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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

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 content is highly actionable with executable command syntax and a thorough flow example, and workflows are clearly sequenced with validation for destructive operations. Its main weaknesses are duplicated material that hurts conciseness and a monolithic structure with no local reference files for progressive disclosure.

Suggestions

Remove the duplicated 'Sessions cleanup' / prune section, keeping prune documented once in the Sessions behavior block, to tighten conciseness.

Split the large agent registry and the flows authoring API reference into reference files under ./references/ and link to them from SKILL.md to improve progressive disclosure.

Collapse the redundant agent-prefixed session command listings (the 'acpx codex sessions ...' block) into a note that the agent prefix is optional, since the unprefixed forms already show the syntax.

Dimension	Reasoning	Score
Conciseness	The body is a dense, mostly-efficient CLI reference that assumes Claude's competence, but it duplicates material — 'sessions prune' is documented in both the Sessions behavior list and a separate 'Sessions cleanup' section, and session subcommands appear in both the Command model and the Sessions section — so it could be tightened.	3 / 5
Actionability	Nearly every section gives exact, executable command syntax with real flags and copy-paste-ready examples, including a complete TypeScript flow authoring example covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes (session lifecycle, flow authoring with nodes/edges) are clearly sequenced, and the destructive 'prune' operation carries a '--dry-run' validation checkpoint, so the destructive cap does not apply; minor validation gaps remain in a few flows.	4 / 5
Progressive Disclosure	No bundle files (references/scripts/assets) exist and the 615-line SKILL.md is monolithic, inlining content that could live in separate files (the full agent registry, the flows authoring API reference) with only an external GitHub URL as a pointer rather than clear one-level-deep local references.	3 / 5
	Total	15 / 20 Passed

Description

75%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, distinctive, and rich in natural trigger terms, but it omits any explicit 'Use when...' trigger guidance, which caps completeness at 3. Adding a concrete trigger clause would lift the completeness score.

Suggestions

Append an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when orchestrating coding agents from scripts, managing persistent ACP sessions, or composing multi-agent flows.'

Soften the technical API names (defineFlow/decision/decisionEdge) with a user-natural synonym so the trigger terms read as something a user would actually say.

Lead with the trigger condition before the capability list so 'when to use it' is as prominent as 'what it does'.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete capabilities — 'prompt/exec/sessions workflows, session scoping, queueing, permissions, output formats, system-prompt overrides, and multi-agent flows authored with defineFlow/decision/decisionEdge' — giving comprehensive coverage of specific actions rather than vague language.	5 / 5
Completeness	It clearly answers 'what' (a headless ACP CLI with listed capabilities) but contains no 'Use when...' trigger clause or equivalent explicit 'when' guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural phrases a user would say appear ('agent-to-agent communication', 'prompt', 'exec', 'sessions', 'multi-agent flows'), but several tokens are technical API names (defineFlow/decision/decisionEdge) rather than user-natural terms, leaving a few common variations missing.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined — a headless ACP CLI for agent-to-agent communication with a named API surface — making it clearly distinguishable from other skills with minimal conflict risk.	5 / 5
	Total	17 / 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 (621 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openclaw/acpx
Path: skills/acpx/SKILL.md
Commit: 2d735cf

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.