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

81%

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

75%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.

A thorough, highly actionable reference with concrete commands and examples throughout, well-structured and well-signaled. Its main weakness is verbosity: substantial bulk reference material is inlined in SKILL.md despite being available in repo docs, and explicit validation feedback loops are sparse.

Suggestions

Move the large provider matrix and additional-vendors list into a reference file (or rely solely on the existing docs/guides/providers.md pointer) to shrink the SKILL.md body and improve conciseness.

Add explicit validate-then-retry feedback loops to the config-editing and debugging workflows (e.g., run `picoclaw status` / `mcp test` after a change and only proceed on success).

Consider splitting the voice/TTS and subagent sections into one-level-deep reference files, keeping SKILL.md a concise overview that points to them.

Dimension	Reasoning	Score
Conciseness	The body is reference-dense and PicoClaw-specific (not explaining general concepts Claude knows), but it is ~870 lines and inlines large tables (a 25-row provider matrix, a tool-families table, full voice/TTS setup) that duplicate material the skill itself points to in docs/, so it is mostly efficient yet could be tightened.	3 / 5
Actionability	It provides copy-paste-ready commands (picoclaw onboard, auth login, mcp add, cron add), concrete config JSON/YAML examples, file paths, and env vars covering the common cases.	5 / 5
Workflow Clarity	Quick Start, the Debugging Workflow (numbered 1-8), and STT/TTS setup are clearly sequenced with concrete commands, but explicit validate-then-fix-then-retry feedback loops are mostly absent, leaving minor checkpoint gaps.	4 / 5
Progressive Disclosure	Headers are clear, references to repo docs are explicitly signaled ("Load These Docs Next" plus inline "read docs/..." pointers), and navigation is easy; however bulk reference content (provider matrix, tool families) is inlined in SKILL.md rather than split into bundle files, which is a minor organization gap for a skill this size.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong, third-person description that clearly answers both what the skill does and when to trigger it, with a comprehensive subsystem list. The only weakness is that the action verbs are somewhat generic rather than maximally concrete.

Dimension	Reasoning	Score
Specificity	Names the PicoClaw domain plus concrete action verbs ("Configure, extend, debug, or contribute") and enumerates many specific subsystems (CLI, config.json, gateway, auth, models, skills, MCP, cron, routing, sessions, self-evolution), but the verbs themselves stay somewhat generic rather than fully concrete, so it sits just below a 5.	4 / 5
Completeness	It explicitly states both what the skill does ("Configure, extend, debug, or contribute to PicoClaw itself") and when to use it ("Use when the task is about PicoClaw CLI commands, config.json, ..."), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers a broad set of natural terms a PicoClaw user would actually say (PicoClaw, CLI commands, config.json, gateway, auth, models, skills, MCP, cron, routing, sessions, slash commands), but it reads as an enumerated subsystem list rather than the full synonym/extension coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	It is scoped tightly to "PicoClaw itself" with subsystem-specific triggers, giving it a clear niche with minimal overlap against other skills.	5 / 5
	Total	18 / 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
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: bbf6893

Reviewed: 17 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.