session-send

This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./opencode/skills/session-send/SKILL.md

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.

A tight, highly actionable single-purpose skill that earns its tokens on non-obvious harness specifics and gives copy-paste-ready commands. The only gap is the absence of a post-send verification/confirmation step.

Suggestions

Add a brief post-send verification step (e.g., re-listing sessions or checking the inbox) so the sender can confirm delivery.

Consider trimming the CooperBench rationale to one clause since the send/don't-send lists already convey the rule.

Dimension	Reasoning	Score
Conciseness	The body is lean and focuses on harness-specific gotchas Claude would not know (agent vs session_id, BREEZING_ROLE), with only minor over-explanation such as the CooperBench rationale that could be trimmed.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands (`bin/harness session list`, `bin/harness inbox send` with all flags) plus env-var extraction with `:?` guards covering the common cases.	5 / 5
Workflow Clarity	A clear numbered sequence with a preventive checkpoint (confirm the `agent` column, wait for the peer to publish identity before sending) but no post-send verification step, so it falls just short of 5.	4 / 5
Progressive Disclosure	This is a short single-purpose skill under 50 lines with no external references needed; it is well organized into clearly signaled sections, satisfying the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

70%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 clear, trigger-rich description that explicitly tells Claude when to use the skill, with minimal conflict risk. It is held back from the top level because it states triggering conditions more concretely than the actual actions the skill performs.

Suggestions

Lead with the concrete action the skill performs (e.g., 'Sends a message to another session's agent inbox via bin/harness inbox send') before the trigger clause.

Add a couple of natural synonyms such as 'hand off work' or 'ping another agent' to round out trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (cross-session messaging) and several triggering scenarios ('notify other session', 'session handoff', 'tell other agent') but describes no concrete actions the skill performs, only when it fires.	3 / 5
Completeness	Both 'what' (notify/handoff/cross-session message) and an explicit 'when' clause are present; the 'what' is somewhat implied rather than stated as a concrete action, keeping it just below a 5.	4 / 5
Trigger Term Quality	It includes several natural phrases a user would say ('notify other session', 'session handoff', 'tell other agent', 'cross-session message') with good coverage, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The cross-session handoff niche with distinct triggers ('tell other agent', 'session handoff') is mostly distinct with only minor overlap risk against general messaging skills.	4 / 5
	Total	15 / 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: Chachamaru127/claude-code-harness
Path: opencode/skills/session-send/SKILL.md
Commit: 2b2b748

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.