bond

Designing retention strategy, re-engagement, and churn prevention: retention analysis frameworks, re-engagement triggers, gamification, habit formation, and loyalty programs.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.archive/bond/SKILL.md

Quality

Content

60%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 a clear sequenced workflow and well-signaled reference navigation, but it is noticeably verbose — heavy inline statistics and a long time-sensitive regulatory paragraph with many specific dates inflate the token budget and drag down conciseness.

Suggestions

Move the dense regulatory/citation paragraph (FTC click-to-cancel, ROSCA, EU Directive 2023/2673, DFA with specific 2025-2026 dates) into a dedicated reference file or a clearly marked 'regulatory' section, keeping only the operative rule inline.

Trim inline statistic dumps (e.g., '25-95% profitability', '91-95% accuracy', '~32% higher prediction accuracy') to the single most decision-relevant figure per claim, offloading the rest to a benchmarks reference.

Make the MEASURE-phase validation explicit with a concrete feedback loop (define KPI → run experiment → check significance → iterate or rollback) rather than leaving it as 'propose an experiment or rollout check'.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: multiple inline statistic dumps and a ~150-word regulatory paragraph carrying 8+ specific dates ('July 2025', 'March 11, 2026', 'June 19, 2026', 'late 2026') appear inline rather than in a deprecated/old-patterns section, triggering the time-sensitivity penalty.	2 / 5
Actionability	Provides concrete executable guidance — segment churn benchmarks, dormancy thresholds (3d/7d), the pause→downgrade→discount offer sequence with acceptance rates, lifecycle day-by-day structure, and a 6-item deliverable template — with only minor gaps where directives stay high-level ('Match signal to intervention').	4 / 5
Workflow Clarity	The MONITOR→IDENTIFY→INTERVENE→MEASURE sequence is clear with MEASURE as an explicit verification checkpoint, Ask-First boundaries as risk checkpoints, and Output Routing for branching; validation is present but somewhat abstract with no deep error-recovery loop.	4 / 5
Progressive Disclosure	A 'Reference Map' plus a Recipes 'Read First' column give clear one-level-deep navigation to reference files, but no bundle files are shipped to verify, and dense inline regulatory/ML-model detail could be split into references.	4 / 5
	Total	14 / 20 Passed

Description

66%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 and occupies a distinct retention/churn niche with good natural trigger terms, but it omits any explicit 'Use when...' trigger clause, which caps completeness at 3. Tightening action framing and adding trigger phrases would lift it.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger situations (e.g., 'Use when the user wants to reduce churn, recover dormant users, design save flows, or build loyalty/gamification mechanics').

Add common synonyms users say ('win-back', 'save flow', 'dormant users', 'NRR/GRR') to broaden trigger-term coverage.

Reframe capability areas as discrete actions (e.g., 'Analyze churn cohorts, design re-engagement triggers, build loyalty programs') to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Lists several specific capability areas ('retention analysis frameworks, re-engagement triggers, gamification, habit formation, and loyalty programs'), but these are framed as domain categories rather than discrete atomic actions, leaving minor gaps.	4 / 5
Completeness	Has a clear 'what' (designing retention/re-engagement/churn-prevention plus listed frameworks), but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes natural keywords users would say ('retention strategy', 're-engagement', 'churn prevention', 'gamification', 'habit formation', 'loyalty programs'), but misses common synonyms like 'win-back', 'save flow', 'dormant users', or 'NRR'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear retention/churn niche with distinct triggers and minimal conflict risk, with only minor overlap risk against closely related growth/marketing/lifecycle skills that the body itself routes to.	4 / 5
	Total	15 / 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: simota/agent-skills
Path: .archive/bond/SKILL.md
Commit: f425adc

Reviewed: 5 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.