CtrlK
BlogDocsLog inGet started
Tessl Logo

engagement-inbox-manager

Use when the user asks to "triage our comments, DMs, and mentions", "draft replies to this thread", "can we repost this fan post", or "set up inbox SLAs and an escalation path"; produces a ranked triage queue with register detection (sincere / ironic / performative / parasocial, sentiment-inversion table included — "this is so bad" under a comedy register is praise), a commenter taxonomy (troll monitor-only / rager / misguided / unhappy-customer / advocate) with a response-tier ladder and per-channel SLAs, an escalation matrix ending at the crisis path, a moderation ladder plus house rules for owned spaces, and a UGC curation-and-rights mode whose dated permission entries route to the channel registry — every reply is a ranked DRAFT a human posts; nothing is ever auto-sent. Not for launch-window feedback triage — use launch-feedback-synthesizer. 评论私信提及分诊/语域识别/回复草稿/UGC授权

72

Quality

92%

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

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-sequenced, actionable instruction skill with strong validation checkpoints and clean one-level-deep navigation. The only weakness is redundancy — several guard rails and routing rules are repeated verbatim across sections.

Suggestions

Consolidate the registry-write rule (propose via registry-events.py to memory/events/channels.ndjson, never memory/channels/) into one canonical statement rather than restating it in Scope guard, Reads/Writes/Promotes, Instructions steps 7-8, and Save Results.

State the crisis-path hand-off boundary once and link to crisis-response-planner, instead of repeating it in the intro, Scope guard, Instruction step 4, References, and Next Best Skill.

Consider moving the eight UGC permission-entry fields and the escalation-matrix row definitions into a referenced reference doc to slim the inline Instructions section.

DimensionReasoningScore

Conciseness

Largely efficient prose but padded: the scope guard, registry-write rule, and crisis-handoff caveat are each restated multiple times across the intro, Scope guard, Skill Contract, Instructions, and Reference Materials, which could be tightened.

2 / 3

Actionability

Concrete, executable guidance throughout — eight numbered steps name exact memory paths, the eight permission-entry fields, the escalation row types, and the propose-via-registry-events.py routing — instruction-only but fully actionable.

3 / 3

Workflow Clarity

A clear eight-step sequence with explicit validation checkpoints: NEEDS_INPUT on missing exports, crisis-path hand-off the moment a matrix row trips, evidence-link capture before a permission entry, and idempotent propose-and-resolve ordering — plus a 'Done when' checklist.

3 / 3

Progressive Disclosure

Well-organized overview (Quick Start, Skill Contract, Data Sources, Instructions, References, Next Best Skill) with one-level-deep references to sibling skills and named reference docs; no nested reference chains and no bundle files to resolve.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 highly specific, with verbatim natural-language triggers and an explicit what/when/negative-when structure. Its main weakness is verbosity — the parenthetical examples and Chinese gloss could be trimmed without losing triggering power.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'ranked triage queue with register detection', 'commenter taxonomy ... with a response-tier ladder and per-channel SLAs', 'escalation matrix', 'UGC curation-and-rights mode ... dated permission entries' — matching the top anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (the produced artifacts enumerated) and when (the 'Use when the user asks to ...' triggers), plus a negative trigger ('Not for launch-window feedback triage — use launch-feedback-synthesizer'), satisfying the top anchor.

3 / 3

Trigger Term Quality

Quotes natural user phrasings verbatim ('triage our comments, DMs, and mentions', 'draft replies to this thread', 'can we repost this fan post', 'set up inbox SLAs and an escalation path'), which are terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear niche (always-on social inbox triage/drafting) with distinct quoted triggers and an explicit hand-off boundary to launch-feedback-synthesizer, making a wrong-skill trigger unlikely.

3 / 3

Total

12

/

12

Passed

Validation

75%

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

Validation12 / 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: 34 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

12

/

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.