open-horizon-labs
- 36 skills
- 0 followers
- 5 hours ago last updated
- ▌ Superego 2 · open-horizon-labs bundle<!-- NOTE: This file is synced from codex-skill/SKILL.md. Edit the source there and copy here. -->
- ▌ Bottle 2 · open-horizon-labs bundleOpen Horizon Labs meta-tool. One entry point for ba, wm, and superego. Use "bottle-init" to set up all tools, "bottle-status" to check state.
- ▌ Superego · open-horizon-labs bundleMetacognitive oversight. Invoke with "$superego" to evaluate, "$superego init" to set up, "$superego remove" to uninstall.
- ▌ Bottle · open-horizon-labs bundleOpen Horizon Labs orchestration. "$bottle init" for setup, "$bottle dive" to start sessions, "$bottle web-context" for fresh docs.
- ▌ Ba · open-horizon-labsTask tracking. "$ba status" for current tasks, "$ba claim <id>" to start work, "$ba finish <id>" when done.
- ▌ Sg · open-horizon-labsMetacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions.
- ▌ Wm · open-horizon-labsWorking memory. "$wm dive" to prep sessions, "$wm compile" for context, "$wm distill" to extract learnings.
- ▌
- ▌ Problem Weave · open-horizon-labs bundleMap a cross-layer problem with independent problem statements and Strategy & Tactics trees, then interweave overlap, opposition, dependencies, and gaps. Use when one frame hides distinct work across users, systems, teams, or explanations. Routes durable artifacts to $record and selected tactics to /oh-plan.
- ▌ Aim · open-horizon-labsClarify the outcome you want - a change in user behavior, not a feature shipped. Use at the start of any work to ground the session in strategic intent.
- ▌ Ship · open-horizon-labsRun RNA's mandatory project-specific quality gate from completed implementation through review, verification, CI, and merge. Use when a draft PR is ready to be delivered.
- ▌ Setup · open-horizon-labsInstall and configure the Repo-Native Alignment (RNA) MCP server. Downloads the binary, configures the MCP server, pre-warms the code index, and updates AGENTS.md with tool guidance.
- ▌
- ▌ Record · open-horizon-labs bundleCreate or update repo-native outcomes, objectives, capabilities, signals, guardrails, metis, and ADRs. Use to preserve S&T lineage or record learning, measurements, constraints, and outcome status.
- ▌ Review · open-horizon-labsCheck work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.
- ▌ Dissent · open-horizon-labsDevil's advocate. Seek contrary evidence before locking in. Use when about to make a significant decision, when confidence is high but stakes are higher, or when the team is converging too quickly.
- ▌ Distill · open-horizon-labsHuman-led curation of accumulated metis and guardrails. Surface patterns across sessions, propose what to promote, compact, or dismiss. Use after multiple sessions, before a new phase, or when search results feel noisy.
- ▌ Execute · open-horizon-labsDo the work. Pre-flight, build, detect drift, salvage if needed. Use when you have a clear aim and are ready to implement.
- ▌ Oh Join · open-horizon-labsResolve multi-dependency fan-in by merging dependency PRs into a common base and updating issue dependencies
- ▌ Oh Plan · open-horizon-labsCreate GitHub issues from task descriptions or session context. Investigates when needed, skips when context exists.
- ▌ Oh Task · open-horizon-labsClaim a GitHub issue, create its branch and draft PR before implementation, execute the work in isolation, and hand the completed draft to RNA's full ship gate.
- ▌ Salvage · open-horizon-labsExtract learning before restarting. Code is a draft; learning is the asset. Use when work is drifting, approach has reversed 3+ times, or scope is expanding while "done" keeps fuzzing.
- ▌ Adr Sync · open-horizon-labsBackfill ADR frontmatter with direct executable validation refs, compile/check ADR validation manifests, and report missing real checks without inventing them.
- ▌
- ▌
- ▌ Teach Oh · open-horizon-labsProject setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when starting or when aims shift.
- ▌ Dead Code · open-horizon-labsDetect potentially dead code using RNA graph data. Finds public functions with zero non-test callers. No code changes needed — queries existing graph edges.
- ▌ Jira Plan · open-horizon-labsCreate Jira subtasks from task descriptions or session context. Investigates when needed, skips when context exists.
- ▌ Oh Review · open-horizon-labsReview a PR against its linked issue requirements, post structured feedback
- ▌
- ▌ Arch Diagram · open-horizon-labsGenerate an architecture diagram from RNA data. Queries frameworks, endpoints, entry points, and external service calls, then renders in the user's preferred format (d2, mermaid, plantuml, etc.).
- ▌ Problem Space · open-horizon-labsMap what we're optimizing and what constraints we treat as real. Use before jumping to solutions, when hitting repeated blockers, or when patches keep accumulating.
- ▌ Solution Space · open-horizon-labsExplore candidate solutions before committing. Use when you have a problem statement and need to evaluate approaches - band-aid, optimize, reframe, or redesign.
- ▌ Review Readiness · open-horizon-labsAgent-led PR/working-tree review triage. Start from the diff, add RNA graph/business context only where it changes review decisions, and state when raw git diff is enough.
- ▌ Problem Statement · open-horizon-labsDefine the framing of a problem. Change the statement, change the solution space. Use when starting work, when solutions feel wrong, or when you suspect an X-Y problem.
- ▌ Cess · open-horizon-labs bundleApply Counterexample-Supplemented Sketches (CESS) to open-world agent and software synthesis. Use when a user mentions CESS, Sketch-CE, counterexample-supplemented sketches, evolved sketches, compiled projections, simulation-driven correction, or asks to make an agent-generated system improve from reviewed failures without losing earlier behavior.