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

74%

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

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 content is a tightly written, executable activation workflow with exact commands, explicit precedence rules, error recovery, and a clear step sequence. Its main weakness is that validation handling is uneven (Step 5 lacks the fallback Step 1 has) and the actual engineering workflow beyond activation is delegated without local detail.

DimensionReasoningScore

Conciseness

The body is dense operational instruction with no explanations of concepts Claude already knows; only minor flourishes ("Fully embody this persona so the user gets the best experience", "chat, clarifying questions, and bmad help are always fair game") could be trimmed. This matches anchor 4 — efficient with minor trimmable instances — rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

It gives exact copy-paste commands ("uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key agent" and the resolve_config.py invocation), an install fallback ("npx skills add bmad-code-org/BMAD-METHOD --skill bmad"), and concrete file precedence plus merge semantics. The gap keeping it from anchor 5: the core story-implementation workflow itself is never concretely specified, only delegated to dispatched skills.

4 / 5

Workflow Clarity

Steps 1–8 are clearly sequenced with an explicit error-recovery fallback in Step 1 and a closing checkpoint ("confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed"). Minor validation gaps remain — Step 5 has no failure handling unlike Step 1, and the manual merge fallback has no verification step — so anchor 4 rather than 5.

4 / 5

Progressive Disclosure

There are no bundle files and no reference chains; the ~70-line body is organized into clean sections (Conventions, On Activation, Steps 1–8) with all content appropriately inline for a single-process activation skill. This is anchor 4 — good structure, content appropriately placed — rather than 5, since it exceeds the under-50-line simple-skill case and offers no well-signaled reference structure.

4 / 5

Total

16

/

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 has a clear what-and-when structure with distinctive persona triggers, but the capability listing is thin and the trigger vocabulary is narrow. Users asking for story implementation or coding help in natural language would likely miss it.

Suggestions

Enumerate the concrete capabilities more fully, e.g. "Implements approved stories test-first (red/green/refactor), writes and refactors code, and verifies every acceptance criterion" — currently only "implements stories and code changes" is stated.

Broaden trigger terms to cover natural user phrasings: "Use when the user asks to implement or code a story, make code changes, or requests Amelia, the developer agent".

Clarify the niche versus sibling BMAD agents (e.g. architect, PM) so "developer agent" requests are unambiguously routed to this skill.

DimensionReasoningScore

Specificity

"implements stories and code changes" names the domain plus one or two actions, but coverage is not comprehensive — testing, acceptance-criteria handling, and review are absent. It sits at anchor 3: more concrete than a bare domain claim (2) but not the several specific actions of anchor 4.

3 / 5

Completeness

It explicitly answers both parts: "Senior software engineer who implements stories and code changes" (what) and "Use when the user asks to talk to Amelia or requests the developer agent" (when). The when-clause is explicit but could be more specific and concrete, matching anchor 4 rather than anchor 5's comprehensive trigger phrases.

4 / 5

Trigger Term Quality

"talk to Amelia" and "requests the developer agent" are relevant trigger phrases, but common variations users would naturally say ("implement a story", "write code", "senior developer") are missing. This matches anchor 3 — some relevant keywords, missing synonyms and variations — rather than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"talk to Amelia" and "the developer agent" give clear niche triggers with minimal conflict risk, though "implements stories and code changes" overlaps broadly with generic development skills. This is anchor 4 (mostly distinct, minor overlap with closely related skills), not anchor 5's fully distinct trigger set.

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

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.