general-tasks

Default process for handling open-ended tasks that touch files, the shell, or the web.

Quality

43%

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

Fix and improve this skill with Tessl

tessl review fix ./templates/template-claw-assistant/workspace/skills/general-tasks/SKILL.md

Quality

Content

65%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 admirably concise and well-structured for a simple process skill, but its steps remain abstract meta-instructions without concrete, executable detail. Adding specific, actionable guidance would lift actionability without sacrificing brevity.

Suggestions

Make steps more actionable, e.g. 'Before writing, run `ls`/Read to check for an existing file' instead of 'Prefer reading existing files before writing new ones'.

Add a lightweight verification checkpoint, such as 'After each step, confirm the expected outcome before proceeding', to improve workflow clarity.

Clarify the summary step with concrete fields (files changed, command run, status) so the output is reproducible.

Dimension	Reasoning	Score
Conciseness	The body is a lean numbered list with no padding or explanation of concepts Claude already knows; every line earns its place, matching the score-5 anchor.	5 / 5
Actionability	Steps like 'Restate the goal in one sentence' and 'Execute steps one at a time' are high-level hints rather than concrete, executable guidance, matching the score-2 anchor; it is not a 1 because a usable sequence is present, and not a 3 because no specific commands or concrete detail are given.	2 / 5
Workflow Clarity	A clear numbered sequence (1-5) is present, but there are no validation checkpoints or feedback loops and step 4 interrupts the linear flow, matching the score-3 anchor of steps listed with checkpoint gaps; the destructive-operation cap does not apply since this is not a destructive or batch skill.	3 / 5
Progressive Disclosure	This is a simple, single-purpose skill under 50 lines with a clear header and well-organized numbered list and no need for external references, so per the simple-skills guideline progressive disclosure scores 5.	5 / 5
	Total	15 / 20 Passed

Description

21%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 concise and grammatical but far too generic: it names a broad domain without concrete actions, omits any 'Use when' trigger guidance, and would conflict with most other skills. Specificity and trigger quality are the weakest dimensions.

Suggestions

Add concrete capabilities, e.g. 'Restate goals, plan steps, execute one at a time, and summarize changes' instead of the generic 'handling open-ended tasks'.

Append an explicit trigger clause such as 'Use when an open-ended task touches files, the shell, or the web and no more specific skill applies.'

Narrow the scope or add distinguishing phrases so it does not collide with every general-purpose skill.

Dimension	Reasoning	Score
Specificity	The phrase 'handling open-ended tasks that touch files, the shell, or the web' names the domain but offers only the generic action 'handling' with no concrete capabilities, matching the score-2 anchor; it is not a 1 because a domain is named, and not a 3 because no specific actions are listed.	2 / 5
Completeness	It gives a vague 'what' ('Default process for handling open-ended tasks...') and entirely lacks a 'when'/'Use when' clause, matching the score-2 anchor; the missing trigger guidance also caps completeness at 3 per the judging guidelines, and it sits below that cap.	2 / 5
Trigger Term Quality	Keywords like 'open-ended tasks', 'files', 'shell', and 'web' are generic catch-alls rather than the natural phrases a user would say to invoke this skill, matching the score-2 anchor of one or two generic keywords missing natural phrasing.	2 / 5
Distinctiveness Conflict Risk	'Default process for handling open-ended tasks that touch files, the shell, or the web' is entirely generic and would overlap with virtually any other skill, matching the score-1 anchor.	1 / 5
	Total	7 / 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: mastra-ai/mastra
Path: templates/template-claw-assistant/workspace/skills/general-tasks/SKILL.md
Commit: 3b0d190

Reviewed: 5 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.