CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

support-triage-and-routing

Prioritize support requests, identify owners, route internally, and prepare safe customer drafts

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./resources/skills/communication/support-triage-and-routing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured instruction skill: concrete urgency criteria, explicit fields, a safety gate on external messaging, and a verification checklist, all with no wasted tokens. The only meaningful gaps are a missing draft template and the absence of an explicit fix-and-retry loop when verification fails.

DimensionReasoningScore

Conciseness

The body is lean with zero padding: no concept explanations, no restating what Claude already knows, and every line carries an instruction, a criterion, or a check. It matches the anchor of assuming Claude's competence with every token earning its place.

5 / 5

Actionability

The guidance is concrete for an instruction-only skill: enumerated urgency criteria ("critical for outage, data loss, security exposure, or imminent contractual breach; high for a blocked user without a workaround"), a required-fields list for each issue, and an explicit authorization gate for routing. It falls short of anchor 5 only because "prepare safe customer drafts" lacks a draft structure or example, and sender resolution depends on unspecified "available contacts and service ownership data".

4 / 5

Workflow Clarity

The six-step procedure is clearly sequenced and validation is genuinely present (a dedicated Verification checklist plus a re-read step and escalation summary), so the batch-operation cap does not apply. It stops at anchor 4 because there is no explicit error-recovery feedback loop (e.g., what to do when a verification item fails) — the checklist states the checks but not the fix-and-retry path.

4 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references, and is organized into four well-labeled sections (When to Use, Procedure, Pitfalls, Verification) with no content that belongs in a separate file. Per the rubric's guideline for such skills, this matches the top anchor.

5 / 5

Total

18

/

20

Passed

Description

66%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 concrete, terse description of the skill's actions with good domain keywords, but it omits any "use when" trigger guidance, which caps completeness and weakens its ability to fire at the right moments. Adding an explicit trigger clause with terms like "triage" and "escalation" would resolve both gaps.

Suggestions

Append an explicit trigger clause, e.g. "Use when triaging a support inbox or backlog, prioritizing tickets, assigning ownership, or escalating incidents" — its absence currently caps completeness at 3.

Include the natural user terms "triage", "tickets", "backlog", and "escalation" ("triage" appears only in the skill name, not the description) to broaden trigger keyword coverage.

Mention the escalation-summary output in the capability list so the "what" covers what the procedure actually produces.

DimensionReasoningScore

Specificity

The description lists four concrete domain actions — "Prioritize support requests, identify owners, route internally, and prepare safe customer drafts" — comparable to the anchor's several specific actions. It stops short of anchor 5's comprehensive coverage because capabilities present in the body (e.g., escalation summaries) are omitted, and "prepare safe customer drafts" leaves the draft content unspecified.

4 / 5

Completeness

The "what" is clear (prioritize, identify owners, route, prepare drafts), but the description contains no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 2 because the "what" side is concrete and multi-action, and not a 4 because "when" is entirely absent rather than merely under-specified.

3 / 5

Trigger Term Quality

Natural phrases like "support requests", "prioritize", "route", and "customer drafts" give good keyword coverage. It falls short of anchor 5's comprehensive coverage because common user phrasings such as "triage" (which appears only in the skill name), "tickets", "backlog", "escalation", and "inbox" are missing.

4 / 5

Distinctiveness Conflict Risk

The support-operations framing ("route internally", "customer drafts") carves a fairly distinct niche with only minor overlap risk against generic email-drafting or inbox-summarization skills. It does not reach anchor 5 because the absence of explicit trigger phrases makes it slightly less distinguishable from those related skills.

4 / 5

Total

15

/

20

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.

Validation — 15 / 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

odysseus-dev/odysseus

Path

resources/skills/communication/support-triage-and-routing/SKILL.md

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.