acpx

Use acpx as a headless ACP CLI for agent-to-agent communication, including prompt/exec/sessions workflows, session scoping, queueing, permissions, output formats, system-prompt overrides, and multi-agent flows authored with defineFlow/decision/decisionEdge.

Quality

66%

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/acpx/SKILL.md

Quality

Content

71%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 and well structured as a CLI reference, with solid validation checkpoints on destructive operations. Its main weaknesses are length/redundancy and the absence of progressive disclosure for a skill this large.

Suggestions

Move the full built-in agent registry, the flows authoring API reference, and the detailed command/option catalog into separate reference files under references/, leaving SKILL.md a concise overview with clearly signaled links.

Deduplicate the prune examples (shown in both Sessions and Sessions cleanup) and trim Practical workflows entries that restate earlier patterns.

Consolidate the model/config-option behavior notes in Cancel/Mode/Config/Model into a single reference section to reduce repetition.

Dimension	Reasoning	Score
Conciseness	The body is dense, reference-style, and assumes Claude's competence, but at ~625 lines it includes redundancy — prune examples appear in both the Sessions and Sessions cleanup sections, and Practical workflows reuses patterns already shown — so it could be tightened.	3 / 5
Actionability	Copy-paste-ready bash commands, a complete TypeScript flow example, exhaustive option/behavior listings, and concrete per-command examples cover the common cases fully.	5 / 5
Workflow Clarity	Workflows are well sequenced and the destructive prune operation has an explicit --dry-run validation checkpoint, plus flows have permission preflight and import/reconnect paths report failures clearly; it stops short of a single coherent validate-fix-retry pipeline, so it is not a 5.	4 / 5
Progressive Disclosure	Sections are clearly headed and well organized, but no local bundle files exist and large reference material (full agent registry, complete flows authoring API, command reference) is inlined in SKILL.md rather than split into one-level-deep reference files; only external GitHub links are offered.	3 / 5
	Total	15 / 20 Passed

Description

62%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 occupies a distinct niche, but it omits any explicit 'when to use' trigger guidance and leans on technical jargon rather than natural user phrases. Rewording the imperative opening into third-person voice would also recover the specificity penalty.

Suggestions

Append an explicit 'Use when...' clause naming natural trigger phrases (e.g., running coding agents from scripts, managing persistent agent sessions, composing multi-agent workflows).

Rephrase 'Use acpx as...' into third person (e.g., 'Runs coding agents via a headless ACP CLI...') to avoid the second-person voice penalty.

Soften jargon like 'defineFlow/decision/decisionEdge' in favor of user-natural terms such as 'declarative multi-agent flows', reserving API names for the body.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities ('prompt/exec/sessions workflows, session scoping, queueing, permissions, output formats, system-prompt overrides, and multi-agent flows'), matching the comprehensive anchor 5, but the imperative 'Use acpx as...' is second-person voice, triggering the rubric's -1 specificity penalty.	4 / 5
Completeness	The 'what' is clear ('headless ACP CLI for agent-to-agent communication' plus enumerated workflows), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3.	3 / 5
Trigger Term Quality	'agent-to-agent communication' and 'multi-agent flows' are reasonable keywords, but heavy jargon ('ACP CLI', 'defineFlow/decision/decisionEdge') crowds out natural user phrasing and no synonyms or extension cues are present.	3 / 5
Distinctiveness Conflict Risk	'headless ACP CLI for agent-to-agent communication' carves a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (630 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openclaw/acpx
Path: skills/acpx/SKILL.md
Commit: 8100a58

Reviewed: 12 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.