vh-solara

Operate the vh-solara agent harness itself — install, self-update, run the upgrade loop, read release migration notes, and use guide/update/doctor. Load this skill when asked to install, update, or operate the harness, or to read what changed in a release.

Backlog ledger discipline for vh-solara — conflict-safe edits to docs/planning/backlog.md (hybrid split-commit) plus DEFER/follow-up curation routing. Load this skill before editing the backlog, when handling a cas_conflict on the backlog, or when deciding where a DEFER/p2 finding should land.

Caller-facing routing aid for media-perception in vh-solara — decide between in-context perception (vision-capable caller) and single-delegation to the media-perception specialist (text-only caller or heavy/multi-step perception). Load this skill when you hold an image, diagram, chart, video, document/PDF, or audio locator and need to decide how to perceive it.

Debugging loop for existing bugs — build a deterministic red signal FIRST, then reproduce, minimise, hypothesise, instrument, fix, regression-test, with a 3-line post-mortem. Use this when fixing a bug, chasing a failure, or reproducing a defect. Includes an explicit downgrade-to-human handoff when deterministic red is unavailable.

Guide for creating and updating repo-local OpenCode skills in this coding repository. Use this whenever a user asks to create, update, improve, validate, or troubleshoot a skill under `.opencode/skills/`, or when archived sessions should be distilled into reusable coding workflows.

Test-driven development loop for new behavior — red, green, refactor, next vertical slice. Use this when adding or changing behavior test-first at pre-agreed seams. Loads when the user asks to TDD a feature, write tests first, drive an implementation with tests, or settle when refactor should happen.

Gated-commit protocol for vh-solara. Load this skill when you need to commit changes, stage files, or understand the commit-gate enforcement model. Use this whenever the task involves git add, git commit, git push, git reset, or any git write operation.

Decision helper for picking the right read-only opencode workflow — researcher, debate, one-shot solution-brief, or phased solution-brief (research.md → debate.md → brief.md) — based on the question's uncertainty shape. Use this when the operator asks "should we research / debate / solution-brief this?", before drafting any new read-only session prompt, when the framing is ambiguous about which workflow shape fits, or when a stakeholder reframe has just landed and the workflow choice should be reconsidered.

Launch, monitor, stop, list, or resume long-running non-GPU local shell tasks without relying on one shell timeout. Use this when the user asks to run local build/release/maintenance commands that may outlive one shell call or one OpenCode session.

Package a safe-to-share bug bundle for vh-solara via `vh-agent-harness diagnostics-export`. Loads when the operator needs to share harness state with a maintainer, file a bug report, or archive session memory for a complex issue. Field-aware secret redaction, repo-local output, never auto-uploaded.

Generator/maintainer for the project's repo-recon structural data file at `.opencode/repo-configs/repo-recon-data.yml`. Use this whenever the user asks to map the repo, locate entrypoints/hotspots/packages/tests, create or refresh the repo-recon data, or recreate it after a structural change. The data file is external_generated — the harness scaffolds it blank on install, then the project (this skill or project agents) owns it.