agent-release-gate

Run the agent release gate — a portable, wire-level QA harness for the agent runtime. Drives the same product endpoint the playground drives and asserts on the SSE frame stream and real side effects, never on model prose, so it works against any deployment (cloud or self-hosted) from three env vars. Use before an agent-workflows release, or after changing the runner, the SDK agent adapters, the runner Docker images, or the agent service. Triggers: "run the release gate", "QA the agent runtime", "does the agent still work end to end", "pre-release agent QA".

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%

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

A well-crafted, actionable, and concise SKILL body with strong workflow checkpoints and a textbook 'read on demand' resource section. Its one real defect is that none of the referenced resource files actually exist in the bundle, so the progressive-disclosure structure does not deliver.

Suggestions

Ship the referenced bundle files (resources/coverage.md, resources/LESSONS.md, resources/qa_product.py, resources/qa_probe.py, resources/qa_longctx.py, resources/seeds/) so the 'read on demand' links resolve instead of dangling.

If any referenced path is intentionally external (e.g. docs/design/agent-workflows/projects/qa/), mark it as outside the skill bundle so readers know it is not packaged here.

Add a one-line note in the Resources section stating these files live alongside the skill, so their absence is detectable as a packaging bug rather than a dead link.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes competence — it never explains what SSE or a release gate is, and the 'When results lie' section packs genuinely non-obvious knowledge rather than padding.	3 / 3
Actionability	Provides copy-paste-ready, concrete commands with specific flags — 'export AGENTA_BASE=...', 'uv run resources/qa_product.py --all --custom-slug <vault-slug>' — not pseudocode or vague direction.	3 / 3
Workflow Clarity	Clear sequence (set env vars -> run gate -> read result) with explicit verification checkpoints: the driver 'fails fast' and names missing env, each journey prints PASS/FAIL/SKIP, and 'Any FAIL blocks the release until triaged'.	3 / 3
Progressive Disclosure	The body is ideally structured with a 'Resources (read on demand)' section of one-level-deep, clearly signaled references, but every referenced path (resources/coverage.md, resources/LESSONS.md, resources/qa_product.py, etc.) is absent from the bundle — the navigation is broken, not 'easy navigation'.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 strong, third-person description that names concrete actions, gives an explicit when-to-use clause, and lists natural trigger phrases. It is specific, complete, and distinct without resorting to fluff or first/second-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Drives the same product endpoint', 'asserts on the SSE frame stream and real side effects, never on model prose' — rather than vague language.	3 / 3
Completeness	Clearly answers both what (a wire-level QA harness asserting on SSE frames and side effects) and when ('Use before an agent-workflows release, or after changing the runner, the SDK agent adapters...').	3 / 3
Trigger Term Quality	An explicit 'Triggers:' clause gives natural phrases a user would say — 'run the release gate', 'QA the agent runtime', 'does the agent still work end to end', 'pre-release agent QA'.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (agent-runtime release-gate QA) with distinct triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	12 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: Agenta-AI/agenta
Path: .agents/skills/agent-release-gate/SKILL.md
Commit: 93872a6

Reviewed: 5 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.