CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

office-hours

/c-level-agents:office-hours [topic] — YC-style 6-question founder interrogation before any advice. Forces clarity on problem, customer, distribution, defensibility, capital, and founder fit. Use when a founder question is too vague to route — e.g. 'should we grow faster?' — or before drafting a strategy brief.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The body delivers fully actionable, well-sequenced guidance with copy-paste output formats and explicit validation gates, and it is appropriately self-contained. Its single weakness is token efficiency: the 'Why This Works' section and a few philosophical asides restate knowledge Claude already has.

Suggestions

Cut or compress the 'Why This Works' section — the framing-failure rationale ('Most bad decisions don't fail at execution — they fail at framing') and the YC-pattern attribution are context Claude already has; one sentence or nothing is needed.

Trim philosophical evaluation asides that don't change behavior, e.g. 'Founder-market fit is the strongest predictor of survival' and 'If the answer is mercenary, the company will be too', keeping only the actionable criteria ('If you can't name one, the ICP isn't ready').

DimensionReasoningScore

Conciseness

The body is mostly lean, but the 'Why This Works' section explains framing/solutionism reasoning Claude already knows ('Most bad decisions don't fail at execution — they fail at framing') and philosophical asides like 'Founder-market fit is the strongest predictor of survival' add padding. This matches anchor 3 — efficient with some unnecessary explanation that could be trimmed — rather than anchor 4's 'minor instances'.

3 / 5

Actionability

Every question is given exact wording plus per-question evaluation criteria ('‘We’ll execute better’ is not a defense'), the output is a copy-paste-ready brief template with a GREEN/YELLOW/RED assessment scale, and routing rules are explicit. For an instruction-only skill this is fully executable guidance covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

The sequence is clear — trigger conditions, founder answers all six in writing before any C-role weighs in, brief produced, then gated routing — with an explicit validation gate (GREEN required before routing) and a feedback loop (YELLOW → 'sharpen Q[N] before proceeding'; RED → 'kill or redefine'). No destructive or batch operations, so the validation cap does not apply.

5 / 5

Progressive Disclosure

This is a self-contained single-file skill with no bundle files; nothing in the body clearly belongs in a separate file, and sections are well-organized and easy to navigate. Cross-references to sibling commands are clearly signaled in dedicated 'Related Commands' and 'Routing' sections, matching the simple-skill pattern where good organization alone earns a 5.

5 / 5

Total

18

/

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.

The description is strong: it states a specific capability, explicitly covers all six interrogation areas, and includes a well-formed 'Use when' clause with a concrete example trigger phrase. Its only weaknesses are minor — a slightly richer synonym set for triggers and a small overlap with the sibling brief command.

DimensionReasoningScore

Specificity

Names the domain ('YC-style 6 question founder interrogation before any advice') and enumerates concrete coverage across 'problem, customer, distribution, defensibility, capital, and founder fit'. It is one action with six named facets rather than multiple discrete actions, matching anchor 4 rather than 5, and is clearly above the 1-2 concrete actions of anchor 3.

4 / 5

Completeness

It explicitly answers what ('YC-style 6 question founder interrogation before any advice. Forces clarity on problem, customer, distribution, defensibility, capital, and founder fit') and when ('Use when a founder question is too vague to route — e.g. ‘should we grow faster?’ — or before drafting a strategy brief') with a concrete trigger example, matching the anchor-5 example exactly.

5 / 5

Trigger Term Quality

'Use when a founder question is too vague to route — e.g. ‘should we grow faster?’ — or before drafting a strategy brief' provides natural phrases a user would actually say, including a verbatim example utterance. Coverage is good but misses common variations like 'office hours', 'startup advice', or 'pitch feedback', so it falls short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (founder interrogation gate before strategy work) with distinct triggers that are unlikely to fire for unrelated skills. Minor overlap risk exists with the sibling '/c-level-agents:brief' command via the 'before drafting a strategy brief' trigger, placing it at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alirezarezvani/claude-skills

Path

c-level-agents/skills/office-hours/SKILL.md

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.