Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Executive People

ASecurity

Make executive people decisions about role design, hiring, compensation, performance, retention and organization structure while accounting for human and jurisdiction-specific risk.

3 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsperformance

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add marcmarti9/agentit --skill executive-people --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Executive People?

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

Security grade badge for Executive People
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marcmarti9-executive-people/badge)](https://www.skillsdirectory.com/skills/marcmarti9-executive-people)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: executive-people
description: Make executive people decisions about role design, hiring, compensation, performance, retention and organization structure while accounting for human and jurisdiction-specific risk.
---

# Executive People

Use this skill for hiring, role design, compensation philosophy, performance management, retention, team structure, management capacity and organizational change.

People decisions are business decisions with real human consequences. Give a direct recommendation, but do not reduce people to spreadsheet cells or pretend employment rules are universal.

## Understand the situation

Establish the relevant context:

- company stage and strategy;
- role purpose and expected outcomes;
- level, scope and decision authority;
- current team structure and management load;
- tenure, performance evidence and prior feedback where applicable;
- compensation constraints and market/location;
- hiring urgency versus cost of a bad hire;
- legal/jurisdictional constraints;
- cultural or retention consequences.

Do not infer performance, motivation, protected characteristics or misconduct without evidence.

## Role and organization design

Start with the work the company needs done, then design the role/org around it.

Useful questions:

- What outcomes must this role own?
- Is the gap actually headcount, capability, process or management attention?
- Can responsibilities be simplified before adding a layer?
- Does the role have clear decision rights and interfaces?
- Is a manager carrying too many materially different responsibilities?
- Will a reorg solve a changed strategy/scale problem, or merely redraw boxes?

A management span around 5–8 direct reports is a common reference point, not a law. Complexity, seniority, role homogeneity and operating cadence can justify materially different spans.

## Hiring

For material hires:

1. Define outcomes and scorecard before sourcing.
2. Separate must-have capability from prestige proxies.
3. Assess evidence against the actual work.
4. Check values/behavioral fit without turning “culture fit” into sameness.
5. Model total cost and onboarding time.
6. Define first-30/60/90-day outcomes appropriate to the role.
7. Decide what evidence would make the company stop or reopen the search.

Senior hiring errors can consume months of execution and management attention. Speed matters, but urgency is not a reason to lower the bar invisibly.

## Compensation

Use a coherent philosophy rather than one-off exceptions:

- choose relevant market/location/level benchmarks;
- define bands and internal consistency;
- consider cash/equity/incentive mix and affordability;
- make performance incentives measurable and actually influenceable by the person;
- inspect compression, retention and fairness consequences before exceptions.

Use current compensation data when numbers matter.

## Performance and difficult situations

Distinguish among:

- unclear expectations;
- capability/role mismatch;
- insufficient support/resources;
- inconsistent management;
- sustained underperformance despite clarity/support;
- conduct or values violations.

A performance-improvement plan should be a real improvement path with specific expectations, support, evidence and review dates—not a decorative paper trail. Where termination or formal discipline may be involved, employment-law specifics require jurisdiction-aware professional guidance.

## Retention

Focus on **regretted attrition and critical capability loss**, not raw turnover alone.

Investigate causes with evidence: manager quality, role scope, compensation, growth, workload, mission, team dynamics, location or market pull. Do not default to compensation if the system problem is elsewhere.

## Decision method

1. Define the business outcome and human impact.
2. Diagnose whether the root issue is role, person, process, incentives or structure.
3. Compare realistic options and reversibility.
4. Check legal/jurisdictional and confidentiality boundaries.
5. Recommend the action and communication approach.
6. Define owner, timeline and evidence for review.

Pair with `executive-legal` when employment law, contracts, equity or formal disputes are material; pair with `executive-finance` when headcount/comp economics can change the decision.

## Failure modes

Avoid:

- hiring because everyone is overloaded without fixing a broken process;
- title inflation instead of scope clarity;
- using “culture fit” as an evidence-free rejection;
- surprise performance action after absent feedback;
- reorgs with no changed strategy/scale reason;
- compensation exceptions that silently destroy bands;
- treating legal requirements from one jurisdiction as global.

## Provenance

Original Agentit guidance materially informed by the people/HR specialist design and operating heuristics in Sente Labs' OpenExecutive (Apache-2.0). See `THIRD_PARTY_NOTICES.md`.

Attribution

marcmarti9marcmarti9
View sourceMore from marcmarti9 →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →