CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-agent-dev

Senior software engineer who implements stories and code changes. Use when the user asks to talk to Amelia or requests the developer agent

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-dev/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 an exemplary instruction-only skill: a crisp 8-step activation sequence with verbatim commands, explicit wait/validation checkpoints, and robust failure fallbacks for both the resolver script and menu dispatch. Its only weaknesses are minor trimmable rationale phrases and a couple of dense passages that could be split into reference files as the skill grows.

DimensionReasoningScore

Conciseness

The body is dense, instruction-only, and assumes Claude's competence (no concept explanations), but rationale clauses like "so the user can see at a glance which agent is speaking" and "so the active persona stays visually identifiable" are minor over-explanations that could be trimmed, matching anchor 4 rather than the 'every token earns its place' of 5.

4 / 5

Actionability

Guidance is fully executable: verbatim runnable commands ("uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key agent"), a precise fallback with file order and merge semantics, and concrete dispatch rules with a worked example ("hey Amelia, let's implement the next story").

5 / 5

Workflow Clarity

Steps 1-8 are clearly sequenced with explicit validation checkpoints ("Stop and wait for input"; "confirm every entry was executed in order... Do not begin the main workflow until all activation steps have been completed") and error-recovery feedback loops (script-not-found -> offer setup -> re-run; failure -> manual three-file merge fallback).

5 / 5

Progressive Disclosure

Sections are well-organized and the activation procedure is appropriately self-contained with no dangling references, but at roughly 70 body lines it exceeds the under-50-line simple-skill case, and dense passages (the Step 1 merge rules, Step 5 folder taxonomy) could live in a reference file, matching anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

62%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 clearly states the role and includes an explicit 'Use when' clause with distinctive persona-based triggers, but the capability coverage is thin and the triggers miss the natural task language (implement a story, code changes) users would most likely say. It is solid but leaves both specificity and trigger breadth on the table.

Suggestions

Add concrete task-oriented trigger phrases to the 'Use when' clause, e.g. 'Use when the user asks to implement a story, work on tickets, or make code changes' — users are more likely to describe the task than to name the agent.

Expand the 'what' side beyond one clause: name the key activities (implement approved stories test-first, meet acceptance criteria, ship verified code) so capability coverage is comprehensive rather than 1-2 actions.

Consider adding synonyms for the persona ('developer agent', 'Amelia', 'senior software engineer') to broaden natural keyword coverage while keeping the triggers distinct from sibling BMAD agent skills.

DimensionReasoningScore

Specificity

The description names the domain ("Senior software engineer") with 1-2 concrete actions ("implements stories and code changes") but offers no broader coverage of what the agent actually does, matching the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' of a 4.

3 / 5

Completeness

Both a clear what ("implements stories and code changes") and an explicit "Use when" clause are present, but the when triggers are persona-invocation-based rather than task-based, so it fits anchor 4 ('when could be more explicit or specific') rather than the fully concrete anchor 5.

4 / 5

Trigger Term Quality

"talk to Amelia" and "requests the developer agent" are relevant natural phrases, but common task-oriented variations users would actually say ("implement the next story", "write the code for", "work on story 3.2") are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"talk to Amelia" is a unique, unambiguous trigger, and "requests the developer agent" is mostly distinct within an agent suite; only minor overlap risk exists with closely related sibling agent skills, matching anchor 4 rather than anchor 3's 'could still overlap with similar skills'.

4 / 5

Total

14

/

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-dev/SKILL.md

Revision

61e01f8

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill