CtrlK
BlogDocsLog inGet started
Tessl Logo

brainstorming

Coordinates collaborative design sessions that explore requirements, analyze codebase context, and produce an approved design document with trade-offs. Use when building a new feature, adding functionality, creating components, modifying behavior, starting a project, or planning any creative work. DO NOT TRIGGER when the user already has a concrete design and just wants implementation.

69

Quality

84%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

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.

This is a well-crafted process skill with excellent workflow clarity, strong actionability through specific commands and file paths, and robust validation checkpoints via HARD-GATE blocks. Its main weaknesses are moderate redundancy (the approval-gating message is repeated three times in slightly different forms) and the monolithic structure that could benefit from splitting detailed sections into referenced files. Overall it effectively guides Claude through a complex collaborative design process.

Suggestions

Consolidate the three HARD-GATE blocks into a single prominent section or a reusable principle reference, rather than repeating the same 'stop and wait' instruction verbatim in multiple places.

Consider extracting the Research Scout Phase and Dialogue sections into separate referenced files to improve progressive disclosure and reduce the main file's length.

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but has some redundancy — the HARD-GATE blocks repeat the same 'stop and wait for approval' instruction three times, the anti-pattern section restates what the checklist already implies, and the process flow diagram duplicates the checklist. The key principles section also partially restates earlier content.

2 / 3

Actionability

The skill provides concrete, specific guidance: exact file paths (docs/plans/YYYY-MM-DD-<topic>-design.md), specific bash commands for worktree detection, named scout types, branch naming conventions (feature/ prefix, kebab-case), and clear invocation targets (kit:git-worktrees, kit:team-orchestration, kit:writing-plans). The checklist is fully actionable with each step specifying what to do.

3 / 3

Workflow Clarity

The workflow is exceptionally clear with a numbered checklist, explicit STOP gates for human approval (validation checkpoints), a re-entry path with detection logic, a graphviz diagram showing the full flow including decision diamonds and feedback loops (revise and re-present), and clear terminal state identification. Error recovery is handled via the revision loop.

3 / 3

Progressive Disclosure

The content is well-structured with clear sections (Overview, Checklist, Re-Entry, Process Flow, Research Scout Phase, Dialogue, After the Design, Key Principles), but it's a fairly long monolithic document. Some content like the detailed scout phase or dialogue guidance could be split into referenced files. However, no bundle files exist, so everything must be inline. The organization within the single file is good but the length pushes it toward a wall of text.

2 / 3

Total

10

/

12

Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that clearly articulates what the skill does (collaborative design sessions producing design documents) and when to use it (with explicit trigger and exclusion clauses). The main weakness is the breadth of trigger terms, which could cause overlap with implementation or project scaffolding skills. The negative trigger clause is a thoughtful addition that helps mitigate conflict risk.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'explore requirements', 'analyze codebase context', 'produce an approved design document with trade-offs'. These are clear, actionable steps describing what the skill does.

3 / 3

Completeness

Clearly answers both 'what' (coordinates collaborative design sessions, explores requirements, analyzes codebase, produces design document) and 'when' (explicit 'Use when...' clause with multiple triggers, plus a 'DO NOT TRIGGER' exclusion clause). This is comprehensive.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'building a new feature', 'adding functionality', 'creating components', 'modifying behavior', 'starting a project', 'planning'. Also includes a helpful negative trigger ('already has a concrete design and just wants implementation') to reduce false matches.

3 / 3

Distinctiveness Conflict Risk

While the design/planning niche is reasonably distinct, terms like 'building a new feature', 'adding functionality', and 'planning any creative work' are broad enough to potentially overlap with implementation-focused or project management skills. The DO NOT TRIGGER clause helps but the trigger scope is still quite wide.

2 / 3

Total

11

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
shousper/claude-kit
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.