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

71

Quality

90%

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

81%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 instruction skill with a clear sequenced workflow and explicit validation checkpoints. Its main weakness is repetition of the same red-line and registry-write guidance across multiple sections.

Suggestions

Consolidate the proxy-labeling red line and registry propose-path into a single authoritative statement, then reference it rather than restating in Scope Guard, Data Sources, Instructions step 6/7, Save Results, and Reference Materials.

Move the connector-by-connector detail (rate limits, syntax per source) entirely into CONNECTORS.md and keep the body to a brief pointer, reducing inline density.

Add a short 'Done when' checklist recap near the top of Instructions so the verification gates are visible without reading all 8 steps.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's competence, but the proxy-labeling red line, registry propose path, and scope guards are restated across Scope Guard, Data Sources, Instructions, and References, adding some redundancy that keeps it short of fully lean.

4 / 5

Actionability

Provides concrete connector scripts, specific spike threshold (current day > 2× the 7-day median), per-class SLAs, and exact memory paths, yielding mostly executable guidance with only minor gaps from the absence of inline code snippets.

4 / 5

Workflow Clarity

An 8-step numbered sequence is paired with explicit verification gates ('Done when' criteria, coverage disclosure requiring every closed-platform cell labeled, 'ask before writing' to hot-cache) and idempotent registry proposals resolved in offset order as a validation checkpoint.

5 / 5

Progressive Disclosure

No bundle files exist, but the body uses well-signaled one-level-deep references ([CONNECTORS.md], [echo-benchmark.md], [skill-contract.md], [SECURITY.md]) in a dedicated Reference Materials section; the repeated inline red-lines prevent a top score.

4 / 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 third-person, specific, and densely packed with concrete capabilities and natural trigger phrases, clearly distinguishing itself from sibling skills. It is a strong, near-ideal skill description.

DimensionReasoningScore

Specificity

Names multiple concrete actions—versioned listening-query architecture with per-source syntax, six-class triage with per-class routing and SLA, 7-day baseline with spike flags, B2B trigger watchlist, and coverage disclosure—covering the skill comprehensively.

5 / 5

Completeness

Explicit 'Use when...' clause with concrete trigger phrases answers 'when', while the enumerated capabilities (query architecture, sweep, triage, baseline, watchlist, disclosure) answer 'what', plus a 'not for' exclusion.

5 / 5

Trigger Term Quality

Includes natural user phrases ('monitor brand mentions', 'set up social listening', 'did anything spike about us this week', 'watch these accounts for buying triggers') plus synonyms and 中文 keywords, giving comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche (always-on keyless listening) with explicit disambiguation against launch-monitor, engagement-inbox-manager, share-of-voice-tracker, and crisis-response-planner, minimizing conflict risk.

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.