twenty-partner-meeting-recap

Pull recent Fireflies partner meetings, match each to an existing Partner record by attendee email/domain, write a recap (transcript-first, Fireflies summary as fallback), and inject it as a Note on the partner's profile. Use after a batch of partner calls when you want each partner's CRM record updated with what was said. Read-only for leads/discovery calls (they have no Partner match and are skipped).

Quality

90%

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

88%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 high-quality, actionable skill body with copy-paste GraphQL, precise thresholds, and strong validation/feedback loops for both the batch write and the destructive prune path. Only minor conciseness and structural-split refinements would push it higher.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding about what Fireflies or a CRM is — with every phase and gotcha (User-Agent header, transcripts cap of 50, ASR garble thresholds) earning its place; a few explanatory asides like 'the historical convention' could be trimmed.	4 / 5
Actionability	Fully executable guidance: exact GraphQL queries for every operation, a copy-paste Python helper, precise matching rules, and concrete numeric thresholds (>=15 sentences, >=4 words/sentence) for the content-quality gate.	5 / 5
Workflow Clarity	A clearly sequenced Phase 0–6 flow with explicit validation checkpoints — prerequisite key check, content-readiness skip, dedup-before-write, read-back verification, and for --prune an explicit confirm-then-delete-then-verify loop with irreversible-deletion warnings.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a dedicated Reference queries block; no bundle files exist so everything is inlined, and the sizable GraphQL reference could conceivably live in a separate file, but single-file placement is reasonable and easy to navigate.	4 / 5
	Total	18 / 20 Passed

Description

92%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, specific description that clearly states what the skill does and when to use it, with concrete actions and a useful boundary clause. Slightly niche trigger vocabulary keeps it just short of perfect trigger-term breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Pull recent Fireflies partner meetings', 'match each to an existing Partner record by attendee email/domain', 'write a recap (transcript-first, Fireflies summary as fallback)', 'inject it as a Note on the partner's profile' — with comprehensive coverage of the end-to-end flow.	5 / 5
Completeness	Explicitly answers both what (pull, match, recap, inject as Note) and when ('Use after a batch of partner calls when you want each partner's CRM record updated'), plus a boundary clause ('Read-only for leads/discovery calls ... are skipped').	5 / 5
Trigger Term Quality	Natural trigger phrases like 'partner calls', 'CRM record updated with what was said', and 'Fireflies' map well to what a user would say, though coverage is domain-specific jargon with few synonyms rather than comprehensive synonym/extension coverage.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Fireflies partner meetings → existing Partner record → CRM Note) with distinct triggers; the body further distinguishes it from sibling 'twenty-partner-match', giving minimal conflict risk.	5 / 5
	Total	19 / 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: twentyhq/twenty
Path: packages/twenty-apps/internal/twenty-partners/src/skills/twenty-partner-meeting-recap/SKILL.md
Commit: d43ab16

Reviewed: 9 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.