aiox-po

Activate the AIOX Product Owner agent (Pax). Use for backlog management, story refinement, acceptance criteria, sprint planning, and prioritization decisions Trigger when user asks to po, or says 'activate po', 'switch to po', '@po'.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.kimi/skills/aiox-po/SKILL.md

Quality

Content

56%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 well-structured and actionable with clear workflows, but suffers from significant duplication (commands repeated three times, YAML re-stating the markdown) that hurts token efficiency. Progressive disclosure is only partially realized because the full agent config is inlined rather than split into referenced files.

Suggestions

Eliminate the triple command listing: keep one canonical command table and have the YAML and Quick Commands sections reference it instead of re-listing.

Move the large embedded YAML agent definition into a referenced bundle file (e.g., references/agent-definition.yaml) and summarize it in SKILL.md, improving both conciseness and progressive disclosure.

Specify arguments for every command (e.g., '*backlog-review {sprint}', '*sync-story {story-id}') so all guidance is fully executable.

Dimension	Reasoning	Score
Conciseness	Commands are listed three times (Star Commands table, embedded YAML 'commands:' block, and Quick Commands) and the large inline YAML duplicates the persona/commands already shown in markdown, creating noticeable token waste.	2 / 5
Actionability	Concrete '*'-prefixed commands with argument specs and specific delegation targets give mostly executable guidance, with minor gaps where args are unspecified.	4 / 5
Workflow Clarity	Activation Protocol and the 7-step Typical Workflow are clearly sequenced, with a START/END story lifecycle and a validation command; only minor checkpoint gaps remain.	4 / 5
Progressive Disclosure	Section headers and signaled one-level references exist, but the ~220-line embedded YAML config and dependency lists that could live in separate files are inlined, and no bundle files are present to verify referenced paths.	3 / 5
	Total	13 / 20 Passed

Description

83%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.

The description clearly communicates the skill's purpose and explicit activation triggers with concrete PO-tasks coverage. A minor punctuation typo ('decisions Trigger') and a few missing synonyms keep trigger quality and specificity just below maximum.

Suggestions

Fix the missing period before 'Trigger' ('...prioritization decisions. Trigger when...') for clean parsing.

Add a couple of natural synonyms (e.g., 'product owner', 'prioritize backlog') to broaden trigger coverage.

Tighten the action list by leading with the primary verb form (e.g., 'Manage and prioritize the product backlog, refine stories, define acceptance criteria, plan sprints').

Dimension	Reasoning	Score
Specificity	Names the product-owner domain and lists several concrete actions ('backlog management, story refinement, acceptance criteria, sprint planning, and prioritization decisions'), with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both 'what' (activate the AIOX Product Owner agent and perform listed PO tasks) and 'when' with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides natural activation phrases users would say ('activate po', 'switch to po', '@po') with good coverage, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clear PO niche with distinct '@po'/'activate po' triggers and minimal conflict risk, with only minor overlap against related @pm/@sm roles.	4 / 5
	Total	17 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: SynkraAI/aiox-core
Path: .kimi/skills/aiox-po/SKILL.md
Commit: 4ef6530

Reviewed: 2 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.