CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

iterative-engineering-design

Use when planning or implementing ambiguous, design-heavy, or cross-cutting engineering changes where the existing system, domain model, lifecycle behavior, or production compatibility must be understood. Helps build and preserve a shared model through design, implementation, and reset. Do not use for code review, audits, explanation-only tasks, narrow fixes, or already-specified mechanical work.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 coherent, opinionated methodology skill with concrete directive guidance and a clear sequenced workflow. Its main weakness is conciseness: the core thesis is restated several times and could be tightened without losing meaning.

Suggestions

Tighten conciseness by collapsing repeated restatements of the 'shared model' thesis into a single canonical statement and trimming section-closing aphorisms that restate the prior section.

Make workflow checkpoints more navigable by converting the prose-embedded review points into a short explicit checklist (e.g. a 'Before extending the implementation' bullet list in the Reset section).

Add one concrete worked micro-example of a proposal-vs-mechanism separation to lift actionability from mostly-executable to fully concrete guidance.

DimensionReasoningScore

Conciseness

The prose is dense and assumes Claude's competence (no basic-concept padding), but recurring restatements of the same thesis (e.g. 'The purpose of the exchange is not compliance or debate. It is to improve the shared model.' is echoed across sections) keep it from being fully lean.

3 / 5

Actionability

Consistently directive with concrete testable heuristics ('creation, partial use, correction, reversal, historical data, and mixed old/new behavior'; 'Ask what becomes known, what must remain attached, what should be cleared, and how the operation can later be undone'); absence of code is unpenalized for an instruction-only skill.

4 / 5

Workflow Clarity

A clear sequenced process across eight sections (understand -> propose -> test against behavior -> evidence -> bounded work -> separate semantics -> reset -> honest collaboration) with explicit review points and a reset feedback loop, though checkpoints are prose-embedded rather than crisp checklists.

4 / 5

Progressive Disclosure

Self-contained with no bundle files and well-organized into eight clear H2 sections; marginally over the 50-line simple-skill exception (~125 lines) so it sits just below the top anchor, but structure and navigation are good.

4 / 5

Total

15

/

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, well-scoped description that explicitly states both what it does and when to use it, reinforced by concrete negative triggers. Voice is correctly third person and trigger terms are natural.

DimensionReasoningScore

Specificity

Names several concrete actions ('planning or implementing...engineering changes', 'build and preserve a shared model through design, implementation, and reset') with only minor coverage gaps; not a full score because the actions are process-oriented rather than a comprehensive discrete-operation list.

4 / 5

Completeness

Explicitly answers both what ('Helps build and preserve a shared model through design, implementation, and reset') and when ('Use when planning or implementing...' plus 'Do not use for...'), with concrete trigger phrases matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural trigger phrasings ('planning or implementing ambiguous...engineering changes', 'design-heavy', 'cross-cutting') plus explicit negative triggers ('code review', 'audits', 'narrow fixes'), giving good keyword coverage though not exhaustive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche (ambiguous design-heavy cross-cutting changes) is sharpened by explicit anti-triggers ruling out code review, audits, explanation-only tasks, narrow fixes, and mechanical work, giving minimal conflict risk.

5 / 5

Total

18

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

openmeterio/openmeter

Path

.agents/skills/iterative-engineering-design/SKILL.md

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.