CtrlK
BlogDocsLog inGet started
Tessl Logo

multi-agent-brainstorming

Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.

52

Quality

57%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/multi-agent-brainstorming/SKILL.md

The canonical home for this skill is multi-agent-brainstorming in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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.

The body lays out a well-sequenced, gated multi-agent review process with explicit roles and a hard-stop checklist, but it is padded with redundant restatements and lacks concrete invocation prompts for most reviewer agents.

Suggestions

Collapse the redundant Purpose / Failure Modes / Key Principles / Final Reminder sections into a single concise block to reduce token padding.

Provide a copy-ready prompt template for each reviewer agent (Skeptic, Constraint Guardian, User Advocate, Arbiter), not just the Skeptic example.

Remove the stray empty bullet in the Exit Criteria list and tighten the objection-resolution recovery path (e.g., what the Arbiter does when objections remain unresolved after a revision round).

DimensionReasoningScore

Conciseness

Mostly efficient with tight role/process bullets, but Purpose, 'Failure Modes This Skill Prevents', 'Key Principles', and 'Final Reminder' restate the same ideas, and a stray empty bullet sits in the Exit Criteria list — tightening would remove padding.

3 / 5

Actionability

Roles carry explicit May/May NOT mandates and a sequenced process, but only one reviewer has a concrete prompt example ('Assume this design fails in production. Why?'); the other agents lack copy-ready invocation prompts, leaving key execution details missing.

3 / 5

Workflow Clarity

A clear three-phase sequence with ordered reviewer invocation, a mandatory Decision Log, and an explicit Exit Criteria checklist with a 'do not proceed' feedback loop; held at 4 because objection-resolution recovery is only lightly specified.

4 / 5

Progressive Disclosure

Well-organized with clearly headed sections and no external bundle files to navigate; the self-contained structure is appropriate, though the ~250-line body could optionally push detailed role specs into a reference file.

4 / 5

Total

14

/

20

Passed

Description

55%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.

The description clearly states what the skill does with several concrete actions, but omits any explicit 'when to use' trigger guidance and relies on somewhat formal terminology, limiting trigger quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when reviewing or stress-testing a design before implementation, or when the user asks to validate, critique, or peer-review a design').

Include more natural user-facing synonyms such as 'design review', 'brainstorm', and 'critique my design' alongside the formal terms.

Sharpen the distinction from the standard brainstorming skill in the description itself (e.g., 'unlike standard brainstorming, this runs a sequential, role-constrained multi-agent review').

DimensionReasoningScore

Specificity

Lists several concrete actions — 'simulate a structured peer-review process', 'validate designs', 'surface hidden assumptions', 'identify failure modes' — but they sit at a conceptual design level rather than fully concrete operations, leaving minor coverage gaps.

4 / 5

Completeness

The 'what' is clear (simulate a peer-review process to validate designs) but there is no 'Use when...' or equivalent trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant terms like 'peer-review process', 'validate designs', and 'failure modes', but they are somewhat formal and miss common natural synonyms users would actually say (e.g., 'review my design', 'brainstorm', 'critique').

3 / 5

Distinctiveness Conflict Risk

'Structured peer-review process using multiple specialized agents' carves out a niche, but the design-review/validation territory overlaps meaningfully with the standard brainstorming skill it references, leaving overlap risk with closely related skills.

3 / 5

Total

13

/

20

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.