CtrlK
BlogDocsLog inGet started
Tessl Logo

executive-mentor

Adversarial thinking partner for founders and executives. Stress-tests plans, prepares for brutal board meetings, dissects decisions with no good options, and forces honest post-mortems. Use when you need someone to find the holes before the board does, make a decision you've been avoiding, or understand what actually went wrong.

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/executive-mentor/SKILL.md

The canonical home for this skill is executive-mentor in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable advisory skill with a clear quality-loop workflow, weakened by anecdotal padding and by references to bundle/sibling files that are not actually present in the package.

Suggestions

Trim the Andy Grove/Ben Horowitz anecdote and the 'The Difference'/'What This Isn't' framing sections to tighten conciseness without losing the voice.

Either include the referenced files (references/hard_things.md, scripts/decision_matrix_scorer.py, agents/devils-advocate.md, etc.) in the bundle or drop the references, so navigation is not broken.

Pull the essential execution detail currently deferred to sibling skills (../challenge/SKILL.md, ../board-prep/SKILL.md) into inline summaries so the skill stands alone when those siblings are unavailable.

DimensionReasoningScore

Conciseness

Mostly efficient, but narrative padding Claude doesn't need ('Andy Grove ran Intel through the memory chip crisis...', 'Ben Horowitz fired his best friend') and redundant framing sections ('The Difference', 'What This Isn't') could be trimmed without losing meaning.

3 / 5

Actionability

Concrete commands (`python scripts/decision_matrix_scorer.py`), a command table, sample questions, and a procedural Reasoning Technique ('Find the three most likely failure modes... earliest warning signal and the cheapest hedge') give mostly executable guidance, though deep execution detail is deferred to sibling skills.

4 / 5

Workflow Clarity

The Internal Quality Loop (Self-verify → Peer-verify → Critic pre-screen → output format) and the adversarial reasoning sequence provide a clear, checkpointed flow with only minor validation gaps; no destructive/batch operation triggers the cap.

4 / 5

Progressive Disclosure

References are well-signaled and one level deep in an 'Agents & References' section, but the referenced bundle files (references/hard_things.md, scripts/decision_matrix_scorer.py, agents/devils-advocate.md) do not exist in the bundle, so navigation breaks in practice.

3 / 5

Total

14

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with clear what/when structure and concrete trigger phrases; its only real weakness is second-person voice in the 'Use when' clause, which costs it a specificity point and leaves a few natural synonyms out.

DimensionReasoningScore

Specificity

Lists four concrete actions ('Stress-tests plans, prepares for brutal board meetings, dissects decisions with no good options, and forces honest post-mortems'), which would be a 5, but the second-person 'Use when you need...' clause triggers the voice penalty reducing specificity by 1.

4 / 5

Completeness

Explicitly answers both what ('Adversarial thinking partner... Stress-tests plans, prepares... post-mortems') and when ('Use when you need someone to find the holes before the board does, make a decision you've been avoiding, or understand what actually went wrong') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases like 'board meetings', 'a decision you've been avoiding', and 'what actually went wrong' map to things users say, but a few obvious synonyms (e.g. 'pre-mortem', 'devil's advocate') live only in the body, not the description.

4 / 5

Distinctiveness Conflict Risk

The 'adversarial thinking partner for founders and executives' niche is clearly framed and the triggers are distinctive, but it overlaps with general coaching/advisor skills closely enough to keep it just below a 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.