opencode-qa

QA opencode itself, per case: verify the CLI/terminal (opencode run, db, serve, export), prove a specific plugin hook/action/event fired via the SSE event stream, smoke-test the TUI under tmux, and investigate sessions in opencode's SQLite DB by id, title/name, or message text. Ships tested helper scripts (each with a --self-test) plus per-domain references. Use whenever someone wants to QA, smoke-test, verify, or debug opencode's CLI, HTTP server, plugin hooks/events, or TUI, or to find/inspect opencode sessions in the database. Triggers: opencode qa, qa opencode, test opencode, verify opencode hook, opencode session db, find opencode session by id/name/text, opencode tui test, opencode server health, opencode event stream.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable QA skill body that routes each need to tested scripts and one-level-deep references, with strong validation checkpoints and isolation guards throughout. The only weakness is a few passages of trimmable prose that lightly pad an otherwise lean overview.

Suggestions

Trim the 'Honest verdict: tmux is fine for SMOKE...' paragraph and other restating prose to the essential conclusion, since the scripts and references already demonstrate the behavior.

Collapse the version-specific note ('Verified against opencode v1.17.7 (bun 1.3.12, macOS)') into a single sanity-check instruction to reduce time-sensitive clutter.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient, assuming Claude's competence, but contains minor trimmable prose such as the 'Honest verdict: tmux is fine for SMOKE...' narration and a few explanatory sentences that restate what the scripts already demonstrate. It is above the midpoint but not perfectly lean, so 4 rather than 5.	4 / 5
Actionability	Copy-paste-ready, fully executable commands throughout — `opencode run "list files in src" --format json`, `bash scripts/sse-hook-probe.sh --self-test`, real curl invocations with auth flags and session ids — covering the common cases per case in the router.	5 / 5
Workflow Clarity	A router table maps each QA need to a case, script, and reference; 'Golden rules' act as a pre-flight checklist; and explicit validation checkpoints pervade — every script ships `--self-test`, isolation is proven by comparing session counts before/after, and the text script refuses unbounded scans as a feedback guard against the 25 GB table.	5 / 5
Progressive Disclosure	SKILL.md is an overview that routes to well-signaled one-level-deep references via markdown links (references/cli-commands.md, db-investigation.md, server-api.md, events-hooks.md, tui-tmux.md, testing-harness.md, sdk.md, docker-qa.md), all of which exist as real files, with detailed bulk content appropriately split out rather than inlined.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered description that clearly states what the skill does and when to use it, with comprehensive natural-language trigger phrases and synonyms. It is third-person throughout and avoids vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across distinct surfaces — 'verify the CLI/terminal (opencode run, db, serve, export)', 'prove a specific plugin hook/action/event fired via the SSE event stream', 'smoke-test the TUI under tmux', 'investigate sessions ... by id, title/name, or message text' — giving comprehensive coverage rather than vague verbs.	5 / 5
Completeness	Explicitly answers both 'what' (the per-case QA capabilities and shipped helper scripts) and 'when' (the 'Use whenever someone wants to...' clause plus a dedicated concrete 'Triggers:' list), matching the anchor for clearly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	The explicit 'Triggers:' block covers natural phrases and synonyms users would actually say — 'opencode qa', 'test opencode', 'verify opencode hook', 'find opencode session by id/name/text', 'opencode tui test', 'opencode server health', 'opencode event stream' — plus a 'Use whenever someone wants to QA, smoke-test, verify, or debug' clause.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to QA-ing the opencode tool itself with opencode-specific triggers ('opencode run', 'opencode session db', 'opencode tui test'), establishing a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: code-yeongyu/oh-my-openagent
Path: .agents/skills/opencode-qa/SKILL.md
Commit: 6108673

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.