CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ste

Write or rewrite text in ASD-STE100 Simplified Technical English. ONLY use this skill when the user explicitly invokes it by name — i.e. they type "/ste" or literally write "use the ste skill" / "apply ASD-STE100". Do NOT trigger it on paraphrased intent such as "simplify this", "make it clearer", "write technical documentation", or "shorter sentences please" — the user has deliberately scoped this skill to explicit invocation only. For those requests, respond normally without loading this skill unless they name it.

Quality

89%

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

86%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 lean, highly actionable rule set with an explicit self-check validation pass and a clean one-level-deep reference structure. The main flaws are cosmetic: a step-numbering gap (Step 0 jumps to Step 2) and some duplication between the core rules and the self-check list.

Suggestions

Fix the step numbering: 'Step 0 — Classify the text' is followed by 'Core rules' and then 'Step 2 — Self-check pass' with no Step 1. Make drafting an explicit numbered step (e.g., 'Step 1 — Draft with the core rules') so the 0→1→2 sequence reads coherently.

Trim the overlap between the Core rules section and the Step 2 self-check list — modals, verb forms, semicolons, and article rules each appear twice. Keep the self-check as terse one-line-per-rule pointers rather than restating the rules.

DimensionReasoningScore

Conciseness

The body is dense, imperative rule-lists with no explanations of concepts Claude already knows, but the Step 2 self-check list restates several core rules nearly verbatim ("should," "would," "could," "may," "might"; contractions/semicolons; -ing verbs), which is a deliberate checklist yet could be tightened.

4 / 5

Actionability

Guidance is fully concrete and executable for an instruction-only skill: exact limits ("maximum 20 words", noun clusters "maximum 3 words"), specific replacements ("'go down' → 'decrease'"), a worked warning example, a 9-item self-check, and a real working dictionary in references/word-substitutions.md (verified to exist).

5 / 5

Workflow Clarity

The sequence — "Step 0 — Classify the text", apply the core rules, then "Step 2 — Self-check pass" with "fix every hit before you respond" — is clear with an explicit validation checklist, but the numbering skips Step 1 and the drafting step itself is only implicit ("Before drafting, replace unapproved vocabulary"), leaving minor gaps against the top anchor.

4 / 5

Progressive Disclosure

Both referenced files (references/word-substitutions.md, references/examples.md) exist, are one level deep with no nested references, and are clearly signaled with purpose and read triggers ("Read it before drafting; it is short" / "Read it when rewriting existing text or when unsure how a rule applies"), with the dictionary and worked examples appropriately split out of SKILL.md.

5 / 5

Total

18

/

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 strongly written description: a concrete capability statement, maximally explicit trigger guidance with both positive and negative examples, and near-zero conflict risk by design. The only minor gap is that a few additional natural invocation variants are not enumerated.

DimensionReasoningScore

Specificity

"Write or rewrite text in ASD-STE100 Simplified Technical English" names the domain and two concrete actions that fully cover this single-purpose skill, placing it above anchor 3 (where coverage would be incomplete) but below anchor 5 (which expects multiple distinct actions listed).

4 / 5

Completeness

It explicitly answers both "what" ("Write or rewrite text in ASD-STE100 Simplified Technical English") and "when" ("ONLY use this skill when the user explicitly invokes it by name") with concrete trigger phrases and counter-examples, matching the top anchor.

5 / 5

Trigger Term Quality

It enumerates natural invocation phrases — "they type \"/ste\" or literally write \"use the ste skill\" / \"apply ASD-STE100\"" — plus explicit anti-triggers like "simplify this" and "make it clearer", but omits a few natural variants such as "Simplified Technical English" or a bare "use STE".

4 / 5

Distinctiveness Conflict Risk

The explicit-invocation-only scoping ("Do NOT trigger it on paraphrased intent such as 'simplify this'...") gives the skill a clear niche with minimal conflict risk against general writing or editing skills.

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

saski/arnesto

Path

.agents/skills/ste/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.