CtrlK
BlogDocsLog inGet started
Tessl Logo

bmad-technical-research

Deprecated — forwards to bmad-deep-recon (technical type).

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./src/bmm-skills/v6-shims/bmad-technical-research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 well-structured, actionable deprecation shim: it provides an executable customization step, an explicit handoff to bmad-deep-recon with the right parameters, and a clear stopping point, with only minor verbosity in the opening summary.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete steps and no explanation of concepts Claude already knows, but the opening sentence's full enumeration of bmad-deep-recon's surface (draft/process/run modes, six research types, custom shapes) is informational padding that could be tightened, matching the 'mostly efficient but could be tightened' anchor rather than the fully lean 3-anchor.

2 / 3

Actionability

It gives an executable command (`uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`), explicit invocation parameters (research type technical, the four legacy fields, original input verbatim), and a clear stopping directive, matching the 'fully executable guidance; copy-paste ready' anchor.

3 / 3

Workflow Clarity

The 'On Activation' section is a clearly numbered 3-step sequence with an explicit handoff and stop condition ('bmad-deep-recon takes the workflow from here — do not execute any further steps in this shim'); as a simple non-destructive forwarding shim, the simple-skills note allows a 3 without validation feedback loops.

3 / 3

Progressive Disclosure

At under 50 lines with no bundle files and no need for external references, the well-organized sections (deprecation heading, summary paragraph, 'On Activation' steps) satisfy the rubric's note that such simple skills can score 3 on structure alone.

3 / 3

Total

11

/

12

Passed

Description

35%

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 accurately signals deprecation and the forwarding target but is thin as a discovery description: it relies on internal skill names rather than natural user trigger terms and omits any 'when to use' guidance.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., legacy bmad-technical-research invocations), even though it is deprecated.

Include a couple of natural trigger terms a user might say (e.g., 'technical research', 'deep research on a technical topic') rather than only the internal skill name 'bmad-deep-recon'.

Briefly enumerate the concrete actions the underlying skill performs (drafting research prompts, processing reports, running research) to lift specificity toward the 3-anchor.

DimensionReasoningScore

Specificity

The description names a domain ("technical" research) and one concrete action ("forwards to bmad-deep-recon"), matching the 'names domain and some actions, but not comprehensive' anchor rather than the vague single-action anchor at 1 or the multiple-specific-actions anchor at 3.

2 / 3

Completeness

It states what the skill does ("forwards to bmad-deep-recon (technical type)") but provides no 'Use when...' trigger guidance, so per the rubric's cap a missing explicit trigger holds it at 2 rather than 3.

2 / 3

Trigger Term Quality

It contains only internal skill identifiers ("bmad-deep-recon") and the word "forwards" — not terms a user would naturally say when they need this skill — matching the 'no natural keywords; technical jargon' anchor.

1 / 3

Distinctiveness Conflict Risk

It is scoped to a specific named skill and the technical research type, but offers no distinct natural triggers and could overlap with sibling research-type skills, matching the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

7

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.