agently-runtime

Use for Agently runtime extension surfaces: Actions and MCP, ExecutionResource lifecycle, TaskWorkspace file capabilities, RecordStore durability, auto_func and KeyWaiter helpers, FastAPIHelper transport, or optional agently-devtools observation and evaluation.

Quality

83%

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

82%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, well-structured guidance skill with concrete API-level directives, a clear owner-boundary table, and appropriate one-level-deep references to real bundle files. Its weaknesses are the absence of runnable examples and one broken reference path.

Suggestions

Fix or remove the missing reference `../agently/references/context-and-skills.md` (the file does not exist in the bundle) so every "Read by Need" link resolves.

Add one short copy-paste-ready example for the most common case (e.g. registering an action via `@agent.action_func` and dispatching through `agent.use_actions(...)`) to lift actionability to fully executable.

Consider adding explicit verification checkpoints (e.g. a validate-then-dispatch checklist) to the Runtime Rules to make the workflow sequencing as concrete as the Fail Closed section.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean — "Prefer `@agent.action_func`", "Persist resource descriptors, never live clients or secrets" — with no padding and no explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Concrete directives cite specific APIs ("Use a fresh `agent.create_execution()`", "`agent.create_task(...)`", "`create_task_loop(...)`"), giving mostly executable guidance, though there are no complete runnable examples covering common cases.	4 / 5
Workflow Clarity	Decision rules are clearly sequenced — "validate schema, authorization, and policy before dispatch", the Fail Closed section ("validate it against the offered set, then reconstruct canonical records") — with explicit validation for risky permission/side-effect operations, but it is rule-based guidance rather than a numbered workflow with explicit checkpoints.	4 / 5
Progressive Disclosure	A well-organized overview splits detail into one-level-deep references via "Read by Need", each clearly signaled, and the four local reference files (actions-runtime, actions-execution-resource, helpers-and-services, devtools) exist; however one referenced path, `../agently/references/context-and-skills.md`, is missing from the bundle, leaving a navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

83%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 specific, well-scoped description that names many concrete Agently runtime surfaces and opens with an explicit "Use for" trigger. It is highly distinctive; the main weakness is that trigger terms are framework jargon rather than natural user phrasings.

Suggestions

Add a few natural-language trigger phrasings or synonyms a user might actually say (e.g. "when extending the Agently runtime", "Agently actions/MCP", "runtime lifecycle") alongside the framework nouns.

Reframe the capability list toward verb-based actions (e.g. "Define Actions and MCP tools, manage ExecutionResource lifecycle, store durable records") so the "what" reads as actions rather than a noun list.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete capabilities — "Actions and MCP, ExecutionResource lifecycle, TaskWorkspace file capabilities, RecordStore durability, auto_func and KeyWaiter helpers, FastAPIHelper transport" — giving comprehensive coverage of the domain's surfaces.	5 / 5
Completeness	Both "what" (enumerated runtime extension surfaces) and "when" (explicit "Use for" clause) are present; the "what" is a capability list rather than verb-based actions, so it is explicit but could be more concrete as verbs.	4 / 5
Trigger Term Quality	Good keyword coverage across named surfaces under an explicit "Use for" trigger, but the terms are internal framework nouns (Actions, MCP, RecordStore) rather than natural user phrasings, synonyms, or file extensions a user would actually say.	4 / 5
Distinctiveness Conflict Risk	A clear niche ("Agently runtime extension surfaces") anchored by distinct named subsystems yields minimal overlap risk with other skills.	5 / 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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: AgentEra/Agently-Skills
Path: skills/agently-runtime/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.