CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-build-auto

Implements one story, feature, or bug fix end to end without human interaction: plan, code, review, verify, report status. Use when invoked by name, usually by an orchestrator

Quality

83%

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

The canonical home for this skill is bmad-build in bmad-code-org/BMAD-METHOD

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exemplary dispatcher body: one exact command, unambiguous substitution rules, and exhaustive failure-mode handling with no wasted tokens. The only structural weakness is at the bundle level — two reference files ship alongside the skill but are never referenced or navigated to from the body, and the substantive workflow (including its validation steps) is delegated to runtime-rendered output the body cannot show.

Suggestions

Either reference the files in references/ from the body (e.g. a short '## References' section stating when claims-check.md and deletion-check.md apply) or remove them from this skill's bundle, since they currently address a different skill's workflow ('Edge Case Hunter') and are undiscoverable.

Add one line setting expectations that the rendered workflow includes its own review/verify checkpoints, so the delegation of validation to the printed output is explicit rather than implied.

DimensionReasoningScore

Conciseness

Every line instructs ("Run the following command exactly once without changing the current working directory", "Replace `{project-root}` with the nearest folder containing `_bmad/`") with zero concept explanations or padding; roughly 20 lines total. It matches the lean-and-efficient anchor — nothing explains what Claude already knows, so it is not a 4 with trimmable over-explanation.

5 / 5

Actionability

The body gives a fully executable command with precisely defined placeholder substitution rules, exact flag appends ("append `--set workflow.route=<value>`"), enumerated option values (oneshot/full; none/quick/thorough), and concrete handling for every failure mode. It is copy-paste ready modulo two clearly-specified placeholders, matching the fully-executable anchor rather than the minor-gaps anchor at 4.

5 / 5

Workflow Clarity

The sequence is unambiguous — run once in place, follow the printed workflow, with explicit branches for HALT ("report the reason and stop"), a missing script (offer setup, then re-run: a real feedback loop), and other failures including uv being unavailable. It is not a 5 because validation of the core implementation work itself is entirely delegated to the rendered workflow's output rather than present in the body, a minor checkpoint gap; it is well above anchor 3 since no failure branch is left implicit.

4 / 5

Progressive Disclosure

The body itself is well-organized and appropriately lean, but the bundle contains reference files (references/claims-check.md, references/deletion-check.md) that the body never mentions or links, so navigation to them is absent — matching the anchor where references are present but not clearly signaled. It is not a 4 because the provided bundle structure shows zero referenced paths, a real organization gap rather than a minor one; it is above 2 because the body is not a monolith and nothing that belongs in separate files is inlined.

3 / 5

Total

17

/

20

Passed

Description

72%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 with a crisp third-person capability list and an explicit 'Use when' clause. Its main weakness is trigger language: the 'when' rests on an invocation mechanism ('invoked by name, usually by an orchestrator') rather than natural user phrases, and it misses common synonyms like task, ticket, or issue.

Suggestions

Rewrite the trigger clause around natural user phrasing, e.g. 'Use when asked to implement a story, feature, or bug fix, or when an orchestrator invokes this skill by name.'

Add common synonyms and variations users say for this work — 'task', 'ticket', 'issue', 'build', 'implement' — so the description triggers on natural language, not just name invocation.

DimensionReasoningScore

Specificity

"Implements one story, feature, or bug fix end to end" plus the explicit action list "plan, code, review, verify, report status" names multiple concrete actions covering the full lifecycle with no evident gaps, matching the comprehensive-coverage anchor. It is not a 4 because no minor coverage gaps are visible in the enumerated workflow stages.

5 / 5

Completeness

Both parts are present: the 'what' is clear ("Implements one story, feature, or bug fix end to end... plan, code, review, verify, report status") and the 'when' is explicit ("Use when invoked by name, usually by an orchestrator"). It is not a 5 because the 'when' clause lacks concrete trigger phrases a user would actually say, fitting the anchor where 'when' could be more explicit or specific.

4 / 5

Trigger Term Quality

Domain nouns like "story", "feature", and "bug fix" are relevant keywords, but the trigger clause "Use when invoked by name, usually by an orchestrator" describes an invocation mechanism rather than natural user phrasing, and common variations (task, ticket, issue, build, implement) are absent. It does not reach 4 because keyword coverage is not good enough to be 'noticeably above the midpoint' — several natural terms users would say are missing.

3 / 5

Distinctiveness Conflict Risk

The framing "without human interaction" plus "invoked by name, usually by an orchestrator" carves out a distinct autonomous-build niche, leaving only minor overlap risk with general implement-a-feature coding skills. It is not a 5 because "Implements one story, feature, or bug fix" could still collide with generic build/implement skills if name invocation is not followed.

4 / 5

Total

16

/

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-build-auto/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.