CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-agent-pm

John, the Product Manager: coaches planning documents out of the user, then updates or validates them. Use when the user asks for John, the PM or the product manager, or says 'create a PRD', 'draft the product requirements', 'update the PRD', 'validate this PRD', 'review my PRD', 'write a product brief', 'spec this feature for a coding agent', 'prototype this', 'plan a prototype', 'is this problem worth pursuing', 'write the business case', 'draft the program charter', 'write the strategy narrative', 'shape a pitch', 'write the requirements specification', 'write the BRD', 'plan an experiment', 'plan the launch'.

Quality

90%

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.

A dense, well-sequenced orchestration skill: lean prose, concrete commands, and an activation workflow with genuine error-recovery loops. The main weakness is bundle navigation — the template assets are not explicitly linked, and two referenced files (customize.toml, bmod.toml) plus the brd template have no counterpart in the shipped bundle.

Suggestions

Explicitly link the template assets from the body (e.g. 'templates live in {skill-root}/assets/template-<id>.md') or name the assets folder in Conventions, so the 13 bundle files are discoverable without resolving {workflow.template_libraries} first.

Resolve the dangling file references: either ship customize.toml and bmod.toml in the bundle or note where they come from, since both are named as fallback resolution sources in the activation steps.

Clarify the brd template situation — the body routes 'write the BRD' to a brd template but no template-brd.md exists in assets/, so state whether it maps to another template or is resolved elsewhere.

DimensionReasoningScore

Conciseness

The ~45-line body is compressed with zero padding and no explanation of concepts Claude already knows — e.g. 'Stay John until dismissed; the persona carries into every skill you invoke' — every token carries operational content, matching the lean anchor 5 rather than anchor 4 (there are no over-explanation instances left to trim).

5 / 5

Actionability

Concrete executable commands are given verbatim (resolve_customization.py, resolve_config.py, tickets.py with full argument lists, 'npx skills add bmad-code-org/BMAD-METHOD --skill bmad', the '<epic folder>/<template id>-<slug>/' output pattern) with placeholders defined in Conventions. It falls short of anchor 5 because the core create/update/validate execution is delegated to the bmad-facilitate skill, so this file's guidance is not fully copy-paste self-contained.

4 / 5

Workflow Clarity

The 8-step activation is a clear sequence with explicit error-recovery branches — 'Script not found: offer the bmad skill's setup, installing bmad first if needed… then run it again. Any other failure: use customize.toml as shipped and say the overrides were not applied' — plus fallbacks for a missing active_initiative and uninstalled skills, matching the anchor-5 feedback-loop pattern rather than anchor 4's 'minor validation gaps'.

5 / 5

Progressive Disclosure

Sections are well-organized and templates are correctly kept out of the body, but the 13 assets/template-*.md files are never directly linked (navigation runs indirectly through {workflow.template_libraries}), the body references {skill-root}/customize.toml and {skill-root}/bmod.toml which are absent from the bundle, and 'brd' names a template with no matching asset file — 'references present but not clearly signaled' matches anchor 3 rather than anchor 4's minor organization gaps.

3 / 5

Total

17

/

20

Passed

Description

91%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.

A strong description: concrete third-person statement of what the agent does, followed by an explicit 'Use when' clause with an unusually comprehensive set of natural trigger phrases including synonyms. The only weaknesses are a slightly broad 'planning documents' phrase in the what-clause and a few triggers with mild overlap risk against general prototyping/spec skills.

DimensionReasoningScore

Specificity

The description states three concrete actions — 'coaches planning documents out of the user, then updates or validates them' — on a clear object, but 'planning documents' is broader than the anchor-5 standard of a comprehensively enumerated action list; it exceeds anchor 3's 1-2 actions.

4 / 5

Completeness

It explicitly answers both questions: what ('coaches planning documents out of the user, then updates or validates them') and when (an explicit 'Use when' clause listing concrete trigger phrases), directly matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Roughly twenty natural quoted phrases users would actually say — 'create a PRD', 'review my PRD', 'write a product brief', 'write the business case', 'draft the program charter', 'shape a pitch', 'write the BRD', 'plan an experiment', 'plan the launch' — with synonym coverage (PRD / product requirements / requirements specification / BRD), matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

A PM-persona niche with document-specific triggers (PRD, business case, program charter, BRD) is mostly distinct, but 'prototype this', 'plan a prototype' and 'spec this feature' could overlap with generic prototyping or spec-writing skills and sibling BMad agents, so it is not the minimal-conflict anchor 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.