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

86%

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

73%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.

A well-structured, action-oriented instruction skill with clear sequencing and validation checkpoints, scored down only for notable cross-section repetition that inflates token cost. Strengthening progressive disclosure would mean consolidating the repeated sibling-skill routing into the reference list.

Suggestions

Consolidate the repeated organic/boosted and ECHO-O1 denominator points into one stated location and reference it, rather than restating them in the scope guard, instructions, and Next Best Skill sections.

Move the three repeated social-quality-auditor routing notes into a single 'Boundaries / out-of-scope routing' entry and keep Next Best Skill to genuinely distinct next steps.

Add one concrete example of the median rollup with an organic/boosted split (a small table or sample calculation) so the per-post step is copy-paste ready rather than conceptual.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (it never explains what a median or CHAOSS is), but the organic/boosted split, ECHO-O1 denominator point, and social-quality-auditor routing are each restated across the scope guard, instructions, Next Best Skill, and Reference Materials sections — repetition that could be tightened.	3 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill: named connectors (discourse.py, bluesky.py), named formulas (ERR = engagements ÷ reach), named memory paths, and the `operation: propose` request to registry-events.py; minor gaps remain around the actual median/rollup mechanics.	4 / 5
Workflow Clarity	Eight numbered steps are clearly sequenced with an explicit 'Done when' checklist as validation, plus feedback loops (missing receipt → `binding_status: incomplete` and provisional hypothesis, not a terminal decision; denominator switch declared as a trend restart), satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	No bundle files ship (references/, scripts/, assets/ absent), but the body is well-sectioned and points one level deep to clearly signaled materials (echo-benchmark.md, skill-contract.md, CONNECTORS.md, SECURITY.md, human-action-control.md); minor gap is that several sibling-skill routings are inlined rather than consolidated in Reference Materials.	4 / 5
	Total	16 / 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 specific, trigger-rich, complete, and well-bounded, hitting the top anchor on all four dimensions; it uses third-person voice and concrete denominator distinctions (ERR vs ERI vs ER-by-follower) rather than fluff. Its only soft spot is dense jargon and the appended Chinese keyword string, but neither reduces scored quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — produces the metric dictionary (every rate names its denominator), median-not-mean per-post rollups, EMV exec-translation, attributed CHAOSS/Orbit community-health readout, and the best/worst write-back — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both what (the five deliverables it produces) and when (a clear 'Use when...' clause with concrete trigger phrases), and adds an explicit 'Not for' boundary, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural verbatim phrases 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 synonyms, giving comprehensive trigger coverage.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (organic-social measurement loop) and explicitly redirects overlapping work — 'Not for dollar-ROI math or the ECHO profile result gate verdict — use roi-calculator and social-quality-auditor' — minimizing wrong-skill conflict risk.	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: 64562bc

Reviewed: 3 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.