CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-agent-analyst

Business analyst for market research, competitive analysis, and requirements. Use when the user asks to talk to Mary or requests the business analyst

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/bmad-agent-analyst/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 tight, highly executable activation procedure: exact commands, explicit placeholder-resolution conventions, sequenced steps with error-recovery branches, and a clean single-file structure with well-signaled on-demand external files. Its only weakness is mild density in a couple of packed sentences (Step 5 conventions, Step 8 dispatch) that could be broken up for readability.

DimensionReasoningScore

Conciseness

The body is dense and procedural with no explanation of concepts Claude already knows, but a few passages — the packed Step 5 ticket-path conventions sentence ("tickets `initiative-*.md` (older projects `SPEC*.md`), `tickets/epic-*/epic-*.md`, and...") and parts of the Step 8 dispatch rules — could be trimmed or split for clarity, matching the level-4 anchor rather than the fully lean level-5.

4 / 5

Actionability

The guidance is fully executable: exact copy-paste commands ("uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key agent"), concrete fallback merge rules ("Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace..."), and a Conventions section that resolves every placeholder used.

5 / 5

Workflow Clarity

The eight activation steps are clearly sequenced with explicit error-recovery branches ("If the script is not found... offer to run the `bmad` skill's setup"; "If that skill is not installed, say so and offer to install it") and an explicit verification checkpoint ("confirm every entry was executed in order before proceeding"), matching the level-5 anchor with feedback loops and a checklist-style confirmation.

5 / 5

Progressive Disclosure

The single-file body (~69 lines) is cleanly sectioned (## Overview, ## Conventions, ## On Activation with ### Steps 1-8), and all external material (customize.toml, team/user override tomls, resolver scripts, bmod.toml) is clearly signaled and loaded on demand one level deep — no bundle files exist to inline or bury.

5 / 5

Total

19

/

20

Passed

Description

57%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 has an explicit what-and-when structure with distinctive persona triggers, but it names domains without concrete actions and omits task-based trigger terms (market research, competitive analysis, requirements) that users would naturally say. It sits comfortably above the vague-baseline examples yet below the strong examples that pair action lists with concrete trigger phrases.

Suggestions

Rewrite the capability clause with concrete action verbs, e.g. "Conducts market research, performs competitive analysis, and elicits and documents requirements."

Add task-based triggers to the Use-when clause: "...or asks for market research, competitive analysis, SWOT, or requirements gathering."

Include synonyms and deliverable terms (e.g. "business requirements", "PRD", "market analysis") to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

"Business analyst for market research, competitive analysis, and requirements" names three domains but lists no concrete actions (no verbs like "conducts" or "elicits"), matching the anchor "names the domain but actions are minimal or generic" rather than the level-3 anchor which requires 1-2 concrete actions.

2 / 5

Completeness

Both parts are present — a "what" ("Business analyst for market research, competitive analysis, and requirements") and an explicit "Use when..." clause — but the "when" covers only persona invocation and could be more task-specific, matching the level-4 anchor rather than the fully concrete level-5 example.

4 / 5

Trigger Term Quality

"Use when the user asks to talk to Mary or requests the business analyst" provides natural persona triggers, but common task phrasings users would actually say ("market research", "competitive analysis", "requirements") are absent from the trigger clause, so keyword coverage is only partial.

3 / 5

Distinctiveness Conflict Risk

The named-persona business-analyst niche ("talk to Mary", "the business analyst") is mostly distinct with clear triggers, carrying only minor overlap risk with other analyst- or requirements-related skills.

4 / 5

Total

13

/

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-analyst/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.