customer-db

Maintain a persistent SQLite customer database within the sales-cs workspace. The system hook injects peer (DB primary key) and the Sender block provides user_id_external (raw awada user ID). Use peer for all DB operations.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./crews/sales-cs/skills/customer-db/SKILL.md

Quality

Content

68%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 body is highly actionable with complete, verified executable commands and clear sequencing, but it is slightly verbose (duplicate definitions) and the database workflows lack explicit validation checkpoints, which the rubric caps at 3 for destructive/batch operations.

Suggestions

Add an explicit validation/verification checkpoint after database writes (e.g., re-query the row or check the script's exit status before proceeding), which would lift workflow_clarity above the destructive-operation cap.

Remove the duplicate definition of 'peer' (currently explained in both section 一 and section 二) to tighten conciseness.

Clarify the HEARTBEAT.md reference — either confirm it exists in the bundle or note it is system-provided — so the one-level-deep reference is not a dangling link.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but it is redundant in places — 'peer' is defined twice (sections 一 and 二) — and the long enumerated example lists for purpose/prompt_source could be tightened, matching the score-3 'could be tightened' anchor rather than the leaner score-4.	3 / 5
Actionability	Every operation ships a complete, copy-paste-ready bash invocation with real flags, real script paths, and concrete placeholders (cs-update, follow-up-create/cancel/expire/due/mark-sent/complete), and the referenced scripts exist in the bundle and are executable, matching the score-5 anchor.	5 / 5
Workflow Clarity	Sequences are explicit (update-then-reply; cancel-old-then-create-new) and status flow is documented, but the database workflows lack explicit validation/verification checkpoints. Per the rubric's destructive/database-operation rule, missing validation caps workflow_clarity at 3 even though the sequencing is otherwise clear.	3 / 5
Progressive Disclosure	The body is well-organized with clear numbered sections, and operational detail is properly externalized into the scripts/ bundle (all referenced scripts are real files). The only gap is a dangling reference to HEARTBEAT.md and ./db/schema.sql that are not present in the bundle, a minor organization issue matching score-4.	4 / 5
	Total	15 / 20 Passed

Description

51%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 concretely states what the skill does and scopes it to a specific workspace, but it is written as internal mechanism documentation rather than user-facing trigger guidance — it lacks any 'Use when...' clause and natural trigger terms.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., when a sales-cs conversation needs to persist or update customer business status).

Include natural user-facing trigger terms such as 'customer record', 'business status', 'follow-up task', or 'club membership' that a user would actually say.

Lead with the user-visible capability (saving/updating customer status across sessions) before the internal identifier mechanism, so the what/when is front-loaded.

Dimension	Reasoning	Score
Specificity	Names the domain ('Maintain a persistent SQLite customer database') and concrete mechanism details — the hook injects 'peer' as DB primary key, the Sender block provides 'user_id_external', and 'Use peer for all DB operations'. It lists several specific actions/elements rather than a single generic one, with only minor coverage gaps, matching the score-4 anchor.	4 / 5
Completeness	It clearly answers 'what' (maintain a persistent SQLite customer database) but provides no 'when'/Use-when clause at all. Per the rubric, a missing explicit trigger guidance caps completeness at 3, which is the exact anchor fit.	3 / 5
Trigger Term Quality	The only natural keyword is 'customer database' / 'SQLite'; the rest is internal mechanism jargon ('system hook', 'Sender block', 'awada user ID') that no user would naturally say. It lacks the natural trigger phrases users actually use, matching the score-2 anchor.	2 / 5
Distinctiveness Conflict Risk	It is scoped to a specific 'sales-cs workspace' and a dedicated customer SQLite database, giving it a clear niche with only minor overlap risk against other workspace skills, matching the score-4 anchor rather than the broader score-3.	4 / 5
	Total	13 / 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: TeamWiseFlow/xiaobei
Path: crews/sales-cs/skills/customer-db/SKILL.md
Commit: fdc03d6

Reviewed: 11 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.