crisis-response-planner

Use when the user asks to "build our social crisis protocol", "mentions are exploding — what do we do first", or "when do we pause the posting queue"; produces a 1-5 severity ladder with tunable Estimated trigger thresholds (mention-velocity multiples vs the 7-day listening baseline, sentiment flip, journalist/regulator contact, employee-conduct class), the first-mechanical-action rule — pause ALL scheduled posts AND paid amplification, with dated state markers dropped to the channels proposal protocol and reconciled post-incident — a pre-approved holding-statement library with committed update cadences, when-NOT-to-post rules, a spokesperson/approval matrix, and a post-crisis retro template; re-runs the social-quality-auditor pre-publish gate before un-pausing the queue. Not for email deliverability incidents (blocklist, spam-rate spikes) — use deliverability-qa; inside a launch window launch-day-conductor owns incident handling. 社媒危机预案/暂停队列/声明库/发言人矩阵

Quality

90%

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

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 tightly written operational runbook with concrete paths, quantified thresholds, and a well-validated stand-down workflow. Its main weakness is dense prose in the intro/Scope-guard that could be bulletized for token efficiency.

Suggestions

Convert the intro paragraph and Scope-guard paragraph into bullet lists so the routing/ownership facts scan without parsing a paragraph.

Pull the inline skill cross-references out of prose and consolidate them into the Reference Materials / Next Best Skill sections to reduce duplicated link noise.

Keep the Step 2 default-threshold table as a compact literal block (level : multiple : trigger) so it is scannable rather than embedded in narrative.

Dimension	Reasoning	Score
Conciseness	Information-dense and assumes Claude's competence (no 'what is a crisis' padding), but the intro and Scope-guard paragraphs are long prose that could be tightened into bullets without losing meaning.	4 / 5
Actionability	Concrete paths (memory/social/crisis-response-planner/, memory/events/channels.ndjson), specific operations (operation: propose to registry-events.py), and quantified thresholds (3x/5x/10x baseline) are executable; a few steps remain at directive level ('Build the holding-statement library') with sub-detail embedded rather than separable.	4 / 5
Workflow Clarity	Eight clearly sequenced steps with explicit validation checkpoints — all-clear criteria ('velocity holds under 1.5x baseline for 24h'), gate re-run before un-pause, pause-marker reconciliation, and a 'Done when' checklist — plus the batch pause operation carries its own verification loop.	5 / 5
Progressive Disclosure	Well-organized sections (Quick Start, Skill Contract, Data Sources, Instructions, Reference Materials, Next Best Skill) with a dedicated one-level-deep reference list; minor gap is that several references are also threaded inline in prose, slightly diluting the navigation signal.	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, trigger-rich, and concretely enumerates the skill's outputs while explicitly routing away overlapping cases. It is dense but every clause earns its place; minor risk is verbosity rather than vagueness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces a 1-5 severity ladder with tunable...trigger thresholds', 'pause ALL scheduled posts AND paid amplification', 'pre-approved holding-statement library with committed update cadences', 'spokesperson/approval matrix', 'post-crisis retro template', 're-runs the social-quality-auditor pre-publish gate' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (severity ladder, pause rule, statement library, matrix, retro template) and 'when' (leading 'Use when the user asks to...' clause) with concrete trigger phrases, plus negative-scope routing.	5 / 5
Trigger Term Quality	Three quoted natural user utterances ('build our social crisis protocol', 'mentions are exploding — what do we do first', 'when do we pause the posting queue') plus domain terms like 'social crisis protocol' and 'pause the posting queue' give comprehensive natural-language trigger coverage.	5 / 5
Distinctiveness Conflict Risk	Clear niche with distinct triggers and explicit conflict avoidance — 'Not for email deliverability incidents...use deliverability-qa' and 'inside a launch window launch-day-conductor owns incident handling' — minimizing misfire 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: 32 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: social/host/crisis-response-planner/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.