aiox-pm

Activate the AIOX Product Manager agent (Morgan). Use for PRD creation (greenfield and brownfield), epic creation and management, product strategy and vision, feature prioritization (MoSCoW, RICE), roadmap planning, business case development, go/no-go decisions, scope definition, success metrics, and stakeholder communication. Epic/Story Delegat... Trigger when user asks to pm, or says 'activate pm', 'switch to pm', '@pm'.

Quality

63%

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-pm/SKILL.md

Quality

Content

42%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 functions more as an agent-configuration dump than a lean skill: it carries persona flavor, internal module wiring, and an inlined full YAML block that crowds out actionable guidance. Workflows and commands are listed but lack the validation checkpoints and bundled references that would make them executable and navigable.

Suggestions

Remove the inlined full YAML config block and persona trivia (zodiac, vocabulary, greeting variants) that Claude does not need to perform the task.

Add explicit validation/verification checkpoints to the epic execution and PRD workflows (e.g. validate PRD against template before output), since these are batch/structured operations.

Either bundle the referenced task/template/checklist files (create-doc.md, prd-tmpl.yaml, pm-checklist.md, etc.) or replace the external `.aiox-core/...` path references with concise inline guidance so the skill is self-contained.

Dimension	Reasoning	Score
Conciseness	The body is a large YAML dump of persona trivia (zodiac, Portuguese vocabulary, greeting_levels) plus verbose activation mechanics referencing many internal modules; much of this is padding Claude does not need, fitting 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	There are concrete commands (e.g. `create-prd`, `execute-epic {path}`) and a numbered workflow, but the core operating content is declarative YAML config and module paths rather than executable instructions, leaving guidance incomplete and more config-like than action-like.	3 / 5
Workflow Clarity	A sequence appears (Research → PRD → Epic breakdown → Story planning → Epic execution → Course correction) but validation checkpoints are absent and the gating/elicitation rules are buried in prose; it meets 'steps listed but validation gaps' and the destructive/batch cap (epic execution) holds it at 3.	3 / 5
Progressive Disclosure	No bundle files exist and references point to external repo paths (e.g. `.aiox-core/development/tasks/...`, `docs/architecture/...`) that are not bundled here, so navigation is not actually one-level-deep within the skill; structure is present but references are not clearly signaled or resolvable.	3 / 5
	Total	11 / 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 is strong: it states a comprehensive set of concrete PM capabilities, gives clear trigger phrases, and distinguishes itself from sibling agents via explicit NOT-for guidance. Its main weakness is the truncated 'Epic/Story Delegat...' fragment and the somewhat unusual persona-agent framing.

Suggestions

Repair the truncated phrase "Epic/Story Delegat..." so the capability description is complete and professional.

Consider trimming the long capability list into a tighter clause plus a separate trigger clause; the dense enumeration slightly reduces scannability.

Reframe away from agent-persona mechanics ("Activate... agent (Morgan)") toward the task outcome so the description reads as a skill capability rather than a mode switch.

Dimension	Reasoning	Score
Specificity	Lists many specific capabilities ("PRD creation (greenfield and brownfield)", "feature prioritization (MoSCoW, RICE)", "roadmap planning", "go/no-go decisions", "success metrics"), giving concrete action coverage with only minor gaps, fitting the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers both what ("Activate the AIOX Product Manager agent... Use for PRD creation...") and when ("Trigger when user asks to pm, or says 'activate pm', 'switch to pm', '@pm'"), matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.	5 / 5
Trigger Term Quality	Includes natural triggers users would say ("activate pm", "switch to pm", "@pm", "asks to pm") plus domain keywords; a few common synonyms are missing, so it sits just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The AIOX/PRD framing and explicit negative guidance ("NOT for: Market research... → Use @analyst") carve a clear niche with minimal overlap risk, though the agent persona mechanism is unusual and could border on overlapping with other agent skills.	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-pm/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.