agently-request

Use for Agently request-side setup and contracts: model settings, Prompt/input/output design, effect tuning, missing or redundant context, structured output, LongContent, auto_continue, response reuse, streaming, TTS/STT audio, session memory, embeddings, and retrieval within one request family. Use agently-design for cross-node data flow and model/Host ownership.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 well-architected instruction skill: lean directive prose, strong progressive disclosure via a verified Read-by-Need index, and concrete API-level guidance with validation feedback loops. It falls just short of full actionability because it relies on inline method signatures rather than complete executable examples.

Suggestions

Add one or two short, complete runnable ModelRequest code snippets (e.g. a minimal .input/.info/.instruct/.output chain) to lift actionability from concrete guidance to copy-paste ready.

Consider a compact numbered "request setup checklist" so the validation ordering (schema → offered keys → authorization → deterministic constraints before dispatch) reads as an explicit sequence rather than a prose rule.

Dimension	Reasoning	Score
Conciseness	The body is dense, directive, and assumes Claude's domain competence throughout — it never explains concepts Claude already knows and contains no padded prose, with every line stating a normative rule.	5 / 5
Actionability	Guidance is concrete and specific — exact method names like ".input(...)", ".info(...)", ".instruct(...)", ".output(...)", ".image(question=..., file=...\|url=...)", ".auto_continue()" and explicit field-placement rules — but there are no complete copy-paste code blocks covering common cases, leaving minor gaps.	4 / 5
Workflow Clarity	Validation checkpoints and a feedback loop are present ("Validate schema, offered keys, authorization, and deterministic constraints before a real call or side effect" and repair-after-failure guidance), though the content is organized as themed guidance rather than a strictly sequenced procedural workflow.	4 / 5
Progressive Disclosure	The "Read by Need" section maps each topic to a real, one-level-deep bundle file (audio.md, model-setup.md, prompt-management.md, output-control.md, model-request-result.md, session-memory.md, knowledge-base.md — all verified present), keeping the body a lean overview with well-signaled navigation.	5 / 5
	Total	18 / 20 Passed

Description

88%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, concrete description with an explicit trigger clause and a comprehensive capability list, scoped to a single request family with clear boundary guidance against agently-design. Trigger-term naturalness is slightly reduced by product-internal jargon, and not all sibling-skill conflicts are disambiguated in the description itself.

Suggestions

Add a brief in-description disambiguation against agently-triggerflow (e.g. "Use agently-triggerflow when a later step needs a tool result or host computation") to reduce overlap risk with sibling Agently skills.

Soften product-internal terms like "LongContent" and "auto_continue" with a natural-language gloss (e.g. "long-output delivery") so non-expert users can still trigger the skill.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete capabilities ("model settings, Prompt/input/output design, effect tuning, ... structured output, LongContent, auto_continue, response reuse, streaming, TTS/STT audio, session memory, embeddings, and retrieval"), giving comprehensive coverage of the request-side domain rather than vague language.	5 / 5
Completeness	It explicitly opens with a "Use for ..." trigger phrase and pairs it with a concrete what-list of capabilities, clearly answering both what the skill does and when to use it.	5 / 5
Trigger Term Quality	It covers many natural domain terms a developer would say ("structured output", "streaming", "session memory", "embeddings", "retrieval", "TTS/STT"), but leans on product-internal jargon ("LongContent", "auto_continue") that not every user would naturally voice, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche ("within one request family") and explicitly redirects cross-node work to "agently-design", but sibling Agently skills (e.g. agently-triggerflow, only disambiguated in the body) still pose minor overlap risk.	4 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: AgentEra/Agently-Skills
Path: skills/agently-request/SKILL.md
Commit: b281fe2

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.