k tokensUpdated 26 days ago
    Auto-check passed
  • Ceos Cashflow

    bradfeld/ceos

    A skill your agent uses when assessing and optimizing the 8 financial levers that drive cash flow and profitability

    156 GitHub stars~3.2k tokensUpdated 26 days ago
    Auto-check passed
  • Ceos Clarity

    bradfeld/ceos

    A skill your agent uses when taking a Clarity Break — stepping back from day-to-day work for strategic thinking time

    156 GitHub stars~3k tokensUpdated 26 days ago
    Auto-check passed
  • Ceos Dashboard

    bradfeld/ceos

    A skill your agent uses when you want a quick snapshot of overall business health across all EOS components

    156 GitHub stars~3.2k tokensUpdated 26 days ago
    Auto-check passed

Questions about Ceos Trust

What does Ceos Trust do?

A skill your agent uses when building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox. Ceos Trust is an agent skill from bradfeld/ceos.

When should I use Ceos Trust?

Ceos Trust fits situations like: building vulnerability-based trust through quarterly team exercises from the EOS Trust Builders toolbox.

How do I install Ceos Trust in Claude Code?

Run `npx skills add bradfeld/ceos --skill ceos-trust -a claude-code`. Or copy the skill folder (skills/ceos-trust in bradfeld/ceos) into .claude/skills/ceos-trust in your project. Claude Code loads it when a task matches its description.

How do I install Ceos Trust in Codex?

Run `npx skills add bradfeld/ceos --skill ceos-trust -a codex`. Or copy the skill folder (skills/ceos-trust in bradfeld/ceos) into .agents/skills/ceos-trust in your project. Codex loads it when a task matches its description.

Can I use Ceos Trust 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 bradfeld/ceos --skill ceos-trust -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ceos-trust, .gemini/skills/ceos-trust, .github/skills/ceos-trust and .opencode/skills/ceos-trust in your project.

What does Ceos Trust need to run?

Going by SKILL.md and its folder, Ceos Trust needs the command-line tools its instructions call (git).

Does Ceos Trust access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Ceos Trust 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 Ceos Trust use?

Ceos Trust 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 Ceos Trust use?

About 6.6k tokens (SKILL.md is roughly 26k 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 Ceos Trust?

Skills that share tags, products or a category with Ceos Trust: Vulnerability Scanning (sickn33/agentic-awesome-skills, 47k stars), Performing Vulnerability Scanning With Nessus (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Building Vulnerability Scanning Workflow (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Performing Ot Vulnerability Assessment With Claroty (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ceos Trust?

bradfeld (a GitHub user) maintains it in bradfeld/ceos, which has 156 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on September 13, 2026.

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