CtrlK
BlogDocsLog inGet started
Tessl Logo

social-pulse-monitor

Use when the user asks to "monitor brand mentions", "set up social listening", "did anything spike about us this week", or "watch these accounts for buying triggers"; runs always-on keyless listening — a versioned listening-query architecture (brand variants incl. misspellings and 中文 names, exclusion terms, per-source syntax for HN Algolia / Bluesky / GDELT / Tavily), a mention sweep with six-class triage (crisis / bug / lead / praise / question / spam) each routed with an SLA, a 7-day rolling baseline with spike flags (the crisis trigger input), a B2B trigger watchlist (funding / hiring / launch signals), and an explicit coverage disclosure where X/IG/TikTok/LinkedIn/小红书 numbers are proxy-labeled, never Measured. Not for launch-window telemetry (T-0→T+30 rank and review polling) — use launch-monitor. 舆情监听/品牌提及监测/基线突刺/触发信号

70

Quality

89%

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

78%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, actionable overview of a complex listening skill with clear sequencing and consolidated references. The main gaps are restating the proxy-labeling red line multiple times and the absence of executable connector invocation examples or an explicit error-recovery loop.

Suggestions

Consolidate the proxy-labeling red line into one authoritative statement (e.g., Data Sources) and reference it elsewhere rather than restating it fully in the scope guard, instruction 2, instruction 6, and Reference Materials.

Add a short executable example showing actual connector invocation (e.g., `python scripts/connectors/hn.py --query "<brand>"`) so the sweep step is copy-paste ready, not just script-named.

Add an explicit validate→fix→retry checkpoint for the batch registry-proposal submission (e.g., what to do when registry-events.py rejects a proposal) to complete the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes Claude's competence (no basic-concept padding), but the proxy-labeling red line is restated across the scope guard, data sources, instructions, and reference materials — minor over-emphasis that could be tightened.

4 / 5

Actionability

Concrete guidance names exact scripts (hn.py, gdelt.py, tavily.py --news), paths, the spike formula (current > 2× 7-day median), triage classes with SLAs, and the registry protocol, but lacks copy-paste-ready invocation examples showing actual connector command syntax.

4 / 5

Workflow Clarity

A clear 8-step numbered sequence with a "Done when" verification checklist and ask-before-write guardrails, but no explicit validate→fix→retry feedback loop for the batch registry-proposal submission step.

4 / 5

Progressive Disclosure

Clean section structure (Quick Start → Skill Contract → Data Sources → Instructions → Save Results → Reference Materials → Next Best Skill) with a consolidated, well-signaled, one-level-deep reference list and easy navigation.

5 / 5

Total

17

/

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 comprehensive, dense, and well-targeted: it states concrete capabilities, uses natural quoted trigger phrases in both English and Chinese, answers both what and when, and explicitly disambiguates from sibling skills. Its only weakness is density that borders on verbose, but no dimension penalizes that here.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "versioned listening-query architecture", "mention sweep with six-class triage", "7-day rolling baseline with spike flags", "B2B trigger watchlist", "coverage disclosure" — with comprehensive coverage of the skill's actions.

5 / 5

Completeness

Explicitly answers both what ("runs always-on keyless listening" with the enumerated components) and when ("Use when the user asks to..."), and adds negative scope ("Not for launch-window telemetry ... use launch-monitor") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Quotes natural user utterances ("monitor brand mentions", "set up social listening", "did anything spike about us this week", "watch these accounts for buying triggers") plus synonym keywords in 中文 (舆情监听/品牌提及监测/基线突刺/触发信号), giving comprehensive trigger coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche (brand/social listening) with distinct triggers and explicit disambiguation against siblings ("Not for launch-window telemetry ... use launch-monitor"), keeping conflict risk minimal.

5 / 5

Total

20

/

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: 30 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.