One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Dragoon0xSkillDragoon0x/product-skills/skills/product-sense/quality-judgment/SKILL.md
Know when something is good enough to ship and when it needs more work. Covers quality bars, the difference between polish and perfection, and making the ship-or-hold decision. Use when debating whether to ship, setting quality standards for the team, or when quality is inconsistent across releases.
Dragoon0xSkillDragoon0x/product-skills/skills/product-sense/trade-off-evaluation/SKILL.md
Make product trade-offs explicitly and defend them clearly. Covers scope vs. quality, speed vs. polish, and knowing what to sacrifice without destroying value. Use when facing competing priorities, deciding what to cut, or when stakeholders want everything without acknowledging constraints.
Dragoon0xSkillDragoon0x/product-skills/skills/product-sense/ux-intuition/SKILL.md
Develop the instinct for what makes a product feel right, beyond what data can tell you. Covers quality evaluation, interaction judgment, and knowing when something is off even if you can't articulate why. Use when evaluating designs, reviewing prototypes, or when metrics say it's fine but something feels wrong.
Dragoon0xSkillDragoon0x/product-skills/skills/research/feedback-synthesis/SKILL.md
Turn raw user feedback into actionable product decisions. Categorization frameworks, signal vs noise filtering, and severity scoring. Use when processing interviews, support tickets, or reviews into product direction.
Dragoon0xSkillDragoon0x/product-skills/skills/research/jobs-to-be-done/SKILL.md
Understand what people actually hire your product to do. Maps functional, emotional, and social jobs. Surfaces real competition and generates interview frameworks. Use when product direction feels unclear or when features aren't landing.
Dragoon0xSkillDragoon0x/product-skills/skills/research/persona-mapping/SKILL.md
Build user models that actually inform decisions. Maps motivations, friction points, and decision triggers beyond demographic templates. Use when building for multiple user types or when the agent needs to reason about different users.
Dragoon0xSkillDragoon0x/product-skills/skills/research/user-psychology/SKILL.md
Apply motivation, friction, and trust patterns to product decisions. Maps cognitive biases and behavioral triggers to specific UI and copy choices. Use when reviewing flows for drop-off points or when something feels right but doesn't convert.
Dragoon0xSkillDragoon0x/product-skills/skills/retention-activation/aha-moment-mapping/SKILL.md
Identify the moment when a new user first experiences your product's core value. Maps the path from signup to that moment and removes friction in between. Use when new user retention is poor, redesigning onboarding, or when the product has strong acquisition but weak activation.
Dragoon0xSkillDragoon0x/product-skills/skills/retention-activation/churn-signal-identification/SKILL.md
Identify behavioral, usage, and contextual signals that predict a customer is about to leave — before they cancel. Build an early warning system, not a postmortem. Use when churn is too high, building health scores, or designing proactive retention interventions.
Dragoon0xSkillDragoon0x/product-skills/skills/retention-activation/cohort-retention-analysis/SKILL.md
Analyze retention by cohort to understand how and why users stick around or leave. Moves beyond vanity metrics like MAU to actionable retention insights. Use when retention looks bad and you don't know where to focus, measuring impact of product changes, or comparing retention across segments.
Dragoon0xSkillDragoon0x/product-skills/skills/strategy/competitive-framing/SKILL.md
Position against alternatives without being negative. Maps competitive landscape, identifies differentiation axes, and generates comparison frameworks. Use when building comparison pages, handling objections, or differentiating from existing solutions.
Dragoon0xSkillDragoon0x/product-skills/skills/strategy/feature-prioritization/SKILL.md
Decide what to build next based on impact, not excitement. Applies scoring frameworks to feature backlogs. Use when scope is unclear, when the agent is about to build everything at once, or when deciding what ships in v1 vs v2.
Dragoon0xSkillDragoon0x/product-skills/skills/strategy/market-validation/SKILL.md
Test assumptions before committing resources. Generates lean validation plans, fake door tests, and interview scripts. Use before building anything expensive or when there's no evidence anyone wants what's being built.
Dragoon0xSkillDragoon0x/product-skills/skills/strategy/positioning/SKILL.md
Articulate why a product exists, who it serves, and what it replaces. Generates positioning statements, competitive angles, and category definitions. Use when launching something new, entering a crowded market, or when nobody can explain what the product does in one sentence.
Dragoon0xSkillDragoon0x/product-skills/skills/strategy/zero-to-one/SKILL.md
First principles decisions for products that don't exist yet. Helps reason about market gaps, user needs, MVP scope, and what to build first. Use when starting from scratch, scoping an MVP, or when the agent needs to think before it builds.
Dragoon0xSkillDragoon0x/useslidekit/SKILL.md
Comprehensive presentation design skill for Claude Code. Projection-aware design, audience-adaptive layouts, narrative architecture, perceptual data visualization, anti-AI-slop detection, rehearsal intelligence, and multi-format export. Complements Anthropic's built-in PPTX skill.
Dragoon0xSkillDragoon0x/10x-branding/skills/brand-architect/SKILL.md
Build a deeply reasoned, evidence-aware BRAND.md that acts as the canonical operational model of any brand. Use this when a brand needs to be understood, reconstructed, documented, governed, reproduced, critiqued, or extended. The skill converts source material and observed brand behavior into a usable brand intelligence system rather than a conventional brand-book summary.
Dragoon0xSkillDragoon0x/10x-branding/skills/brand-critic/SKILL.md
Critique a specific body of brand work by separating observation, impact, root cause, evidence, and recommendation, with severity set by consequence rather than taste. Use to review a logo, identity, campaign, website, messaging, naming direction, or brand book, when feedback has become subjective or endless, or when work keeps being revised without improving. Produces a critique report with root causes and a defensible verdict.
Dragoon0xSkillDragoon0x/10x-branding/skills/brand-governance/SKILL.md
Build brand governance that protects equity while letting teams move fast — decision rights, asset classification, review thresholds, drift detection, exception handling, and an evidence-led protocol for evolving the brand. Use when brand decisions bottleneck on one person, when guidelines are ignored or applied so rigidly work stalls, when nobody knows who decides, or when a brand needs to change without discarding what it has built. Produces a governance manual teams can act on.
Dragoon0xSkillDragoon0x/10x-branding/skills/brand-intelligence/SKILL.md
Diagnose the real brand problem before anyone designs an answer. Use at the start of any brand engagement, when a brief is vague or arrives pre-solved ("we need a rebrand", "our messaging isn't landing"), or when work keeps failing review for reasons nobody can name. Produces an evidence-backed diagnosis of business reality, audience progress, category behavior, existing equity, perception gaps, and the single highest-leverage problem branding can influence.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
