CtrlK
BlogDocsLog inGet started
Tessl Logo

supervisor-review-queue

Professor's review queue — student output waits here for professor approval before going to clients or courts. Only active if "formal review queue" supervision style was chosen at setup; otherwise dormant. Use when the professor wants to see what's waiting for review, approve, edit-then-approve, or return an item.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./legal-clinic/skills/supervisor-review-queue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The body is well-organized with a clear single-file structure and one external reference, but it repeats its gating logic, leaves the approve/return mechanics underspecified, and omits verification checkpoints before consequential state changes.

Suggestions

State the supervision-style gating check once (in Load context) and reference it from the quick-start and Purpose sections instead of repeating the full logic three times.

Add concrete mechanics for approve/return: how to move an entry between queue/approved/log in review-queue.yaml, how the student is 'notified,' and exactly what is written to the log entry.

Insert an explicit verification checkpoint before approve or return (e.g., confirm the item ID exists and re-display its content) since these actions release work to clients or courts.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete templates, but the supervision-style gating logic is repeated three times (quick-start, Purpose, Load context) and the Purpose section adds rationale Claude does not need to execute; it could be tightened.

2 / 3

Actionability

Concrete file paths, exact response strings, invocation examples, and a YAML schema are present, but the approve/return mechanics are described at a high level ('student notified, logged') with placeholders and no concrete steps for mutating the queue, notifying, or writing the log.

2 / 3

Workflow Clarity

A clear sequence with an explicit gating check exists, but approve/return are consequential state changes that release work to clients or courts with no explicit verification checkpoint before acting, capping the score at 2.

2 / 3

Progressive Disclosure

A well-sectioned body with a single clearly signaled one-level-deep reference (references/review-queue.yaml, which exists), keeping instructions in SKILL.md and data externalized.

3 / 3

Total

9

/

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 description: it states concrete actions, gives an explicit natural-language trigger, answers both what and when, and occupies a distinct niche. Voice is third person throughout, so no voice penalty applies.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'see what's waiting for review, approve, edit-then-approve, or return an item' — matching the anchor that lists several specific concrete actions.

3 / 3

Completeness

Clearly answers both what ('student output waits here for professor approval before going to clients or courts') and when via an explicit 'Use when...' trigger.

3 / 3

Trigger Term Quality

An explicit 'Use when the professor wants to see what's waiting for review, approve, edit-then-approve, or return an item' clause provides natural terms a user would say (review, approve, return).

3 / 3

Distinctiveness Conflict Risk

A clearly scoped niche — a professor's review queue in a legal clinic, gated on the 'formal review queue' supervision style — unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anthropics/claude-for-legal
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.