social-measurement-loop

Use when the user asks to "run the weekly social readout", "which denominator does our engagement rate use", or "which posts won this week and what changes next cycle"; produces the organic-social metric dictionary (every rate names its denominator — ERR engagement-by-reach vs ERI by-impressions vs ER-by-follower — locked across periods), median-not-mean per-post rollups with organic and boosted separated, EMV as labeled exec-translation only (never inside any score), an attributed CHAOSS/Orbit-style community-health readout with employees excluded, and the best/worst-performer write-back the next calendar cycle consumes. Not for dollar-ROI math or the ECHO profile result gate verdict — use roi-calculator and social-quality-auditor. 社媒周报/互动率分母/指标字典/复盘回写

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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-structured, actionable measurement loop with an explicit step sequence, a 'Done when' validation checklist, and a clean one-level reference section. Its main weakness is conciseness: the registry-routing rule and scope exclusions are repeated verbatim across several sections and could be stated once and referenced.

Suggestions

State the registry-events.py 'operation: propose' routing rule once (e.g., in a Constraints or Writes subsection) and reference it from Instructions step 7 and Save Results instead of repeating the full clause verbatim four times.

Collapse the Scope guard exclusion list and the Next Best Skill routing into a single 'out-of-scope' reference, since both enumerate the same handoffs (roi-calculator, share-of-voice-tracker, dark-social-attributor, performance-analyzer).

Consolidate the repeated 'median, not mean' and 'employees excluded' rationales so each appears once in Instructions and is not restated in the Skill Contract and Data Sources sections.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and does not explain basic concepts Claude already knows, but the registry-routing clause 'via an authorized operation: propose request to registry-events.py' recurs ~4 times nearly verbatim (Scope guard, Writes, Instructions step 7, Save Results) and scope exclusions repeat across Scope guard and Next Best Skill — accurate but could be tightened, matching the level-2 anchor rather than 'every token earns its place'.	2 / 3
Actionability	Concrete and specific for an instruction-only skill: named connectors (discourse.py, bluesky.py, gdelt.py), exact save paths (memory/social/social-measurement-loop/YYYY-MM-DD-<period>-readout.md), explicit formulas (ERR = engagements ÷ reach), and required labels (Measured/User-provided/Estimated); the scoring note permits absence of code when guidance is this actionable, so it reaches the level-3 bar rather than stopping at pseudocode-level guidance.	3 / 3
Workflow Clarity	An explicit 8-step numbered sequence is paired with a 'Done when' completion checklist ('every reported rate names its denominator and matches the prior period's lock... rollups are medians... EMV appears in no score') and NEEDS_INPUT / trend-restart feedback paths, satisfying the level-3 anchor of clear sequence with explicit validation rather than the level-2 case of checkpoints only implicit.	3 / 3
Progressive Disclosure	The Reference Materials section lists one-level-deep, well-signaled links each with a one-line purpose (echo-benchmark.md, CONNECTORS.md, SECURITY.md, measurement-protocol.md, plus sibling skills), and the body is organized into clearly navigable sections; no bundle files exist so this is scored on the signaled references, fitting the level-3 anchor of clear overview with well-signaled one-level references rather than inline content that should be split out.	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 exemplary: third-person voice, explicit natural-language triggers, a dense list of concrete capabilities with named denominators, and explicit exclusions that distinguish it from roi-calculator and social-quality-auditor. Both 'what' and 'when' are clearly answered with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named technical detail — 'produces the organic-social metric dictionary (every rate names its denominator — ERR engagement-by-reach vs ERI by-impressions vs ER-by-follower)', 'median-not-mean per-post rollups with organic and boosted separated', 'EMV as labeled exec-translation', 'community-health readout with employees excluded', 'best/worst-performer write-back' — matching the level-3 anchor of several specific concrete actions rather than a single domain mention.	3 / 3
Completeness	Explicitly answers both 'what' (the dictionary, rollups, EMV, community-health readout, write-back) and 'when' via an explicit 'Use when the user asks to...' clause with concrete triggers, satisfying the level-3 anchor; it is not the level-2 case where 'when' is only implied.	3 / 3
Trigger Term Quality	Quotes natural phrasings a user would actually say — "run the weekly social readout", "which denominator does our engagement rate use", "which posts won this week and what changes next cycle" — plus bilingual keywords (社媒周报/互动率分母), giving good coverage of natural terms rather than only jargon or a single generic keyword.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche and actively disambiguates with 'Not for dollar-ROI math or the ECHO profile result gate verdict — use roi-calculator and social-quality-auditor', making conflict with sibling skills unlikely rather than merely 'somewhat specific'.	3 / 3
	Total	12 / 12 Passed

Validation

75%

Warnings & errors only

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

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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: 31 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: social/observe/social-measurement-loop/SKILL.md
Commit: 4a77c48

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.