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

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

67%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, contract-style skill with concrete paths, formulas, labels, and a sequenced workflow backed by validation checkpoints. Its main weakness is deliberate redundancy — out-of-scope routing and the O-sub-item inventory each appear multiple times — that could be consolidated.

Suggestions

Consolidate the out-of-scope routing so it lives in one place (the scope guard) and is merely referenced from step 7 and Next Best Skill, removing the repeated full lists.

Move the full metric-dictionary definitions (ERR/ERI/ER-by-follower formulas and the lock rules) into a referenced file and keep the body's overview shorter, improving both conciseness and progressive disclosure.

Add one explicit validate→fix→retry loop for the denominator-lock step (lock must match prior period or be declared as a trend restart) to push workflow clarity toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but the out-of-scope routing is stated three times (scope guard, step 7, Next Best Skill) and the O-sub-item inventory is repeated in the intro and Skill Contract, so it could be tightened.	3 / 5
Actionability	Gives concrete guidance — exact memory paths, named connector scripts (discourse.py, bluesky.py), explicit rate formulas (ERR = engagements ÷ reach), and a Measured/User-provided/Estimated labeling scheme — with only minor gaps (no copy-paste command blocks beyond registry-events.py references).	4 / 5
Workflow Clarity	Eight clearly sequenced steps are backed by a 'Done when' validation checklist, a denominator lock-match check, and NEEDS_INPUT handling; validation is present for this batch operation, with only minor checkpoint gaps keeping it below a 5.	4 / 5
Progressive Disclosure	Well-organized sections with a dedicated Reference Materials list pointing one level deep to echo-benchmark.md, skill-contract.md, CONNECTORS.md, SECURITY.md, and sibling SKILL.md files; kept below 5 because a fair amount of detail (full contract, all rate definitions, routing rules) is inlined rather than split out.	4 / 5
	Total	15 / 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 exemplary: it pairs concrete natural-language triggers with a precise inventory of outputs and explicit scope exclusions, hitting the top anchor on every dimension. Its only weakness is length — the same inventory could be trimmed without losing the trigger and boundary clarity.

Suggestions

Tighten the mid-section inventory (ERR/ERI/ER-by-follower, CHAOSS/Orbit attribution detail) into a shorter list; the description currently runs long and the rubric does not reward verbosity.

Consider dropping the trailing Chinese keyword string '社媒周报/互动率分母/指标字典/复盘回写' or folding it into the trigger clause, since it duplicates triggers already present in English.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — building the metric dictionary with named denominators (ERR/ERI/ER-by-follower), median-not-mean rollups with an organic/boosted split, EMV exec-translation, an attributed CHAOSS/Orbit community-health readout, and the best/worst-performer write-back — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (the dictionary, rollups, EMV, readout, write-back it produces) and 'when' (a leading 'Use when the user asks to...' clause with concrete trigger phrases), and adds explicit 'Not for...' boundary guidance.	5 / 5
Trigger Term Quality	Embeds the exact natural phrases a user would say ('run the weekly social readout', 'which denominator does our engagement rate use', 'which posts won this week and what changes next cycle') plus Chinese synonyms, covering the full range of triggering utterances.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the organic-social measurement loop) with distinct triggers and explicit hand-offs to roi-calculator and social-quality-auditor, minimizing conflict with sibling skills.	5 / 5
	Total	20 / 20 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: 9df28a0

Reviewed: 4 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.