CtrlK
BlogDocsLog inGet started
Tessl Logo

acp-router

Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.

87

1.49x
Quality

83%

Does it follow best practices?

Impact

91%

1.49x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 concrete, executable templates and well-sequenced workflows that include explicit validation and recovery feedback loops. The main weakness is mild redundancy (duplicated alias list, repeated preflight instruction) and the absence of any file-based progressive disclosure for the longer policy sections.

DimensionReasoningScore

Conciseness

The body is action-oriented with no concept over-explanation, but the harness alias list is duplicated (AgentId mapping vs 'Harness aliases in acpx') and 'read this skill first' is stated three times. Minor trim opportunities keep it at 4 rather than 5.

4 / 5

Actionability

Provides a concrete sessions_spawn JSON example plus copy-paste bash templates for persistent, one-shot, cancel, and close flows, with specific install/version commands. Fully executable templates covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Numbered sequences with explicit validation and feedback loops (verify `${ACPX_CMD} --version`, retry once after repair, only then offer fallback). Validation is present so the destructive/batch cap does not apply; matches anchor 5.

5 / 5

Progressive Disclosure

No bundle files exist and ~220 lines are inline, but content is well-organized into clear section headers. Good structure with minor gaps — the adapter command defaults and install policy could be split into a reference file to shorten SKILL.md, so not 5.

4 / 5

Total

18

/

20

Passed

Description

78%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 highly distinctive, naming concrete routing actions, tools, and the trigger harnesses. Its main weakness is completeness/trigger phrasing: it gives equivalent trigger guidance but lacks a clean 'Use when...' clause and omits 'Kimi' from the trigger list.

Suggestions

Add an explicit 'Use when...' clause naming the trigger context (e.g., 'Use when the user asks to run or continue work in Pi, Claude Code, Codex, OpenCode, Gemini CLI, or Kimi') to lift completeness toward 5.

Include 'Kimi' in the description's trigger list so it matches the body's full harness coverage.

Lead with the trigger phrase before the routing mechanics so the 'when' is as prominent as the 'what'.

DimensionReasoningScore

Specificity

Quotes 'Route plain-language requests...into either OpenClaw ACP runtime sessions or direct acpx-driven sessions' and 'use only `sessions_spawn` for thread creation' — several concrete actions with named tools. Not 3 (more than 1-2 actions) and not 5 (fewer distinct actions than the comprehensive anchor example).

4 / 5

Completeness

Clear 'what' (route into two session types) plus a 'when' via 'For coding-agent thread requests, read this skill first' — equivalent explicit trigger guidance, so not capped at 3. Not 5 because the trigger is phrased as instruction rather than the canonical 'Use when...' form.

4 / 5

Trigger Term Quality

Quotes 'Pi, Claude Code, Codex, OpenCode, Gemini CLI' — natural product names users actually say. Good keyword coverage but 'Kimi' (present in the body) is missing from the description, so not 5.

4 / 5

Distinctiveness Conflict Risk

Quotes 'ACP harness work' routing for named products (Pi/Claude Code/Codex/OpenCode/Gemini CLI) — a clear niche with distinct triggers and minimal conflict risk, matching the anchor 5 example.

5 / 5

Total

17

/

20

Passed

Validation

100%

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
qsimeon/openclaw-engaging
Reviewed

Table of Contents

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.