CtrlK
BlogDocsLog inGet started
Tessl Logo

bmad-dev-story

Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan"

68

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 highly actionable, well-sequenced workflow with strong validation checkpoints and feedback loops. Its main weaknesses are verbosity/redundancy and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Remove the verbatim repetition of the "Your Role" critical rules inside the <workflow> block (lines 77-86) since they already appear at lines 11-17, to recover token budget.

Factor the long <output> message templates (e.g. the no-ready-for-dev options block) into a short reference file or compact them, keeping SKILL.md as an overview that points to detail.

Tighten the XML scaffolding and consolidate the duplicated sprint-status / non-sprint discovery branches in Step 1 to reduce structural redundancy.

DimensionReasoningScore

Conciseness

The ~500-line body is mostly actionable but padded: the critical rules from the "Your Role" block are repeated verbatim inside <critical> tags later, and verbose <output> templates plus XML scaffolding could be tightened, matching the score-2 anchor rather than a lean score-3.

2 / 3

Actionability

Provides fully concrete, executable guidance — exact commands (e.g. the resolve_customization.py invocation and `git rev-parse HEAD`), exact section/field names, and exact status values — matching the score-3 copy-paste-ready anchor.

3 / 3

Workflow Clarity

Ten sequenced steps with explicit validation gates, HALT conditions, and fix-and-retry feedback loops (Steps 7-9) match the score-3 anchor for a clear sequence with checkpoints and error-recovery loops.

3 / 3

Progressive Disclosure

The entire workflow is inline as one monolithic document with no bundle files or one-level-deep reference split; section/step structure provides some organization (score 2) but content that could be separate remains inline rather than the score-3 overview-plus-references pattern.

2 / 3

Total

10

/

12

Passed

Description

90%

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 is well-formed: it pairs a concrete statement of purpose with explicit, natural-language use-when triggers and a distinctive niche. Its only weakness is that the capability statement names a single action rather than enumerating several concrete actions.

DimensionReasoningScore

Specificity

Names the domain and a concrete action ("Execute story implementation following a context filled story spec file") but does not enumerate multiple specific actions, matching the score-2 anchor rather than the multi-action score-3 anchor.

2 / 3

Completeness

Explicitly answers both what it does and when to use it via the "Use when the user says..." clause, satisfying the score-3 anchor for an explicit what-and-when trigger.

3 / 3

Trigger Term Quality

Includes verbatim natural-language triggers users would actually say ("dev this story [story file]" and "implement the next story in the sprint plan"), giving good coverage of natural trigger phrasing.

3 / 3

Distinctiveness Conflict Risk

The BMAD story-implementation niche with distinctive verbatim triggers is unlikely to fire for unrelated skills, matching the score-3 clear-niche anchor.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (501 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
bmad-code-org/BMAD-METHOD
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.