aiox-review-story

QA gate for a story — verdict PASS/CONCERNS/FAIL/WAIVED + lifecycle transition. Use when: review story, qa gate, *qa-gate, /review-story.

Quality

95%

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

100%

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

The content is a well-structured orchestration skill: lean, concrete, with an explicit protocol, a verdict-to-status table, a verification checklist, and a feedback loop for failures. Progressive disclosure is handled cleanly via clearly signaled one-level-deep SOT references rather than inlining detail.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and assumes competence ("Lean SDC skill. Task is source of truth"), avoids explaining concepts Claude already knows, and pushes detail into referenced SOT files, matching the 'every token earns its place' anchor.	3 / 3
Actionability	Concrete, executable guidance throughout: specific paths ("Load `qa-gate.md`", "Write gate under `docs/qa/gates/`"), an explicit verdict-to-status-action table, and a copy-paste-ready status policy — actionable instruction-only guidance per the scoring notes.	3 / 3
Workflow Clarity	A clearly sequenced 5-step Protocol is reinforced by a Post-phase verification checklist and a FAIL→InProgress feedback loop that lists fixes for apply-qa-fixes, satisfying the explicit-validation-and-feedback-loop anchor for a gate operation.	3 / 3
Progressive Disclosure	The body is a tight overview that delegates review depth/schema to clearly signaled, one-level-deep SOT references ("Primary: `qa-gate.md`", "Supporting: `qa-review-story.md`", ".claude/rules/story-lifecycle.md"), with content appropriately split rather than inlined; no bundle files exist to verify, but section organization and reference signaling are clean.	3 / 3
	Total	12 / 12 Passed

Description

90%

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

The description is concise, third-person, and cleanly answers both what the skill does and when to use it, with explicit natural trigger terms. Its only weakness is that it states one core action rather than enumerating several concrete operations, capping specificity at 2.

Suggestions

Expand the 'what' clause to name a few concrete sub-actions (e.g. 'runs the QA review, writes the gate file under docs/qa/gates/, and transitions the story lifecycle') to lift specificity to 3.

Keep the existing 'Use when' clause as-is; it already provides strong trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes "QA gate for a story — verdict PASS/CONCERNS/FAIL/WAIVED + lifecycle transition" name the domain and concrete outputs (enumerated verdicts, lifecycle transition), but it describes a single gate action rather than a list of multiple distinct actions like the score-3 anchor (extract/fill/merge), so it sits at the 'names domain and some actions' level.	2 / 3
Completeness	It explicitly answers what ("QA gate for a story — verdict ... + lifecycle transition") and when ("Use when: review story, qa gate, *qa-gate, /review-story"), with an explicit trigger clause that lifts it above the score-2 cap.	3 / 3
Trigger Term Quality	"Use when: review story, qa gate, *qa-gate, /review-story" gives good coverage of the natural terms a user in this workflow would say, including both phrase and command-form variations, matching the score-3 anchor's coverage criterion.	3 / 3
Distinctiveness Conflict Risk	The niche "QA gate for a story" with distinct triggers ("review story", "qa gate", "/review-story") is narrowly scoped to story review and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: SynkraAI/aiox-core
Path: .grok/skills/aiox-review-story/SKILL.md
Commit: 0b32b68

Reviewed: about 13 hours 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.