openclaw-relay

OpenClaw session relay: prompts/posts via local/remote acpx over SSH.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/openclaw-relay/SKILL.md

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, action-first skill reference with lean prose, copy-paste commands, and explicit recovery workflows; its main weakness is a missing referenced file and inline content that could be split out for cleaner progressive disclosure.

Suggestions

Provide the referenced config/session_aliases.json (or correct the path) so the documented 'targets'/'resolve' examples resolve to a real file rather than a dead reference.

Move the full Defaults and env-vars tables into a bundled reference file and keep a one-line pointer in SKILL.md to improve progressive disclosure.

Confirm scripts/openclaw_relay.py flag names (e.g. publish, cancel, status) referenced in the Session Rules/Failure Handling sections match the script's actual argparse, so every documented command is genuinely executable.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational, leading with concrete commands and intent-to-command rules with no padded explanations of SSH, relay, or acpx concepts, so every token earns its place.	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands with exact flags (doctor, ask, force-send, start/wait/show) and an intent-to-command map, rather than vague or pseudocode guidance.	3 / 3
Workflow Clarity	Multi-step flows are clearly sequenced (start→wait→show) and the Failure Handling section gives an explicit validate→fix→retry recovery loop (doctor→status→show→cancel/ensure/retry) for risky relay operations.	3 / 3
Progressive Disclosure	Sections are well-organized but the body references config/session_aliases.json which does not exist (the config/ directory is missing), and large defaults/env-var tables that could live in a separate reference are kept inline.	2 / 3
	Total	11 / 12 Passed

Description

57%

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 niche-specific and states its purpose concisely, but it lacks an explicit 'Use when...' trigger clause and relies on jargon-heavy terms, leaving it solidly mid-tier rather than exemplary.

Suggestions

Add an explicit 'Use when...' clause listing natural user phrasings (e.g. 'Use when the user wants to relay a prompt or post into an OpenClaw channel session, mentions acpx, or asks to talk to a remote OpenClaw agent over SSH').

Broaden trigger terms beyond jargon to include natural phrases users would actually say ('relay into a channel', 'send through the gateway', 'bridge to a remote agent').

Expand the action list from 'prompts/posts' to a few more concrete verbs (e.g. 'queue async work, resolve target aliases, force-send channel posts') to lift specificity toward a score of 3.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('prompts/posts via local/remote acpx over SSH') but gives only two terse action nouns rather than a comprehensive list of multiple specific actions, matching the score-2 anchor.	2 / 3
Completeness	It states clearly what the skill does but provides no 'Use when...' trigger clause, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant keywords ('OpenClaw session relay', 'acpx', 'SSH') but they skew toward ecosystem jargon and miss common natural phrasings, so coverage is partial rather than broad.	2 / 3
Distinctiveness Conflict Risk	'OpenClaw session relay' with 'acpx' names a narrow, distinctive niche with specific triggers unlikely to conflict with unrelated skills.	3 / 3
	Total	9 / 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: steipete/agent-scripts
Path: skills/openclaw-relay/SKILL.md
Commit: bb36883

Reviewed: about 13 hours 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.