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

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.

A well-structured, highly actionable body with a clear sequenced workflow, validation checkpoints, and clean one-level references. The only weakness is moderate redundancy: the proxy-labeling red line and registry proposal path are restated in several sections.

Suggestions

State the proxy-labeling red line and the registry 'operation: propose' write path once (e.g., in the Skill Contract or Instructions) and reference back rather than restating them in Scope guard, Data Sources, Instructions steps 3/6/7, and Save Results.

The repeated closed-platform list (X/IG/TikTok/LinkedIn/小红书/微信公众号/视频号/抖音) appears in the Scope guard, Data Sources, and Instructions step 6 — consolidate into the coverage-disclosure step and point to it.

DimensionReasoningScore

Conciseness

Dense and free of generic concepts Claude already knows, but the proxy-labeling red line and the registry 'operation: propose' path are restated across the Scope guard, Data Sources, Instructions (steps 3/6/7), and Save Results sections — some tightening would remove redundancy. Not a 3 because the repetition is non-trivial; not a 1 because nothing is padded with known concepts.

2 / 3

Actionability

Executable throughout: named connector scripts (hn.py, bluesky.py, gdelt.py with '≥5s between calls'), a concrete spike threshold ('current day > 2× the 7-day median'), six triage classes each with a named routing target and SLA, and explicit write paths under memory/social/social-pulse-monitor/.

3 / 3

Workflow Clarity

An 8-step numbered sequence with explicit checkpoints: a 'Done when' criterion, the coverage-disclosure table as a verification step, and an idempotent propose-only registry write path. Validation/feedback for the risky batch-write operation is present (never edit the stream directly; channel-registry resolves proposals).

3 / 3

Progressive Disclosure

Overview body points to one-level-deep, clearly signaled references — CONNECTORS.md, SECURITY.md, echo-benchmark.md, skill-contract.md, and sibling SKILL.md files — gathered in a Reference Materials list. No local bundle files exist to verify, but the reference structure is clean and shallow.

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.

A highly specific, third-person description with natural trigger phrasings, a full what-and-when statement, and an explicit scope boundary against the launch-monitor sibling. It earns top marks on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'versioned listening-query architecture', 'mention sweep with six-class triage (crisis / bug / lead / praise / question / spam) each routed with an SLA', '7-day rolling baseline with spike flags', 'B2B trigger watchlist', 'explicit coverage disclosure' — not vague abstractions.

3 / 3

Completeness

Explicitly answers both: what it does ('runs always-on keyless listening — ...') and when to use it ('Use when the user asks to ...'), with the 'Use when...' trigger clause present.

3 / 3

Trigger Term Quality

Quotes natural user phrasings as triggers — 'monitor brand mentions', 'set up social listening', 'did anything spike about us this week', 'watch these accounts for buying triggers' — terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Clear niche (always-on keyless listening) plus an explicit negative boundary — 'Not for launch-window telemetry (T-0→T+30 rank and review polling) — use launch-monitor' — making collision with siblings 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: 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.