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

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/blocked-task-state/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

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 efficient, well-structured pointer to a real one-level reference, but its standalone actionability and workflow clarity are partial because the operative steps live in the referenced file.

Suggestions

Add a one-line summary of the core mandated action (e.g. the Task.state values to use) so the body is actionable without opening the reference.

Include a brief inline validation checkpoint (e.g. confirm the targeted recipient is set before sending) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	Three lean sentences with no padding and no explanation of concepts Claude already knows; every token earns its place.	3 / 3
Actionability	Gives a concrete tool and exact path ('use the view_file tool to read ... blocked-task-state-workflow.md') plus a clear prohibition, but the substantive protocol steps are deferred to the reference rather than given inline.	2 / 3
Workflow Clarity	A clear ordering exists ('before sending any A2A messages'), but the body's own workflow is minimal with no validation checkpoints; the real sequenced steps live in the referenced file.	2 / 3
Progressive Disclosure	A clear overview points via an exact path to a single one-level-deep reference that contains the actual protocol (verified: not a further pointer), with content appropriately split and well signaled.	3 / 3
	Total	10 / 12 Passed

Description

75%Weight 40%Scale 1-3

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 specific, complete, and distinctive with an explicit trigger clause, but loses points for second-person voice and somewhat technical trigger phrasing.

Suggestions

Rewrite in third person to avoid the second-person penalty, e.g. 'Signals blocked, input-required, or failed task states' instead of 'whenever your execution becomes blocked'.

Soften trigger phrasing toward natural user terms, e.g. 'Use when an agent is blocked, needs operator input, or hits a failure that stops progress.'

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('signaling blocked or input-required task states', 'targeted A2A pings using the Task.state envelope rather than global capacity broadcasts'), which would rate 3, but the second-person phrasing ('your execution becomes blocked') triggers the voice penalty of -1.	2 / 3
Completeness	Clearly states what the skill does and provides an explicit 'Triggers: Use this skill whenever...' clause answering when to use it.	3 / 3
Trigger Term Quality	Relevant trigger keywords appear ('blocked', 'input', 'failure that halts progress'), but the phrasing is formal/technical ('requires explicit operator input') and misses common natural variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (A2A blocked-task-state signaling) with distinct triggers that are unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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: c1ce853

Reviewed: 8 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.