scr
Skill0 starsChanged 25 days agoMITView on GitHub
Draft or review messages using Situation–Complication–Resolution (SCR). Use for SCR requests or concise recommendations that need context, a problem, and a proposed action.
In this repository22 other files it gives its agents.
- ai-writing-tellsSkill
- animated-explainerSkill
- ann-handleySkill
- buyer-personasSkill
- desktop-mockupSkill
- linkedin-guest-kitSkill
- mobile-mockupSkill
- pesty-asana-tasksSkill
- pesty-designSkill
- pesty-explainerSkill
- pesty-frontendSkill
- presentation-structureSkill
- problem-solving-processSkill
- pyramid-principleSkill
- storybrandSkill
- storytellingSkill
- transcript-cleanupSkill
- ui-designSkill
- untangleSkill
- website-launch-impact-reportSkill
- youtube-thumbnailsSkill
- yt-structureSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use supplied context to identify the audience, purpose, relevant facts, obstacle, intended action, medium, and requested length.
- Distinctive: line 22
Use the sequence to connect the reasoning, not merely to sort sentences into three labels.
- Distinctive: line 24
Default to one or two sentences per component when no length is specified.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SCR
Turn context and a recommendation into a coherent message: Situation → Complication → Resolution. Support client and internal emails, Slack messages, spoken talking points, pitches, and presentation introductions. Keep the work at the requested message scope; a presentation introduction does not require a full deck or the Pyramid Principle.
Establish the message
Use supplied context to identify the audience, purpose, relevant facts, obstacle, intended action, medium, and requested length. Ask a focused question only when missing information would materially change the message; do not require a fixed intake questionnaire.
Preserve the user's intended recommendation. If none is supplied, propose a qualified action when the evidence supports one, making its proposed status clear. Otherwise clarify the desired action. If the proposed action does not address the stated complication, identify that gap rather than disguising it with persuasive wording.
Build the SCR sequence
- Situation: Establish the background this audience needs to understand the issue. Keep it brief and familiar where appropriate; do not assume agreement or use “as you know” without support. Put the new development in the complication.
- Complication: Introduce the change, obstacle, risk, or pressing issue that interferes with the goal, and explain why it matters. Do not manufacture a crisis to make the message persuasive.
- Resolution: State a concrete proposed plan or recommended action that addresses that complication. Make clear what the recipient is being asked to do or consider when the message calls for a decision. An investigation or bounded trial can be an appropriate action when the cause or solution is uncertain.
Use the sequence to connect the reasoning, not merely to sort sentences into three labels. Match certainty to evidence; distinguish observed outcomes from explanations and hypotheses. Do not invent supporting data, urgency, consensus, commitments, owners, or deadlines.
Default to one or two sentences per component when no length is specified. Adapt to the requested medium and length rather than enforcing a fixed sentence count. For spoken output, use conversational phrasing or talking points that are easy to say aloud.
Draft and review outputs
Drafting: Return one ready-to-use message, followed by a short breakdown labeled Situation, Complication, and Resolution. Identify each part in a phrase or brief sentence rather than repeating the whole message. Keep framework labels out of the finished message unless requested. Follow explicit requests for message-only, labeled output, or another format.
Reviewing: Check whether the context is necessary, the problem and its consequence are clear, and the action addresses the problem. Identify consequential omissions, excessive background, unsupported claims, and vague or disconnected recommendations. Return a short assessment, an improved message, and the SCR breakdown. For critique-only requests, return the assessment without a rewrite. Preserve the author's meaning and distinguish a suggested change in substance from a wording improvement.
Finish when the message fits the audience and medium, the three components connect logically, and its claims and proposed action stay within the available evidence. If a material gap prevents a sound message, expose that gap instead of presenting the draft as ready to use.
Source
Read Alexander Lyon's SCR source notes when the user asks about the source teaching, needs its original examples, or a framework distinction needs clarification. Routine drafting and review do not require loading it. The notes summarize the source teaching; the workflow and output defaults above are this skill's adaptations.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

