open-horizon-labs/skills

1

dissent Devil's advocate. Seek contrary evidence before locking in. Use when about to make a significant decision, when confi…

open-horizon-labs/skills

129

2

ship Deliver code to users. Optimize the path from merged code to working install. Use when execution is complete and you …

open-horizon-labs/skills

115

3

review Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause…

open-horizon-labs/skills

114

4

execute Do the work. Pre-flight, build, detect drift, salvage if needed. Use when you have a clear aim and are ready to imple…

open-horizon-labs/skills

113

5

problem-space Map what we're optimizing and what constraints we treat as real. Use before jumping to solutions, when hitting repeat…

open-horizon-labs/skills

110

6

problem-statement Define the framing of a problem. Change the statement, change the solution space. Use when starting work, when soluti…

open-horizon-labs/skills

110

7

solution-space Explore candidate solutions before committing. Use when you have a problem statement and need to evaluate approaches …

open-horizon-labs/skills

107

8

aim Clarify the outcome you want - a change in user behavior, not a feature shipped. Use at the start of any work to grou…

open-horizon-labs/skills

105

9

salvage Extract learning before restarting. Code is a draft; learning is the asset. Use when work is drifting, approach has r…

open-horizon-labs/skills

103

10

teach-oh Project setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when sta…

open-horizon-labs/skills

101

11

distill Human-led curation of accumulated metis and guardrails. Surface patterns across sessions, propose what to promote, co…

open-horizon-labs/skills

68

12

problem-weave Map a cross-layer problem with independent problem statements and Strategy & Tactics trees, then interweave overlap, …

open-horizon-labs/skills

8