CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bmad-customize

Authors and updates customization overrides for installed BMad skills, and changes to the document templates their agents write from. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', 'customize a workflow', or wants a document such as the PRD to ask for, contain or render something different

Quality

92%

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

96%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 exceptionally tight, executable skill body: every command, path, field name, and merge rule is concrete and verifiable against the bundle, and the workflow carries explicit validation, confirmation, and error-recovery loops. The only structural improvement is offloading the inlined Document-templates sub-procedure and merge-semantics reference detail into a separate reference file.

DimensionReasoningScore

Conciseness

The body is telegraphic and dense ("Discover, route, author, write, verify.") with zero padding and no explanations of concepts Claude already knows — every token earns its place. It consistently assumes the reader's competence throughout all sections.

5 / 5

Actionability

Commands are copy-paste ready with exact placeholders ("uv run {skill-root}/scripts/list_customizable_skills.py --project-root {project-root}"), exact file paths and field names (persistent_facts, activation_steps_prepend, facilitate_order, html_view), and explicit merge semantics. The referenced script exists in the bundle and its flags and output fields match the body's claims.

5 / 5

Workflow Clarity

Preflight through Step 6 is clearly sequenced with explicit validation checkpoints (resolver verify, "Never silently overwrite", "Wait for explicit yes"), an error-recovery feedback loop ("Verify shows override didn't land... re-enter Step 4 with the verify output as context"), a manual fallback merge, and a "Complete when" checklist — matching the anchor-5 pattern.

5 / 5

Progressive Disclosure

Good section structure and a real, clearly signaled one-level script reference (scripts/list_customizable_skills.py, verified present). However, at ~120 lines this is not a simple skill, and the entire Document-templates sub-workflow plus merge-semantics detail is inlined in SKILL.md where it could be split into a reference file — a minor organization gap that keeps it below anchor 5.

4 / 5

Total

19

/

20

Passed

Description

83%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 that clearly states both capability and explicit 'Use when' triggers in natural user language. Trigger coverage is good but misses a few synonyms, and a couple of the quoted triggers are generic enough to risk minor overlap with non-BMad customization skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Authors and updates customization overrides for installed BMad skills" and "changes to the document templates their agents write from" — with minor gaps (discovery, verification, and team/user placement are not mentioned). It goes beyond the 1-2 actions of anchor 3 but is not the comprehensive coverage of anchor 5.

4 / 5

Completeness

Explicitly answers both: what it does ("Authors and updates customization overrides... changes to the document templates their agents write from") and when to use it ("Use when the user says 'customize bmad', 'override a skill'...") with concrete trigger phrases — a direct match for the anchor-5 example.

5 / 5

Trigger Term Quality

Triggers 'customize bmad', 'override a skill', 'change agent behavior', 'customize a workflow', and "wants a document such as the PRD to ask for, contain or render something different" are phrases a user would naturally say. A few natural synonyms (e.g. 'personalize', 'tweak', '.toml') are missing, short of the comprehensive coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche (BMad customization overrides and document templates) is clear and 'customize bmad' is a distinct trigger, but 'override a skill' and 'change agent behavior' could plausibly fire for generic skill- or agent-customization tools — minor overlap risk rather than minimal.

4 / 5

Total

17

/

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/core-tools/bmad-customize/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.