churn-risk-detector

Scan support tickets, Slack channels, NPS scores, and usage patterns to flag accounts showing early churn indicators. Produces a weekly risk scorecard with severity tiers, root cause hypotheses, and suggested save plays per account. Designed for seed/Series A teams where the founder or a single CSM manages all accounts manually.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/research/composites/churn-risk-detector/SKILL.md

Quality

Content

76%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 concrete thresholds, a transparent scoring model, and copy-paste templates, and it is well-structured across phases. Its main weaknesses are missing validation checkpoints in a batch workflow and minor redundancy between the trigger-phrase and cost/tools sections.

Suggestions

Add explicit validation checkpoints to the workflow, e.g. after Phase 1 'Confirm required signal sources are present before scoring' and after Phase 2 'Spot-check one Red account's signals before generating save plays.'

Remove the duplicate 'Trigger Phrases' section (it restates 'When to Use') or merge them, and consolidate the overlapping 'Cost' and 'Tools Required' sections.

Consider extracting the long output-format template (Phase 4) into a reference file once the skill grows, to keep SKILL.md as a leaner overview.

Dimension	Reasoning	Score
Conciseness	Largely efficient and task-specific (no padding explaining what churn/Slack/NPS are), but the closing 'Trigger Phrases' section restates the opening 'When to Use' list and the 'Cost' and 'Tools Required' sections overlap ('No external API costs — pure analysis'); these minor redundancies could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready, executable guidance: specific signal thresholds ('>2x their average in last 30 days', 'Open tickets older than 7 days'), a concrete weighted scoring model (Critical=25, High=15, ...), a fill-in save play template, and a full output-format template covering the common cases.	5 / 5
Workflow Clarity	Phases 0–4 are clearly sequenced (Intake → Signal Extraction → Risk Scoring → Save Play → Output), but the workflow has no validation checkpoints (e.g. verify data completeness before scoring, spot-check a Red account), and as a batch weekly scan over many accounts this triggers the rubric's batch-operation cap of 3.	3 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-sectioned file with clear Phase 0–4 headers and supporting sections, and content is appropriately placed for a standalone analysis skill. Minor gap: the ~75-line output-format template could optionally be split into a reference file, but inlining is reasonable here.	4 / 5
	Total	16 / 20 Passed

Description

75%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 is specific, distinctive, and rich in domain-appropriate terminology, but it lacks an explicit 'Use when...' trigger clause, which caps completeness. Adding a concrete trigger sentence would lift the completeness and trigger_term_quality dimensions.

Suggestions

Append an explicit 'Use when...' clause with natural trigger phrases, e.g. 'Use when running a weekly churn scan, flagging at-risk accounts, or producing a customer health report.'

Add common synonyms users say — 'retention', 'customer health', 'renewal risk' — alongside 'churn' to broaden trigger term coverage.

Keep the concrete action list as-is; it is already comprehensive and well-scoped.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Scan support tickets, Slack channels, NPS scores, and usage patterns', 'flag accounts showing early churn indicators', 'Produces a weekly risk scorecard with severity tiers, root cause hypotheses, and suggested save plays' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers 'what' (scan signals, produce weekly scorecard with tiers/hypotheses/save plays) but provides no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by 'weekly', so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good coverage of natural churn-domain terms ('churn indicators', 'risk scorecard', 'save plays', 'CSM'), but misses common synonyms a user might say such as 'retention', 'customer health', 'renewal risk', or 'at-risk customers'.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche — churn risk detection for seed/Series A teams with no CS platform and a founder/single CSM — with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: gooseworks-ai/goose-skills
Path: skills/research/composites/churn-risk-detector/SKILL.md
Commit: 2523432

Reviewed: 7 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.