bmad-advanced-elicitation

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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.

Well-structured, actionable skill body that uses a script to keep the method catalog out of context and provides clear menu-driven workflow with checkpoints. Templated path placeholders and slight menu-logic repetition are the only gaps.

Dimension	Reasoning	Score
Conciseness	The body is lean procedural guidance with no padding or explanation of concepts Claude already knows, but the menu logic repeats "offer the menu again" across several branches, leaving minor instances that could be tightened.	4 / 5
Actionability	Concrete executable commands are given (`uv run {skill-root}/scripts/pick_methods.py ...` with specific subcommands and flags), but the paths are templated placeholders requiring resolution, keeping it just below copy-paste ready.	4 / 5
Workflow Clarity	A clear sequence (On Activation → Serving the Catalog → Menu → Running a Method) with explicit HALT checkpoints and an apply/reject/proceed feedback loop plus a customization-failure fallback, though it lacks a full validate-then-retry checklist.	4 / 5
Progressive Disclosure	The catalog is served via `scripts/pick_methods.py` "so it never enters context whole", with one-level-deep references to real bundle files (assets/methods.csv, scripts/) clearly signaled and well organized.	5 / 5
	Total	17 / 20 Passed

Description

87%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 trigger conditions with concrete named methods. Minor room to broaden trigger synonyms and add more specific action verbs.

Dimension	Reasoning	Score
Specificity	"reconsider, refine, and improve its recent output" names the domain (LLM output refinement) and several concrete actions, but the verbs stay somewhat abstract rather than enumerating comprehensive capabilities, fitting the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	It explicitly answers both what ("Push the LLM to reconsider, refine, and improve its recent output") and when ("Use when user asks for deeper critique or mentions a known deeper critique method") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"deeper critique", "socratic", "first principles", "pre-mortem", "red team" give strong natural keyword coverage users would actually say, but a few common synonyms (e.g. devil's advocate, steelman) are absent, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The refinement-checkpoint niche plus named critique methods (socratic, pre-mortem, red team) form a clear, distinct trigger surface with minimal overlap against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: src/core-skills/bmad-advanced-elicitation/SKILL.md
Commit: 05bfbd4

Reviewed: 15 days ago

Table of Contents

Discovery Implementation Validation

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.