drivers-ticket-assistant

Help the user understand and complete their assigned DOCSP tickets for drivers. Provides a prioritized overview of all assigned tickets and suggests next steps. Use only when the user explicitly uses the slash command.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/drivers-ticket-assistant/SKILL.md

Quality

Content

75%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 content is a well-structured, actionable workflow with concrete CLI commands, explicit prerequisite handling, and clear status-based branching. It is concise and assumes Claude's competence; the main gap is the absence of explicit validation/feedback loops and any progressive-disclosure file split for the lengthy Step 2 detail.

Suggestions

Add explicit validation checkpoints in the Review branch (e.g. verify the PR found via `gh search prs` actually matches the ticket key before classifying reviewers), since branch logic depends on correct PR-to-ticket mapping.

Consider moving the detailed per-status Step 2 guidance into a reference file (e.g. `references/status-actions.md`) and keeping SKILL.md as an overview to improve progressive disclosure.

Show the exact `jira` skill invocation (e.g. the JQL `assignee = currentUser() AND project = DOCSP`) so the Jira fetch steps are copy-paste ready rather than deferred.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it does not explain what Jira, gh, or PRs are — with only minor verbose conditional branches (e.g. the multiple reviewer-classification sentences) that could be tightened, fitting the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	It provides concrete, executable commands — `gh search prs "<ticket key>"`, `gh pr view <number> --json reviewRequests,reviews`, `gh api "repos/10gen/docs-mongodb-internal/commits?author=<login>&per_page=20"`, Jira REST `?expand=changelog` — plus drafted message templates, with minor gaps (exact jira-skill invocation is deferred), placing it at 4 rather than fully copy-paste 5.	4 / 5
Workflow Clarity	Steps are clearly sequenced (Step 1 overview → Step 2 status-branched actions) with explicit prerequisite guardrails acting as checkpoints and a ranked priority list; it stops short of explicit validate→fix→retry feedback loops, so it sits at 4 rather than 5, and the destructive/batch cap does not apply since the skill suggests rather than auto-executes mutations.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized into clearly signaled sections (Arguments, Prerequisites, Priority Order, Step 1, Step 2 sub-branches) with no nested references and no bundle files to misroute; the long inline Step 2 detail is appropriately kept for a workflow skill, matching 'good structure; minor organization gaps' rather than the 5-anchor which expects one-level-deep file references.	4 / 5
	Total	16 / 20 Passed

Description

71%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 specific, third-person, and clearly distinguishes its niche with an explicit trigger clause, scoring well on distinctiveness and completeness. Its main weakness is trigger-term quality: the activation language is generic and does not surface the natural phrases a user would say.

Suggestions

Add concrete natural-language trigger phrases (e.g. 'Use when the user asks about their driver docs tickets, what to work on next, or ticket review status') so the 'when' maps to terms users actually say.

Surface the category keywords (in-progress, review, backlog, blocked) inside the description itself rather than only in the argument-hint to improve keyword coverage.

Optionally name the slash command explicitly in the description to make the trigger unambiguous.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'understand and complete their assigned DOCSP tickets', 'Provides a prioritized overview of all assigned tickets', 'suggests next steps' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	It states both what ('understand and complete... tickets', 'prioritized overview', 'suggests next steps') and when ('Use only when the user explicitly uses the slash command'), so the missing-trigger cap of 3 does not apply; the 'when' is explicit but not tied to concrete trigger phrases, placing it at 4 rather than 5.	4 / 5
Trigger Term Quality	Relevant keywords are present ('DOCSP tickets', 'drivers', 'assigned tickets', category names in the argument-hint) but the trigger guidance is generic ('Use only when the user explicitly uses the slash command') and lacks the natural phrases/synonyms a user would actually say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The narrow niche ('DOCSP tickets for drivers') plus an explicit slash-command-only trigger gives it a clear distinct trigger with minimal overlap risk, matching the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mongodb/docs
Path: .claude/skills/drivers-ticket-assistant/SKILL.md
Commit: d9cb237

Reviewed: 3 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.