blocked-task-state

Authoritative protocol for signaling blocked or input-required task states. Mandates targeted A2A pings using the Task.state envelope rather than global capacity broadcasts. Triggers: Use this skill whenever your execution becomes blocked, requires explicit operator input, or encounters a failure that halts progress.

Quality

86%

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.

The body is an exemplary lean redirect: a tight overview that delegates the detailed protocol to a single, well-structured one-level-deep reference. It loses only a little on actionability and workflow clarity because the executable message examples and validation loops are deferred to that reference rather than shown inline.

Dimension	Reasoning	Score
Conciseness	The body is two sentences with zero padding — it states a prohibition and a single concrete redirect, assuming Claude's competence and spending no tokens on concepts Claude already knows.	5 / 5
Actionability	It names the exact tool (`view_file`) and the exact file path with a clear precondition ("before sending any A2A messages"), which is executable guidance, but the actual message-format and payload examples for common cases live in the deferred reference rather than inline.	4 / 5
Workflow Clarity	A clear sequence is present — detect blocked state, do NOT broadcast global idle, read the reference, adhere before messaging — with the gating checkpoint "before sending any A2A messages", though explicit validation/verification steps are not stated in the body (they reside in the reference).	4 / 5
Progressive Disclosure	The body is a concise overview pointing one level deep to a real, well-organized reference file (`.agents/skills/blocked-task-state/references/blocked-task-state-workflow.md`) with no further nesting, splitting content appropriately and making navigation easy.	5 / 5
	Total	18 / 20 Passed

Description

87%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 strong: it clearly states a specific niche, mandates concrete protocol actions, and provides an explicit trigger clause covering blocked, input-required, and failed states. The only soft spot is trigger-term variety, where a few more synonyms would round out coverage.

Dimension	Reasoning	Score
Specificity	"Mandates targeted A2A pings using the Task.state envelope rather than global capacity broadcasts" names several concrete actions for a narrow domain, but the full action set (payload schema, negative examples) is deferred to the reference, leaving minor coverage gaps rather than comprehensive enumeration.	4 / 5
Completeness	It explicitly answers both what ("Authoritative protocol for signaling blocked... task states. Mandates targeted A2A pings using the Task.state envelope...") and when ("Triggers: Use this skill whenever your execution becomes blocked, requires explicit operator input, or encounters a failure that halts progress.") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The trigger clause surfaces natural phrases a user/agent would say — "becomes blocked", "requires explicit operator input", "failure that halts progress" — giving good coverage, though it omits several synonyms and variations that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (blocked-task A2A state coordination via the Task.state envelope vs. global capacity broadcasts) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 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: neomjs/neo
Path: .agents/skills/blocked-task-state/SKILL.md
Commit: 210c03c

Reviewed: 10 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.