agently-stage

Use for Agently-Stage process-local task lifetime and sync/async interop: Stage scopes and handles, settlement/cancellation, StageCallBridge and StageStream, Tunnel replay channels, or local EventEmitter listeners. Choose this even inside TriggerFlow when a provider-owned sync wrapper bridges an async SDK; use TriggerFlow for application workflow orchestration or persistence.

Quality

85%

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

78%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.

Well-structured, lean reference skill with clear progressive disclosure and concrete decision guidance. The main gaps are the absence of executable code examples and a time-sensitive version pin in the lead that would fit better in a compatibility note.

Suggestions

Move the version requirement ("Agently 4.1.4.7+ requires agently-stage>=0.3.8,<0.4.0") into a dedicated compatibility/requirements note so the lead stays evergreen.

Add one short copy-paste code snippet per Boundary branch (e.g. `async with Stage(): ...` and `handle = Stage.go(...); await handle.async_get()`) to lift actionability from concrete-named to executable.

Add an explicit validation checkpoint in Invariants, e.g. "assert wait_settled() returned before reporting task completion", to give the workflow a concrete feedback step.

Dimension	Reasoning	Score
Conciseness	Lean, dense technical guidance with no padding or explanation of concepts Claude already knows, but the lead version pin ("Agently 4.1.4.7+ requires agently-stage>=0.3.8,<0.4.0") is time-sensitive information not placed in a deprecated/old-patterns section.	4 / 5
Actionability	The Boundary section gives a concrete, executable selection guide with named APIs ("async with Stage()", "Stage.go(...) plus StageHandle", "get()/async_get()", "wait_settled()/async_wait_settled()"), though it stops short of copy-paste code snippets.	4 / 5
Workflow Clarity	The Boundary section is a well-ordered decision sequence (pick the smallest surface matching the caller) and the Invariants section provides guardrails, but there are no explicit validation checkpoints or feedback loops.	4 / 5
Progressive Disclosure	A "Read by Need" section signals two real one-level-deep references (references/task-lifecycle.md, references/bridges-streams-events.md) with topic descriptions, keeps the overview in SKILL.md, and routes out-of-scope topics to sibling skills.	5 / 5
	Total	17 / 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 names concrete capabilities, gives explicit trigger guidance, and disambiguates adjacent skills. Its only weakness is that trigger terms are technical API names rather than natural conversational phrases.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — "Stage scopes and handles, settlement/cancellation, StageCallBridge and StageStream, Tunnel replay channels, or local EventEmitter listeners" — giving comprehensive coverage of the skill's surface.	5 / 5
Completeness	Explicitly answers both "what" (process-local task lifetime and sync/async interop with named surfaces) and "when" ("Use for ..."; "Choose this even inside TriggerFlow when a provider-owned sync wrapper bridges an async SDK; use TriggerFlow for application workflow orchestration or persistence").	5 / 5
Trigger Term Quality	Good keyword coverage of the domain's natural API names (Stage, StageCallBridge, StageStream, Tunnel, EventEmitter, TriggerFlow), but the terms are heavily technical with few conversational synonyms a user would phrase unprompted.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Agently-Stage process-local lifetime) with explicit disambiguation against TriggerFlow and the implied agently-runtime, actively steering the user away from the wrong skill.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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

Reviewed: 5 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.