openclaw-migration

Import an OpenClaw setup (memories, skills) into Hermes.

Quality

69%

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 ./optional-skills/migration/openclaw-migration/SKILL.md

Quality

Content

81%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.

This is a high-quality, highly actionable migration skill with excellent workflow validation and concrete command/payload examples. Its main weakness is redundancy across the protocol, mapping, and rules sections that inflates token cost.

Suggestions

Consolidate the repeated workspace-agents/execution-gate and clarify-usage guidance so each rule appears once; the 'User interaction protocol', 'Decision-to-command mapping', and 'Important rules' sections currently restate much of the same material.

Fix the duplicate numbering in the simplified decision flow (two consecutive items labeled '5') so the step sequence parses correctly.

Consider moving the lengthy post-run reporting rules and the clarify payload catalog into a separate reference file (e.g., REPORTING.md) referenced one level deep, keeping SKILL.md as a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense and does not explain concepts Claude already knows, but the same guidance is restated across 'User interaction protocol', 'Decision-to-command mapping', and 'Important rules' (e.g., the workspace-agents execution gate and clarify usage rules each appear several times), and the decision-flow list even has two items numbered '5' — material tightening is possible.	3 / 5
Actionability	It provides copy-paste-ready CLI commands, exact `clarify` JSON payload shapes, and a precise decision-to-flag mapping table covering the common cases, which is fully executable guidance.	5 / 5
Workflow Clarity	The Default workflow is a clear sequence with explicit validation checkpoints (dry run, conflict-resolution gate, an 'Execution gate' section, restate-command-plan-before-executing), plus feedback loops (clarify error -> retry once, dry-run -> resolve decisions -> execute), which is exactly what the level-5 anchor calls for on a destructive/batch operation.	5 / 5
Progressive Disclosure	Structure is good with clear section headers and a real, clearly signaled one-level reference to scripts/openclaw_to_hermes.py (with path-resolution guidance); however, large inline catalogs (post-run reporting rules, clarify payload shapes) that could live in separate reference files keep it just below the ideal split.	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 clear and distinct but minimal: it conveys the what and the niche without explicit trigger guidance and with only one action verb. It would benefit from a 'Use when...' clause and the natural term 'migrate'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a user wants to migrate or move their OpenClaw setup (memories, skills, settings) into Hermes.'

Replace or supplement 'Import' with the more natural user verb 'migrate', and list a couple more concrete actions (e.g., convert memories, copy skills, merge command allowlists) to lift specificity.

Mention the migration report / dry-run preview capability so the description reflects the skill's full scope rather than only memories and skills.

Dimension	Reasoning	Score
Specificity	The phrase 'Import an OpenClaw setup (memories, skills) into Hermes' names the source/target domain and a couple concrete objects (memories, skills), but the only action stated is 'import', so it sits at the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than the multi-action level 4.	3 / 5
Completeness	It clearly states the 'what' (import OpenClaw setup into Hermes) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant keywords ('OpenClaw', 'memories', 'skills', 'Hermes', 'Import'), but the more natural user phrasing 'migrate'/'move'/'transfer my OpenClaw setup' is missing, leaving common synonyms uncovered.	3 / 5
Distinctiveness Conflict Risk	The named product pair 'OpenClaw' and 'Hermes' form a clear, distinct niche with minimal overlap risk; this is unlikely to trigger for an unrelated skill.	5 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/migration/openclaw-migration/SKILL.md
Commit: b9aa928

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.