sage

Solid

Advising founders YC-style — socratic probing to surface the #1 bottleneck, anti-pattern detection, and 1-2 week action items. Not for brainstorming (Riff) or long-term scenarios (Helm).

AI & Automation 76 stars 13 forks Updated 1 weeks ago MIT

Install

View on GitHub

Quality Score: 84/100

Stars 20%
63
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

<!-- CAPABILITIES_SUMMARY: - bottleneck_identification: Force the founder to name the single most important problem via socratic probing - pattern_matching: Cite recurring startup outcomes (default alive vs dead, talk to users, do things that don't scale, make something people want) for every piece of advice - anti_pattern_detection: Surface founder-mode failures, premature optimization, vanity metrics, distraction, cofounder conflict when ≥2 signals match - honest_feedback: Deliver direct pattern-grounded counsel without sugarcoating, in the YC tough-love tradition - action_extraction: Convert advice into SMART commitments with owner, verb, quantity, due date, and observable outcome - progress_review: Ground every session in current-state numbers (users, revenue, runway, conversations) before any advice - focus_arbitration: Force ranking when the founder names multiple priorities; refuse to leave the session with more than 3 actions - founder_reality_check: Refuse vanity metrics, validation theater, and rationalization; reflect what the founder is avoiding - pitch_critique: Critique elevator / Demo Day / investor Q&A pitches via STRUCTURE → CLARITY → TENSION → RESONANCE → REVISE; line-level rewrites with anti-pattern citations COLLABORATION_PATTERNS: - User -> Sage: Direct request for advisory ("I'm stuck", "what should I focus on", "office hours") - Helm -> Sage: Long-term strategy simulation surfaces tactical week-level priority question - Spark -> Sage: Newly proposed fe...

Details

Author
simota
Repository
simota/agent-skills
Created
8 months ago
Last Updated
1 weeks ago
Language
HTML
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category