CtrlK
BlogDocsLog inGet started
Tessl Logo

reactivation-specialist

Use when the user asks to "build a win-back campaign", "re-engage lapsed subscribers", "run a re-permission / re-consent sweep", or "sunset my dead list"; produces a closed-loop reactivation program — a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm / suppression rule. Owns none of the SEND-N sub-item notes: engagement-decay / sunset is email-sequence-designer's and preference-center / frequency options is preference-frequency-manager's — this skill references those notes, it does not re-emit them. Not for the general lifecycle flows (welcome/cart/post-purchase) — use email-sequence-designer; not for the preference-center / opt-down ladder — use preference-frequency-manager; not for the consent record itself — use consent-registry; not for computing EQS or the N1 veto — use email-quality-auditor. 流失召回/重新授权/沉默用户清理

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable instruction-only skill with clear sequencing, decision gates, and a done-when checklist. Its main weakness is conciseness: the scope-ownership boundary is restated four times, padding the token budget without adding information.

Suggestions

Consolidate the N-sub-item ownership boundary into a single Scope guard section and reference it from the intro, Skill Contract, and step 7 instead of restating it each time.

Trim the repeated 'does not compute EQS / run vetoes' disclaimer (intro, step 7, Scope guard, Reference Materials) to a single statement.

Inline a minimal handoff-summary template rather than pointing off-bundle to skill-contract.md §Handoff Summary Format, since that file is not present in this bundle.

DimensionReasoningScore

Conciseness

Mostly efficient but the N-sub-item ownership boundary ('does not author the N sub-item notes… hands facts to owners') is restated verbatim in the intro, Skill Contract, instruction step 7, and the Scope guard, which is more than minor padding.

3 / 5

Actionability

Concrete numbered instructions with specifics (cohort window 'no open in 90 days, no click in 180', ladder trigger/delay/intent/exit, frequency cap '3–4 across the whole ladder', profile weights) — minor gaps only, e.g. the handoff summary is delegated off-bundle rather than templated.

4 / 5

Workflow Clarity

Seven sequenced steps with explicit Decision Gates, a 'Done when' checklist, and terminal-state validation ('every subject must land in exactly one terminal state'); a validate-then-repair loop for the sunset decision itself is the main missing checkpoint.

4 / 5

Progressive Disclosure

Clear section headers and one-level-deep references in a Reference Materials section (skill-contract.md, send-benchmark.md, CONNECTORS.md, SECURITY.md, sibling skills); no bundle files exist, and the repeated inlined scope-guard prose is the main organization gap.

4 / 5

Total

15

/

20

Passed

Description

100%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 exemplary: it pairs concrete natural-language trigger phrases with a clear enumeration of deliverables and explicit boundaries against four sibling skills, all in third person. It fully answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete deliverables — 'a lapsed-cohort definition, a staged offer ladder, a re-consent (re-permission) capture step, and a sunset-confirm / suppression rule' — giving comprehensive coverage of the skill's concrete actions.

5 / 5

Completeness

Explicit 'Use when...' clause with concrete trigger phrases answers 'when', and the enumerated four-part program answers 'what' clearly and concretely.

5 / 5

Trigger Term Quality

Quotes natural user phrases — 'build a win-back campaign', 're-engage lapsed subscribers', 'run a re-permission / re-consent sweep', 'sunset my dead list' — with synonyms (win-back, re-engage, re-permission, re-consent, sunset) users would actually say.

5 / 5

Distinctiveness Conflict Risk

Explicit 'Not for...' disambiguation against email-sequence-designer, preference-frequency-manager, consent-registry, and email-quality-auditor carves a clear niche with minimal overlap.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 35 suspicious

Warning

Total

13

/

16

Passed

Repository
aaron-he-zhu/aaron-marketing-skills
Reviewed

Table of Contents

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.