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

68

Quality

85%

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

75%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 a well-structured hosting contract: a sequenced eight-step workflow with explicit validation gates, concrete read/write/promote boundaries, and cleanly signaled references. Its main weakness is modest redundancy of the auto-send guard and platform lists across sections.

Suggestions

Collapse the repeated 'never auto-sends/auto-replies/DMs/schedules' guard so it is stated once in the Scope guard and referenced from instruction steps 5 and 7 rather than restated.

State the closed-platform (X/IG/TikTok/LinkedIn/小红书/微信公众号/视频号/抖音) list once in Data Sources and reference it elsewhere to cut duplicated tokens.

Add one copy-paste connector invocation example (e.g. `scripts/connectors/bluesky.py`) to lift actionability toward fully-executable guidance.

DimensionReasoningScore

Conciseness

The body is largely efficient and assumes Claude's competence (no definitions of registers, SLAs, or platforms), but the auto-send guard and the closed-platform list are restated across the scope guard, Data Sources, and instruction steps 5/7, which could be trimmed — sitting at efficient-with-minor-redundancy rather than lean.

4 / 5

Actionability

Eight numbered steps give concrete, mostly executable guidance with named scripts (registry-events.py, bluesky.py) and explicit permission-entry fields; it stops short of copy-paste code/invocation examples for the connectors, leaving minor gaps versus the fully-executable score-5 anchor.

4 / 5

Workflow Clarity

A clear eight-step sequence with explicit checkpoints (step 1 NEEDS_INPUT, escalation trip → hand off and stop drafting, idempotent proposals, owner-review flags, a 'Done when' checklist) — the validation is distributed rather than a single validate-then-proceed loop, placing it just below the score-5 anchor.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep references (echo-benchmark.md, channel-registry, skill-contract.md, CONNECTORS.md, SECURITY.md) and a dedicated Reference Materials list; with no bundle files present, some inlined detail (repeated platform lists, scope-guard depth) could be externalized, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

96%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 unusually thorough: it pairs concrete capability coverage with verbatim user trigger phrases and an explicit out-of-scope boundary. It is dense rather than padded, with every clause tied to a deliverable or trigger.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — register detection with a sentiment-inversion table, a five-class commenter taxonomy with a response-tier ladder and per-channel SLAs, an escalation matrix ending at the crisis path, a moderation ladder plus house rules, and a UGC curation-and-rights mode with eight permission fields — comprehensive coverage, matching the score-5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (the full produced deliverable set) and 'when' (four quoted trigger phrases), and adds a negative 'Not for launch-window feedback triage — use launch-feedback-synthesizer' boundary, matching the score-5 anchor for explicit what-and-when with concrete triggers.

5 / 5

Trigger Term Quality

Embeds verbatim natural user requests ("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") plus synonyms (comments/DMs/mentions) and a negative trigger, giving comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

A clear niche (always-on social-inbox hosting) with distinct triggers and an explicit negative boundary to one sibling skill; the disambiguation names only launch-feedback-synthesizer rather than the full sibling set, so it sits at 'mostly distinct; minor overlap risk' rather than the score-5 minimal-conflict anchor.

4 / 5

Total

19

/

20

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.