twilio-customer-memory

Store and retrieve customer context using Twilio Conversation Memory. Covers Memory Store provisioning, profile management, traits, observations, conversation summaries, and semantic Recall. Use this skill to give AI agents or human agents persistent memory of customer interactions across sessions and channels.

Quality

82%

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

72%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 integration guide with executable dual-language examples and a strong gotchas (CANNOT) section. Its main weaknesses are the absence of explicit validation/feedback loops around batch operations and an inlined bulk API reference that could be split out for better progressive disclosure.

Suggestions

Add explicit validation checkpoints after batch operations (e.g. verify the observation count returned, confirm linkage by reading back a profile) and a fix-and-retry note to lift workflow_clarity above the batch-operation cap of 3.

Move the per-endpoint API reference into a separate reference file (e.g. references/api-reference.md) and keep SKILL.md as an overview with one-level-deep links, improving progressive_disclosure.

Reduce token cost by leading with one canonical language example per step and folding the alternate language into a collapsed/secondary reference rather than duplicating every block inline.

Dimension	Reasoning	Score
Conciseness	Concepts are explained leanly with no padding of basics Claude already knows, but every step ships full dual Python+Node.js blocks, which is a notable token cost that could be tightened for one-language-first audiences.	4 / 5
Actionability	Copy-paste-ready, fully executable code in both Python and Node.js across all endpoints with real hosts, env-var auth, and concrete request bodies, plus a Recall mode table covering the common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced with explicit ordering constraints ('Do this before setting up...', 'Memory Store must be created before...') and a CANNOT section, but batch write operations lack explicit validate/verify checkpoints or a fix-and-retry feedback loop, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections are well-organized (Overview, Prerequisites, Quickstart, Key Patterns, CANNOT, Next Steps) with signaled sibling-skill links, but the full per-endpoint API reference for multiple languages is inlined in a single ~370-line file rather than split into reference files, and no bundle files exist.	3 / 5
	Total	15 / 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 description that concisely states concrete capabilities and an explicit use-when clause scoped to persistent customer/agent memory. Trigger phrasing is clear but leans slightly abstract rather than enumerating natural user-facing terms.

Suggestions

Add concrete trigger keywords users would actually say (e.g. 'customer history', 'remember this customer', 'recall past interactions') to strengthen natural-keyword coverage.

Consider naming the target artifact/channel (e.g. 'Twilio conversations', 'voice/call agents') so the when-clause has more concrete, distinct trigger surfaces.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — 'Store and retrieve customer context', 'Memory Store provisioning, profile management, traits, observations, conversation summaries, and semantic Recall' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (Store and retrieve customer context; covers provisioning, profiles, traits, observations, summaries, Recall) and 'when' ('Use this skill to give AI agents or human agents persistent memory of customer interactions across sessions and channels').	5 / 5
Trigger Term Quality	Includes natural phrasing like 'persistent memory of customer interactions across sessions and channels', but the triggers are somewhat abstract and miss common synonyms or concrete artifact terms a user might actually say.	4 / 5
Distinctiveness Conflict Risk	The 'Twilio Conversation Memory' niche is specific with distinct triggers, making overlap with unrelated skills minimal; it would not fire for general document or memory tasks.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/twilio-developer-kit/skills/twilio-customer-memory/SKILL.md
Commit: 1dc1958

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.