CtrlK
BlogDocsLog inGet started
Tessl Logo

outlook-email-task-extraction

Extract action items, deadlines, commitments, and owners from Outlook email threads and mailbox searches. Use when the user wants a task list from one thread, several related messages, or a mailbox slice, including who owes what and when.

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

87%Weight 40%Scale 1-3

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

A concise, well-structured instruction-only skill with specific tool calls and a concrete output schema. Its main gap is that quality/validation checkpoints are implicit in the Output section rather than woven into the workflow steps as explicit verification gates.

Suggestions

Add an explicit verification step to the Workflow (e.g., step 7: 'Confirm each task has an owner and a source quote; flag any task missing either') to turn the implicit Output checks into a real validation checkpoint.

For the optional write-back path, add a validation checkpoint before 'set_message_categories' (e.g., 'Confirm the category list with the user before tagging, since it modifies the mailbox') to satisfy the destructive/batch feedback-loop expectation.

Make the merge rule in step 5 actionable by naming the tie-breaker concretely (e.g., 'prefer the latest message by date and quote it as Evidence') so the freshest-status logic is unambiguous.

DimensionReasoningScore

Conciseness

Lean ~30-line body with no padding and no explanation of concepts Claude already knows; every section (Overview, Relevant Actions, Workflow, Output) earns its place. Slightly above a 2 because nothing needs tightening.

3 / 3

Actionability

Names concrete tool actions ('search_messages', 'fetch_message', 'fetch_messages_batch', 'set_message_categories') and a specific output schema ('Task', 'Owner', 'Due', 'Status', 'Evidence'); per the code-vs-instruction note, absence of code is not penalized when guidance is this actionable.

3 / 3

Workflow Clarity

The six-step workflow is clearly sequenced, but verification checkpoints are implicit (living in the Output section: 'Call out ambiguity', 'If there are no concrete tasks, say that clearly') rather than explicit steps in the workflow itself, which fits the 'sequence present but checkpoints missing or implicit' anchor rather than a 3.

2 / 3

Progressive Disclosure

Under 50 lines with no need for external references and well-organized sections, which the simple-skills note says can score 3 on progressive disclosure with just clear organization.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 names concrete capabilities, includes an explicit 'Use when' trigger, and is tightly scoped to Outlook task extraction. It hits the top anchor on every dimension with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Extract action items, deadlines, commitments, and owners' — rather than vague language, matching the top anchor for naming several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Extract action items, deadlines, commitments, and owners') and when via an explicit 'Use when the user wants a task list...' clause, so completeness is not capped at 2.

3 / 3

Trigger Term Quality

Uses natural terms a user would say — 'task list', 'one thread', 'several related messages', 'mailbox slice' — giving good coverage rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

Scoped to 'Outlook email threads and mailbox searches' with a clear niche (task extraction) and distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

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.