openclaw-relay

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

Quality

70%

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

82%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 highly actionable with comprehensive executable examples and well-structured workflows including recovery loops, held back only by minor conciseness redundancy and a referenced config file that is absent from the bundle.

Suggestions

Add the missing config/session_aliases.json to the bundle (or correct the reference) so the signaled path resolves.

Collapse the duplicated remote-host SSH examples into one parameterized form to tighten conciseness.

Make the pre-send validation an explicit gate (e.g., a numbered 'probe -> only send when probe succeeds' step) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of SSH or what a session is), with only minor redundancy in the repeated '--transport ssh --host' examples, fitting anchor 4 rather than the fully trimmed anchor 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands for every subcommand (doctor, targets, resolve, ask, force-send, ensure, send, show, start, wait, cancel) with complete flags, matching anchor 5's 'fully executable; specific examples cover the common cases'.	5 / 5
Workflow Clarity	The Failure Handling and Async Workflow sections give clear sequenced steps with recovery feedback loops (cancel -> ensure -> retry) and a probe-before-send checkpoint, but validation is more implicit than a strict validate-then-proceed gate, so anchor 4 fits better than 5.	4 / 5
Progressive Disclosure	Good section structure with clearly signaled references ('Script path: scripts/openclaw_relay.py', 'Target aliases file: config/session_aliases.json'); the script exists in the bundle but the referenced config/session_aliases.json is missing, a minor organization gap that keeps this at 4 rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

57%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 specific and clearly niched, but it omits any explicit 'when to use' trigger guidance and relies on technical jargon rather than natural user phrasing, capping completeness and trigger-term quality at 3.

Suggestions

Append a 'Use when...' clause with natural trigger phrases (e.g., 'Use when the user wants to relay prompts or posts into an OpenClaw session via acpx or over SSH').

Add natural-language synonyms alongside jargon (e.g., 'send a message into an OpenClaw channel', 'bridge to a remote agent') to improve trigger-term quality.

Spell out what 'acpx' means for users who may phrase the request differently, to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'prompts/posts via local/remote acpx over SSH' — names the domain and 1-2 concrete actions (prompts, posts) plus the transport, but coverage is not comprehensive, matching anchor 3 rather than anchor 4's 'several specific actions'.	3 / 5
Completeness	The 'what' is clear ('OpenClaw session relay: prompts/posts via local/remote acpx over SSH') but there is no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap completeness stays at 3.	3 / 5
Trigger Term Quality	Keywords present ('relay', 'acpx', 'SSH', 'OpenClaw') are relevant but technical/jargon-heavy and lack natural synonyms or common variations a user would say, fitting anchor 3 over anchor 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	'OpenClaw session relay via local/remote acpx over SSH' defines a clear niche with distinct triggers and minimal conflict risk with other skills, matching anchor 5.	5 / 5
	Total	14 / 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: steipete/agent-scripts
Path: skills/openclaw-relay/SKILL.md
Commit: dc4f583

Reviewed: 2 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.