prioritize-accounts

Use when the user asks which existing accounts to work now, which leads are hottest in a grounded list or pipeline, how to rank a territory, book, pipeline, ICP list, or account list, where to focus this week, or what rep-ready next actions to take. Prioritize accounts using current evidence, suppress or account for in-flight motion, and identify reachable contacts when supported. Use enrichment instead for net-new company discovery or missing-data completion.

Quality

86%

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

Quality

Content

72%

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

The body is highly actionable with concrete template/schema mechanics and good progressive disclosure to real bundle files, but it is verbose and repeats several rules across sections, and the view-generation workflow is presented as prose rather than a tight ordered checklist with checkpoints. Tightening the duplication and consolidating the generation steps would lift conciseness and workflow clarity.

Suggestions

Deduplicate the CRM-owns-universe and do-not-build-the-candidate-set-from-enrichment rules so each appears once in Overall Rules, then reference it from Account Ranking and Modes instead of restating it.

Consolidate the Account Action View generation steps into a single numbered checklist (serialize payload -> validate against schema -> escape < as \u003c -> replace placeholder -> write file -> sanity-check no placeholder remains) so the validation checkpoints read as an explicit sequence.

Trim filler phrasing like 'It is critical to use all of these categories if you can' and other restated qualifiers to recover token budget without losing meaning.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded with restated rules — the CRM-owns-universe constraint and the do-not-create-universe-from-enforcement point recur across 'Account Ranking', 'Overall Rules', and the Modes section, and some phrases ('It is critical to use all of these') are longer than needed.	2 / 3
Actionability	Fully concrete guidance: exact template path, exact JSON schema path, exact placeholder '__PRIORITIZE_ACCOUNTS_DATA_JSON__', escaping rule ('replace every < with \u003c'), OS-specific output paths, and the required account-row field list are all copy-paste ready.	3 / 3
Workflow Clarity	A numbered priority sequence and explicit validation checkpoints exist ('Sanity check that the generated file contains no unresolved placeholder', 'conforms exactly to references/template-payload.schema.json'), but the multi-step view-generation flow is spread across prose rather than a single ordered checklist, and several rules are stated in multiple places which muddles the sequence.	2 / 3
Progressive Disclosure	SKILL.md is an overview that points one level deep to clearly signaled, real bundle files — references/suppression-and-fallbacks.md, assets/account-priority-pane.template.html, and references/template-payload.schema.json all exist and are referenced with their purpose.	3 / 3
	Total	10 / 12 Passed

Description

100%

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, trigger-rich, complete, and distinctive — it names concrete actions, uses natural seller language, opens with an explicit Use-when clause, and carves out a clear niche with an explicit redirect to a sibling skill. No notable weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Prioritize accounts using current evidence, suppress or account for in-flight motion, identify reachable contacts' — plus an explicit scope exclusion ('Use enrichment instead for net-new company discovery or missing-data completion').	3 / 3
Completeness	Explicit 'Use when...' clause supplies the trigger, and the action sentence supplies what it does, clearly answering both what and when.	3 / 3
Trigger Term Quality	Uses natural seller phrasing users would actually say — 'which leads are hottest', 'rank a territory, book, pipeline, ICP list, or account list', 'where to focus this week'.	3 / 3
Distinctiveness Conflict Risk	Sits in a clear sales-prioritization niche and actively redirects a neighboring capability ('Use enrichment instead for net-new company discovery or missing-data completion'), reducing conflict risk.	3 / 3
	Total	12 / 12 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/sales/workflows/prioritize-accounts/SKILL.md
Commit: ff87d47

Reviewed: about 9 hours 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.