clawdbot-release-check

Check for new OpenClaw releases and notify once per new version.

1.45x

Quality

77%

Does it follow best practices?

Impact

90%

1.45x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./clawdbot/clawdbot-release-check/SKILL.md

Quality

Content

87%

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

The content is concise, actionable, and well-structured with correct progressive disclosure to real bundle scripts. Its only gap is a missing verification checkpoint in the setup workflow.

Suggestions

Add a verify step after setup, e.g. run `crontab -l | grep clawdbot` and confirm the gateway restarted, to lift workflow clarity.

Optionally note expected output of `check.sh --status` so success is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean with short sections and direct commands, explaining no concepts Claude already knows and avoiding padding, matching the lean-and-efficient anchor.	3 / 3
Actionability	Concrete copy-paste commands with real flags ("clawhub install", "setup.sh --telegram", "check.sh --force", "openclaw gateway restart") make the guidance fully executable.	3 / 3
Workflow Clarity	The cron setup sequence (install -> setup.sh -> restart gateway) is listed but lacks an explicit verification checkpoint that the cron job registered or the gateway restarted, fitting the steps-present-but-checkpoints-implicit anchor.	2 / 3
Progressive Disclosure	Implementation is correctly delegated to real one-level-deep bundle files ({baseDir}/scripts/check.sh, setup.sh) under clearly signaled sections, with no monolithic inline content or nested references.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 clearly niche-scoped but lacks explicit "when to use" trigger guidance and broader natural term variation, which cap completeness and trigger quality. Adding a Use-when clause would lift the two tied lowest dimensions.

Suggestions

Append a "Use when the user wants OpenClaw update checks, release notifications, or version-bump alerts" clause to satisfy the completeness and trigger-term dimensions.

Add common natural variations ("updates", "new version", "changelog") so users' phrasings map to the skill.

Keep the existing "once per new version" constraint — it strongly supports distinctiveness.

Dimension	Reasoning	Score
Specificity	"Check for new OpenClaw releases and notify once per new version" lists concrete actions (check, notify) plus a meaningful constraint (once per version), matching the multiple-specific-actions anchor rather than the domain-only score-2 anchor.	3 / 3
Completeness	It clearly answers what (check + notify per version) but never says when Claude should use it; per the rubric a missing "Use when..." clause caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant keywords ("OpenClaw releases", "notify") are present but coverage of natural variations (updates, version bump, changelog) is thin and there is no explicit trigger guidance, fitting the some-keywords-but-missing-variations anchor.	2 / 3
Distinctiveness Conflict Risk	The OpenClaw-specific niche and "once per new version" constraint make it clearly distinguishable and unlikely to trigger for the wrong skill, matching the clear-niche anchor.	3 / 3
	Total	10 / 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
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: jdrhyne/agent-skills
Commit: a4d31ad

Reviewed: 11 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.