bmad-agent-pm

Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager

Quality

74%

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 ./skills/bmad-agent-pm/SKILL.md

Quality

Content

75%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 a well-structured, mostly lean persona-activation workflow with concrete commands, a fallback resolution path, and explicit completion gating. It is held back from 5s by minor persona padding, thin error-recovery loops beyond Step 1, and the absence of any bundle/reference structure to fully exercise progressive disclosure.

Suggestions

Trim persona-embodiment padding (e.g. 'Fully embody this persona so the user gets the best experience') to tighten conciseness.

Add a brief retry/feedback note for Step 5 (config resolution) mirroring the Step 1 fallback, so failure handling is consistent across the activation workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — concrete commands, placeholder tokens, and terse bullet rules — with only minor over-explanation such as 'Fully embody this persona so the user gets the best experience'.	4 / 5
Actionability	Provides executable commands (e.g. `uv run {project-root}/_bmad/scripts/resolve_customization.py ...`) and a concrete fallback procedure with explicit merge rules; a few steps remain abstract ('Adopt Persona', 'Greet the user warmly') but that is inherent to a persona skill.	4 / 5
Workflow Clarity	Eight clearly sequenced activation steps with an explicit fallback in Step 1 and a completion checkpoint ('confirm every entry was executed in order... Do not begin the main workflow until all activation steps have been completed'); no destructive/batch operation applies, so the cap is not triggered, though error-recovery feedback loops beyond Step 1 are thin.	4 / 5
Progressive Disclosure	Well-organized into Overview, Conventions, and a numbered On Activation sequence; no bundle files exist and the skill is largely self-contained, so good section structure earns a strong score, though it slightly exceeds the under-50-line simple-skill threshold.	4 / 5
	Total	16 / 20 Passed

Description

73%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 third-person, concise, and answers both what and when with distinctive persona-based triggers. Its main weakness is specificity — it describes a role and two activities rather than a comprehensive set of concrete actions, and its triggers omit the natural task phrasings users might use.

Suggestions

Add concrete action verbs to the 'what' clause (e.g. '...drives user interviews, writes PRDs, and scopes validated increments') to lift specificity.

Broaden the 'when' trigger to include task-oriented phrasings users naturally say, such as 'Use when the user wants to write or refine a PRD, gather requirements, or scope product work'.

Dimension	Reasoning	Score
Specificity	Names the domain (product management) and 1-2 concrete actions ('PRD creation', 'requirements discovery'), but is not comprehensive — it reads as a role summary rather than a list of specific operations.	3 / 5
Completeness	Explicitly answers both what (PM for PRD creation and requirements discovery) and when (Use when the user asks to talk to John or requests the product manager); the 'when' is explicit but the trigger phrasing is narrower than the actual task surface.	4 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('talk to John', 'requests the product manager') with good coverage, though it misses common task-oriented variations like 'write a PRD' or 'gather requirements'.	4 / 5
Distinctiveness Conflict Risk	The named persona 'John' and 'product manager' framing form a clear, distinct niche with minimal conflict risk against other skills.	5 / 5
	Total	16 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: bmad-code-org/BMAD-METHOD
Path: skills/bmad-agent-pm/SKILL.md
Commit: 0a00053

Reviewed: 3 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.