CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 tightly written, fully executable activation workflow: exact commands, explicit fallback merge rules, sequenced steps with checkpoints, and well-defined error-recovery paths. Its only weaknesses are mild persona padding and the absence of small illustrative examples (a sample menu row, a sample persistent fact).

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — TOML merge rules in one sentence, no basic-concept explanations — and every section instructs rather than describes. A few persona-preamble sentences ('Fully embody this persona so the user gets the best experience') could be trimmed, matching anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Guidance is directly executable: exact uv/npx commands, exact file precedence (base → team → user), and precise menu table columns and dispatch rules. Minor gaps remain — no sample menu table or example persistent fact to illustrate common cases, and execution hinges on externally resolved {agent.*} values — so it falls short of anchor 5's 'specific examples cover the common cases'.

4 / 5

Workflow Clarity

Eight clearly sequenced activation steps with an explicit checkpoint ('confirm every entry was executed in order... Do not begin the main workflow until all activation steps have been completed') and feedback loops for error recovery (script missing → offer setup → rerun; resolver failure → documented manual merge; menu skill missing → install offer). This matches the anchor-5 pattern; there are no destructive or batch operations that would warrant additional validation.

5 / 5

Progressive Disclosure

A single-file, single-purpose skill (~70 lines) with well-organized sections and no nested references; the only file pointers (customize.toml, bmod.toml, _bmad/ scripts) are one level deep and clearly signaled with explicit path-resolution conventions. Per the simple-skill exception, well-organized sections alone warrant anchor 5.

5 / 5

Total

18

/

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 answers both what and when in third person with distinctive persona-based triggers, but its capability coverage is thin: only two concrete actions, and the trigger clause misses natural PRD-work requests like 'help me write a PRD'. It is strong on distinctiveness yet leaves recall-dependent gaps.

Suggestions

Add one or two more concrete actions to the 'what' clause (e.g., 'runs stakeholder interviews and breaks requirements into ship-sized increments') to lift specificity.

Extend the 'when' clause with PRD-work trigger phrases such as 'Use when the user wants to write or review a PRD, gather product requirements, or talk to John'.

Include the synonym 'product requirements document (PRD)' or 'PM' so users who never mention 'John' still match the skill.

DimensionReasoningScore

Specificity

Names the domain ('Product manager') with exactly two concrete actions ('PRD creation', 'requirements discovery'), matching the anchor for 1-2 concrete actions but not comprehensive coverage. Anchor 4 requires several specific actions with only minor gaps, which two actions do not meet.

3 / 5

Completeness

Both 'what' ('Product manager for PRD creation and requirements discovery') and 'when' ('Use when the user asks to talk to John or requests the product manager') are explicit. The 'when' clause omits PRD-creation triggers, so it could be more specific, matching anchor 4 rather than 5.

4 / 5

Trigger Term Quality

Natural trigger phrases are present ('asks to talk to John', 'requests the product manager') alongside PRD/requirements keywords, giving good coverage. Common variations like 'write the PRD', 'product requirements document', or 'PM' are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — a named PM persona ('John') for PRD creation and requirements discovery — with distinct triggers, so conflict with other skills is minimal. It is not the anchor-4 case of minor overlap with closely related skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.