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

96%

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

92%Weight 40%Scale 1-3

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

A high-quality, executable, well-sequenced workflow with strong validation feedback loops for both batch writes and destructive pruning. The only soft spot is progressive disclosure: the skill is a single self-contained file with no split-out reference material despite its length.

Suggestions

Move the "Reference queries" GraphQL block into a references/ file (e.g. references/queries.graphql.md) and link to it from the phases, so SKILL.md stays an overview.

Pull the note-format template (Phase 3) into a short references/recap-template.md so the inline format block does not inflate the main body.

Consider extracting the Phase 2 matching rules (email/domain maps, free-provider list, ambiguity handling) into a references/matching.md linked from Phase 2.

Dimension	Reasoning	Score
Conciseness	Lean and action-oriented throughout — no basic-concept explanations, no library discourse; every phase adds operational detail Claude would not already know (the 50-cap, free-provider list, ASR thresholds). It is not the level-2 anchor because there is no padded introductory explanation.	3 / 3
Actionability	Provides a complete executable `gql()` helper and copy-paste-ready GraphQL for every operation, plus concrete thresholds (>=15 sentences, >=4 words/sentence) and an exact free-provider blocklist — fully executable guidance.	3 / 3
Workflow Clarity	Six numbered phases with explicit validation checkpoints: Phase 0 stops on missing keys, Phase 4 reads notes back to verify, Phase 6 confirms and re-lists to verify deletion, with a dedup check before writing. No batch/destructive gap to cap it at 2.	3 / 3
Progressive Disclosure	Well-organized into phases, but the ~200-line body is monolithic with all GraphQL references inline and no bundle files (references/scripts/assets absent); the inline reference block is content that could be split out for one-level-deep navigation.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 names concrete actions, gives an explicit use-when trigger, and carves out a distinct niche with clear skip behavior. It would not be improved by moving to a lower anchor on any dimension.

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" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly answers both what (pull/match/recap/inject) and when via the explicit "Use after a batch of partner calls" trigger, plus the skip behavior for leads/discovery calls.	3 / 3
Trigger Term Quality	"Use after a batch of partner calls when you want each partner's CRM record updated with what was said" supplies natural terms ("partner calls", "recap", "CRM record") a user would actually say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The Fireflies + Twenty Partner + recap niche is highly specific and explicitly distinguished from the lead-matching sibling, so it is unlikely to trigger for the wrong skill.	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
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: bb4e427

Reviewed: 6 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.