follow-up-after-call

Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions and drafts.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 well-structured, actionable instruction skill with a clear multi-step workflow, confirmation gates, a failure-handling loop, and properly signaled one-level references that exist in the bundle. Weakest dimension is conciseness, driven by repeated constraints and a verbose automation section.

Suggestions

Deduplicate the no-send/no-post/no-CRM constraint so it appears once (e.g., in Output Rules) to tighten conciseness toward 5.

Tighten the Automation Offer Guard into a short rule plus a pointer to a reference, since its detail exceeds what the overview needs.

Make the 'stop once grounded' and 'enrichment is enough' checkpoints explicit (e.g., a one-line pass criterion) to lift workflow_clarity from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no basic concept explanations), but repeats the no-send/no-post/no-CRM constraint in the intro and again in step 4, and the Automation Offer Guard is verbose; a 5 would require trimming that redundancy.	4 / 5
Actionability	Highly concrete instruction-only guidance: a copy-paste output template, exact phrases ('write exactly `Not applicable: this was an internal call.`'), and exact markers (Unknown, TBD, `(paste into the relevant opp)`); not a 5 because several decision branches rely on judgment phrasing rather than fully specified rules.	4 / 5
Workflow Clarity	Four clearly sequenced steps with explicit confirmation gates ('ask the user to confirm it via `ask_user_input()` before drafting') and a Failure Handling feedback loop; not a 5 because some checkpoints (e.g., when enrichment is 'enough') are qualitative rather than explicit pass/fail criteria.	4 / 5
Progressive Disclosure	The body owns the core workflow and output while signaling two real one-level references with clear load conditions ('Use [references/request-schema.yaml] when normalizing structured input...'); not a 5 because the large inline output template and Automation Offer Guard could arguably live in a reference, leaving the overview leaner.	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, third-person description that clearly states both the trigger conditions and the concrete actions, with good natural-term coverage and a distinct niche. Main room for improvement is tightening the action list and adding shorter user-typed shorthand triggers.

Suggestions

Add compact shorthand triggers users actually type (e.g., 'follow up after my call', 'recap my last call', 'send a post-call email') to lift trigger-term coverage from 4 to 5.

Tighten the action list to mirror the output package sections (recap, action items, external email, CRM next step, internal recap) so specificity reflects full coverage.

Dimension	Reasoning	Score
Specificity	Names the post-call domain and lists several concrete actions ('Advise on, assess, qualify, recap, and produce seller-ready follow-up actions and drafts'), with only minor coverage gaps; not a 5 because the actions stay somewhat high-level rather than enumerating the full package components.	4 / 5
Completeness	Explicitly answers both 'when' ('Use after a completed ... call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence') and 'what' (advise, assess, qualify, recap, produce drafts) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keyword coverage across synonyms ('customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation') and evidence forms ('transcript, notes, recording summary'), with a few common variations omitted; not a 5 since it lacks compact shorthand phrases a user would actually type.	4 / 5
Distinctiveness Conflict Risk	The post-call sales follow-up niche is specific and the triggers ('after a completed ... sales call, discovery session, demo') are distinct, giving minimal conflict risk with unrelated skills.	5 / 5
	Total	18 / 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
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/follow-up-after-call/SKILL.md
Commit: be5af90

Reviewed: 5 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.