picoclaw-agent

Configure, extend, debug, or contribute to PicoClaw itself. Use when the task is about PicoClaw CLI commands, config.json, gateway, auth, models, skills, MCP servers, cron, routing, sessions, self-evolution, built-in slash commands, or repository internals. Use PicoClaw-native workflows, terminology, paths, and configuration.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a comprehensive, highly actionable PicoClaw reference with strong command/config coverage, but it runs long with some redundancy and keeps detailed material inline rather than progressively disclosing it. Workflows have sequence but lack explicit validation feedback loops for risky operations.

Suggestions

Deduplicate the Quick Start commands against the Command Surface section, or have Quick Start link forward to Command Surface instead of repeating the full list.

Add explicit validate->fix->retry checkpoints around destructive/batch operations (picoclaw config reset, skills remove, mcp remove) to lift workflow clarity.

Move the full provider matrix and the detailed voice/TTS JSON+YAML setup into reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference material (commands, config, tables) but ~870 lines long with redundancy: Quick Start re-lists commands that reappear verbatim in Command Surface, and the full provider matrix plus repeated JSON+YAML voice examples could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready executable commands, complete config.json JSON blocks, and clear tables throughout (CLI surface, provider matrix, tool families, subagent selection).	3 / 3
Workflow Clarity	The Debugging Workflow and voice setup give numbered sequences, but checkpoints are implicit ("Check that...") rather than explicit validate->fix->retry loops, and destructive commands (config reset, skills remove, mcp remove) lack validation feedback steps.	2 / 3
Progressive Disclosure	Sections are well organized and a "Load These Docs Next" block signals one-level-deep doc references, but no bundle files exist and the bulk of detailed reference content (provider matrix, voice setup, tool families) is inline in a monolithic SKILL.md rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 a strong, third-person statement that names concrete actions, gives an explicit Use-when trigger with natural keywords, and carves out a distinct niche tied to PicoClaw internals. It matches the rubric's good examples closely.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ("Configure, extend, debug, or contribute") plus a detailed enumeration of subsystems (CLI commands, config.json, gateway, auth, models, skills, MCP servers, cron, routing, sessions, self-evolution, slash commands).	3 / 3
Completeness	Clearly answers both what ("Configure, extend, debug, or contribute to PicoClaw itself") and when (explicit "Use when the task is about..." clause with concrete triggers).	3 / 3
Trigger Term Quality	Good coverage of natural terms a user would say when they need this skill: "PicoClaw CLI commands", "config.json", "gateway", "auth", "models", "skills", "MCP servers", "cron", "routing", "sessions".	3 / 3
Distinctiveness Conflict Risk	Scoped to "PicoClaw itself" with PicoClaw-native workflows/terminology/paths, giving it a clear niche unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (874 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: sipeed/picoclaw
Path: workspace/skills/picoclaw-agent/SKILL.md
Commit: 49183d7

Reviewed: about 16 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.