agently-request

Use when shaping or collaboratively reviewing one Agently request family: model/settings setup, business Prompt contracts, structured output and validation, result or stream consumption, Session memory, embeddings, RecordStore retrieval, or retrieval-backed answers.

Quality

84%

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

76%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, densely actionable instruction-only body that avoids padding and uses one-level-deep references well. Its main weakness is workflow clarity — destructive/batch operations lack an explicit validate→fix→retry loop — plus one broken cross-source reference.

Suggestions

Add an explicit numbered validate→fix→retry sequence (e.g. schema/ensure failure → shallower projection or coherent split → Host reconstruction → re-validate before the real call) so destructive/batch operations have a feedback loop.

Fix or remove the broken cross-source reference to '../agently/references/context-and-skills.md', which does not resolve to an existing file.

Consider a brief 'Quick start' one-off fluent chain example (`.input(...).info(...).instruct(...).output(...)` → result call) so the canonical happy path is immediately actionable.

Dimension	Reasoning	Score
Conciseness	Dense, lean normative guidance that assumes Claude's competence — no padded concept explanations, just directives like '.input/.info/.instruct/.output' placements and concrete invariants.	5 / 5
Actionability	Concrete, specific directives (e.g. '.image(question=..., file=...\|url=...)', '[[ref:<ref_id>]]', 'ModelRequestResult' vs 'AgentExecutionResult') give executable guidance; absent copy-paste code is acceptable for an instruction-only skill but keeps it just short of fully executable.	4 / 5
Workflow Clarity	Declarative rules and an 'Avoid' list provide direction, and 'Validate schema, offered keys, authorization...before a real call or side effect' is mentioned, but there is no explicit sequenced validate→fix→retry feedback loop for the destructive/batch operations the skill describes.	3 / 5
Progressive Disclosure	The 'Read by Need' section maps each topic to a one-level-deep reference file with clear signaling; however, the cross-source reference '../agently/references/context-and-skills.md' does not resolve to a real file, leaving a navigation gap.	4 / 5
	Total	16 / 20 Passed

Description

92%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, specific description that explicitly states both what it does and when to use it, enumerating concrete capability domains and cleanly distinguishing itself from a sibling skill. Trigger-term quality is the only slight weakness, favoring Agently brand vocabulary over natural user phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability domains — 'model/settings setup, business Prompt contracts, structured output and validation, result or stream consumption, Session memory, embeddings, RecordStore retrieval, or retrieval-backed answers' — giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (the enumerated request-family capabilities) and 'when' (opens with 'Use when shaping or collaboratively reviewing one Agently request family').	5 / 5
Trigger Term Quality	Good coverage of domain terms ('structured output and validation', 'Session memory', 'embeddings', 'RecordStore retrieval') with an explicit 'Use when' trigger, but leans on Agently brand vocabulary over natural user phrases and omits common synonyms/file extensions.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'one Agently request family' and clearly separated from the sibling agently-triggerflow skill, giving it a distinct niche with minimal conflict risk.	5 / 5
	Total	19 / 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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: AgentEra/Agently-Skills
Path: skills/agently-request/SKILL.md
Commit: 5dc8d96

Reviewed: 3 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.