CtrlK
BlogDocsLog inGet started
Tessl Logo

draft-crm-note

Use when converting a supplied interaction or reply into a structured CRM-note draft without changing an external record.

69

Quality

85%

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

100%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 tight, well-structured instruction skill: lean prose, a concrete copy-paste output template, a sequenced workflow with a safety gate, and a final validation checklist. It assumes Claude's competence throughout and needs no external references.

DimensionReasoningScore

Conciseness

The body is lean and directive with no padding or explanation of concepts Claude already knows; every section (Purpose, Required inputs, Workflow, Output format, Guardrails, Quality check) earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

Although instruction-only, the guidance is fully executable: concrete workflow steps (e.g., label interpretations `Inference` with supporting fact, list unsupported fields under `Unknowns`) plus a copy-paste markdown output template provide complete, specific direction.

5 / 5

Workflow Clarity

A clear 6-step sequence is paired with an explicit gating checkpoint (step 5) and a final validation checklist (Quality check), giving explicit validation steps and a safety gate; the skill is non-destructive (DRAFT ONLY) so a fix-retry loop is not required.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed; the single-purpose skill is well-organized into clearly labeled sections with no nested references, satisfying the simple-skill exception for a 5.

5 / 5

Total

20

/

20

Passed

Description

70%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 concise, third-person, and answers both what and when with a clear niche and low conflict risk. Its main limitation is specificity—the action set is narrow and the "when" trigger restates the task rather than expanding into situational phrases.

Suggestions

Broaden specificity by naming the discrete outputs the draft contains (e.g., observed facts, inferences, unknowns, proposed next step) rather than a single 'converting' action.

Expand the 'when' clause with situational triggers users actually voice, such as 'Use when logging a reply, summarizing an interaction, or drafting a case note for review'.

Add common synonyms (log, case note, activity note) to improve trigger-term coverage for users who do not say 'CRM note'.

DimensionReasoningScore

Specificity

"converting a supplied interaction or reply into a structured CRM-note draft" names the domain and one concrete action (convert to structured draft) but does not enumerate several distinct capabilities, matching the 1-2 concrete actions anchor rather than the multi-action 4.

3 / 5

Completeness

An explicit "Use when..." clause supplies the trigger and the action states the what, so both are present; the "when" restates the task rather than offering distinct situational triggers, so it does not reach the multi-phrase clarity of a 5.

4 / 5

Trigger Term Quality

Natural terms a user would say are present ("interaction", "reply", "CRM-note", "draft") giving good coverage, though common synonyms like "log", "case note", or "activity note" are missing, fitting the good-but-incomplete anchor.

4 / 5

Distinctiveness Conflict Risk

The CRM-note-drafting niche and the "without changing an external record" qualifier distinguish it from CRM-update skills with only minor overlap risk against general note-taking/summarization skills, fitting the mostly-distinct anchor.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
llaskin/AI-SDR-Skill-Pack
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.