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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-release-gate/SKILL.md

Quality

Content

67%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.

The body is highly actionable with concrete commands and strong validation rules for a release-gate workflow, and it organizes its references well. Its main weakness is conciseness: extensive inline incident history (dates, session IDs, bug narratives) inflates the token budget and would be better archived, with summaries left in SKILL.md.

Suggestions

Move the per-cell incident narratives (session UUIDs, 'Verified PASS 2026-08-06' lines, PR numbers) into resources/LESSONS.md or a separate findings archive, leaving one-line summaries in SKILL.md to cut the time-sensitive token load.

Promote the mandatory qa_commit_approval.py step and the SKIP-as-failure rule into a short numbered release checklist so the workflow sequence is unambiguous rather than buried in prose.

Move the long per-matrix-cell descriptions into their respective resource files (or a matrix.md) and keep SKILL.md to a one-line purpose per cell, tightening the progressive-disclosure split.

Dimension	Reasoning	Score
Conciseness	The body is dense and project-specific rather than explaining concepts Claude already knows, but it carries heavy inline historical narrative — session UUIDs, repeated 'Verified PASS 2026-08-06' dates, PR numbers, and per-incident bug stories — that is time-sensitive and could be tightened or moved to an archive, matching 'mostly efficient but could be tightened'.	3 / 5
Actionability	Provides concrete, copy-paste-ready commands with flags — 'export AGENTA_BASE=...', 'uv run resources/qa_product.py --all --custom-slug <vault-slug> ...', plus one-cell and one-journey variants — covering the common cases, with only placeholder values as minor gaps.	4 / 5
Workflow Clarity	The run sequence (set env vars → run the gate → read PASS/FAIL/SKIP → also run qa_commit_approval.py → triage) is clear with explicit validation rules ('Any FAIL blocks the release', a SKIP in a security/concurrency area is a FAILURE), but the mandatory commit-approval step and SKIP handling are woven through prose rather than a clean numbered checklist, leaving minor sequencing gaps.	4 / 5
Progressive Disclosure	A well-organized 'Resources (read on demand)' section signals one-level-deep references (coverage.md, LESSONS.md, qa_product.py, the matrix cells) each with a description, but lengthy per-cell narratives are inlined in the body rather than split into the referenced files, and the referenced resources/ bundle is not actually present.	4 / 5
	Total	15 / 20 Passed

Description

87%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 strong, specific description that clearly states what the skill does, when to use it, and which natural phrases trigger it, with a distinct niche and low conflict risk. The only soft spot is trigger-term coverage, which is good but not exhaustive of synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Drives the same product endpoint the playground drives', 'asserts on the SSE frame stream and real side effects, never on model prose', 'works against any deployment ... from three env vars' — which goes beyond naming the domain, though it stops short of enumerating a fully comprehensive action set.	4 / 5
Completeness	It explicitly answers both 'what' (a portable, wire-level QA harness asserting on SSE frames and real side effects) and 'when' ('Use before an agent-workflows release, or after changing the runner, the SDK agent adapters, the runner Docker images, or the agent service') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The explicit 'Triggers:' clause supplies four natural phrases users would say — "run the release gate", "QA the agent runtime", "does the agent still work end to end", "pre-release agent QA" — giving good coverage, though a few synonyms (e.g. "agent QA", "smoke test the agent") are absent.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined — a wire-level release-gate QA harness for the agent runtime with SSE-frame assertions — and the triggers are distinct, making overlap with unrelated skills minimal.	5 / 5
	Total	18 / 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
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: a09a0f0

Reviewed: 1 day 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.