CtrlK
BlogDocsLog inGet started
Tessl Logo

think

Turns rough ideas into approved, decision-complete plans with validated structure before coding. Use when users ask in any language for planning, architecture, design direction, feasibility, value judgment, or whether a feature is worth doing before implementation. Not for bug fixes or small edits.

68

Quality

84%

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

The canonical home for this skill is think in tw93/Waza

SKILL.md
Quality
Evals
Security

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.

A well-structured, directive planning skill with concrete thresholds, checklists, feedback loops, and exemplary one-level-deep progressive disclosure. The body is efficient but carries a few rhetorical sentences and abstract directives that keep conciseness, actionability, and workflow_clarity just under full marks.

Suggestions

Trim rhetorical justification sentences (e.g. the "discards the iterations someone else already paid for" line) to pure directives to lift conciseness toward 5.

Add one short worked example of a completed approved-plan output with filled-in fields, so abstract directives like "deform the design to survive its failure" have a concrete, copy-paste-ready reference and improve actionability.

Open with a single numbered core sequence (preflight → check official solutions → propose → validate → simplicity gate → handoff) so the mode-based sections hang off one explicit ordering and improve workflow clarity.

DimensionReasoningScore

Conciseness

The body is mostly lean and directive with concrete thresholds (8 files, 3 components), but a few rhetorical justification sentences (e.g. "First-principles design next to a proven implementation discards the iterations someone else already paid for.") could be trimmed to pure directives, keeping it just below the lean-every-token-earns-its-place anchor.

4 / 5

Actionability

Guidance is largely concrete (specific thresholds, a defined Output template, named rules), but several directives stay abstract ("deform the design to survive its failure", "state what evidence would change it"), which is actionable guidance rather than fully copy-paste-ready steps.

4 / 5

Workflow Clarity

There is a clear progression with checkpoints and checklists (Validate Before Handoff, red-flags self-check, Simplicity Gate, approval gates) plus feedback loops, but the flow is organized as conditional modes/gates rather than one explicit linear numbered sequence, leaving minor sequencing gaps.

4 / 5

Progressive Disclosure

The body is a clear overview that points to three well-signaled one-level-deep reference files (durable-context.md, mode-evaluation.md, mode-triage.md), each stating when to load it; all referenced files exist and contain no nested references, matching the clear-overview anchor.

5 / 5

Total

17

/

20

Passed

Description

90%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 explicitly answers what, when, and what-not, with comprehensive multilingual trigger terms and a clear negative boundary. The only soft spot is specificity, where the core capability is expressed as one abstract action rather than a list of concrete actions.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action ("Turns rough ideas into approved, decision-complete plans with validated structure"), but frames it as a single abstract action rather than listing several specific concrete actions, so it sits at the anchor-3 level rather than 4.

3 / 5

Completeness

It clearly states both what (turn rough ideas into approved, decision-complete plans) and when (explicit trigger phrases), and adds a negative scope clause ("Not for bug fixes or small edits"), matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

The explicit "Use when users ask in any language for planning, architecture, design direction, feasibility, value judgment, or whether a feature is worth doing" clause gives comprehensive natural-term coverage with synonyms (feasibility / value judgment / worth doing) and a multilingual signal, matching the comprehensive-synonym anchor.

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche (pre-implementation planning/design) with distinct triggers and an explicit exclusion ("Not for bug fixes or small edits"), giving minimal overlap risk with code-editing skills.

5 / 5

Total

18

/

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
tw93/Waza
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.