CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

async-repl-protocol

Async REPL Protocol

Quality

67%

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 ./.claude/skills/archive/async-repl-protocol/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 is concise, well-structured, and provides executable code patterns for both rules, with only a minor defect in the truncated second example. It is a strong, token-efficient skill body.

DimensionReasoningScore

Conciseness

The body is lean and efficient, stating only the two rules with minimal code and assuming Claude's competence (no explanation of async/await or what a REPL is), matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Rule 1 gives concrete executable patterns ('await view_file(path)', 'await ask_memory(...)') and rule 2 gives an executable GOOD example, but the BAD example is truncated mid-block and the code fence is left unterminated, a minor gap that keeps it just below the fully copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

This is a simple skill with two clearly numbered, unambiguous rules and no destructive or batch operation requiring validation, so the simple-skill exception applies and the actions are unambiguous enough for a 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (no bundle files exist), and is well organized with a title, intro, and numbered rule subheadings, matching the simple-skill exception for a 5 with just well-organized sections.

5 / 5

Total

19

/

20

Passed

Description

28%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 is essentially just a title with no concrete actions and no use-when trigger guidance, leaving both the 'what' and 'when' weakly answered. It carves out a roughly specific niche but needs actionable verbs and an explicit trigger clause.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Runs tool calls and returns results inside Agentica's async REPL harness, awaiting Future-returning tools and keeping each response to a single code block.'

Add an explicit 'Use when...' trigger clause, e.g. 'Use when testing tools or evaluating responses in Agentica's async REPL harness.'

Include natural trigger terms users would actually say (e.g. 'async REPL', 'REPL harness', 'tool testing') rather than only the bare name 'Async REPL Protocol'.

DimensionReasoningScore

Specificity

The description 'Async REPL Protocol' names the domain (async REPL) but states no concrete actions whatsoever, fitting the 'names the domain but actions are minimal or generic' anchor better than the entirely-vague anchor 1 and well below the '1-2 concrete actions' anchor 3.

2 / 5

Completeness

It offers only a vague 'what' (the name of a protocol) and no 'when', matching the 'Has a vague what and no when' anchor; the missing explicit trigger guidance caps it low per the rubric guideline.

2 / 5

Trigger Term Quality

'async' and 'REPL' are relevant keywords a user of this harness might say, but there is no 'Use when...' phrasing and the natural trigger phrases users would say are missing, matching the 'one or two generic keywords; missing the natural phrases' anchor.

2 / 5

Distinctiveness Conflict Risk

'Async REPL Protocol' is a fairly specific niche, but as a bare title it could still overlap with other testing/REPL skills, matching the 'somewhat specific but could still overlap' anchor.

3 / 5

Total

9

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

description_field

'description' is very short (19 chars), consider making it more detailed

Warning

Total

15

/

16

Passed

Repository

parcadei/Continuous-Claude-v3

Path

.claude/skills/archive/async-repl-protocol/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.