CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

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.

A highly actionable, well-structured skill body with concrete payload contracts, an exact template workflow, and a complete fallback output format. Its main costs are redundancy (duplicated read-only rules and overlapping automation/next-step sections) and a couple of malformed or external cross-references.

Suggestions

Consolidate the duplicated read-only rule from 'Overall Rules' and 'Automation Offer Guard' into a single statement, and fold the Automation Offer Guard's offer logic into the Next Step Options section to remove overlap.

Fix the malformed mandatory link on the 'Common Skill Instructions' line (add a space and a proper path separator, e.g. 'plugins/sales/skills/index/SKILL.md#cross-skill-best-practices') so the referenced section is reachable.

Add a short error-recovery step for view generation (what to do if the payload fails template-payload.schema.json validation or the placeholder sanity check fails), and present the View Generation Rules as a numbered sequence.

DimensionReasoningScore

Conciseness

The body is dense and instructional with no padding about concepts Claude already knows, but it carries real redundancy: the read-only prohibition appears both in 'Overall Rules' and again in the Automation Offer Guard section, and the Automation Offer Guard overlaps heavily with the Next Step Options list. It is more than minor trimming, so it sits at anchor 3 rather than 4.

3 / 5

Actionability

Fully executable guidance throughout: exact template path (assets/account-priority-pane.template.html), exact placeholder (__PRIORITIZE_ACCOUNTS_DATA_JSON__), per-OS output paths, an escaping rule (replace < with \u003c), a canonical payload schema, a complete copy-paste Chat Fallback markdown format, and a ready-to-use automation prompt template. This matches the copy-paste-ready anchor 5.

5 / 5

Workflow Clarity

The ranking priority order and the view-generation procedure (build payload → serialize → escape → replace placeholder → write → sanity check for unresolved placeholders → return link) are clearly sequenced with an explicit validation checkpoint. It falls short of anchor 5 because there is no error-recovery loop (e.g., what to do when the payload fails schema validation) and the generation sequence is a flat bullet list rather than an ordered checklist. The destructive/batch cap does not apply since the skill is explicitly read-only.

4 / 5

Progressive Disclosure

References are one level deep, clearly signaled, and all real (references/suppression-and-fallbacks.md, references/template-payload.schema.json, and the assets template all exist in the bundle with substantive content). Not anchor 5 because the mandatory cross-skill link is malformed ('plugins/sales/skills/index/SKILL.md## Cross-Skill Best Practices' is missing a separator) and the trailing ../index/SKILL.md section references point outside the bundle, leaving minor navigation gaps.

4 / 5

Total

16

/

20

Passed

Description

87%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 strong description with explicit 'Use when...' trigger phrases, concrete capability statements, and clear boundary guidance against the enrichment skill. The only weaknesses are minor: some internal jargon and a few missing natural synonyms.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'Prioritize accounts using current evidence, suppress or account for in-flight motion, and identify reachable contacts when supported' — with only minor gaps and some internal jargon ('grounded list', 'rep-ready'). It lists more than 1-2 actions but falls short of the fully comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both: what ('Prioritize accounts using current evidence, suppress or account for in-flight motion, and identify reachable contacts when supported') and when ('Use when the user asks which existing accounts to work now...') with concrete trigger phrases. It also adds boundary guidance ('Use enrichment instead for net-new company discovery'), matching the top anchor exactly.

5 / 5

Trigger Term Quality

Covers natural phrases users would actually say — 'which accounts to work now', 'which leads are hottest', 'how to rank a territory', 'where to focus this week', 'pipeline', 'ICP list', 'account list'. Good keyword coverage, but a few common synonyms (e.g., 'target list', outreach-prioritization phrasings) are missing, so it does not reach the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (prioritizing existing accounts in a pipeline/territory) and explicitly disambiguates from the nearest neighbor ('Use enrichment instead for net-new company discovery or missing-data completion'), giving minimal conflict risk.

5 / 5

Total

18

/

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

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
XiaomiMiMo/MiMo-Code
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.