problem-frame-author
Reverse-engineers and drafts problem frames from existing project documentation and code.
Install
mkdir -p .claude/skills/problem-frame-author && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14508" && unzip -o skill.zip -d .claude/skills/problem-frame-author && rm skill.zipInstalls to .claude/skills/problem-frame-author
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Draft a first problem frame for this repository from existing requirements, specs, ADRs, code, or tests. Use when Codex needs to create validator-ready CBF or SWF inputs, reverse-engineer a problem frame from code, or turn requirement/spec truth into structured problem-frame files without yet claiming spec compliance.Key capabilities
- →Draft a problem frame for a repository
- →Create validator-ready CBF or SWF inputs
- →Reverse-engineer a problem frame from code
- →Turn requirement/spec truth into structured problem-frame files
How it works
This skill drafts a problem frame by analyzing existing project artifacts such as requirements, specifications, architectural decision records, code, or tests. It aims to create structured problem-frame files.
Inputs & outputs
When to use problem-frame-author
- →Reverse-engineer requirements from existing code
- →Draft problem frames for new features
- →Generate validator-ready inputs for design validation
About this skill
problem-frame-author
Claude runtime entry for [email protected]. This generated projection does not
prove installation, operation execution, validation or runtime discovery.
Regenerate it from the selected package and verified Claude adapter.
Read the installed skill for its declared operations.
Resolve the installed metadata with the installed skill
directory as the explicit package_root.
Obtain the caller's explicit project_root, configuration selection and operation. The project-owned .ai/custom/framework.json is not supplied by this entry. Pass the chosen configuration path explicitly under the installed skill's contract; do not infer it from the current working directory.
Selected installed skill members:
- references/authoring.md
- references/configuration.md
- references/example.md
- references/format.md
- references/operations.md
- schemas/cbf-record-v1.schema.json
- scripts/problem_frame.py
- templates/cbf.md
For metadata version 4, knowledge_consumption declares exact knowledge package
versions, operations and resource IDs. Follow the installed skill's selected
binding to access knowledge. An optional missing package or resource makes the
named coverage unavailable; do not assume it was installed or promise that
coverage. Required dependencies must be present before the operation is used.
For metadata versions 1–3, follow the declared operation and runtime contracts. An instruction operation means read its declared instructions; a tool operation uses its declared tool. This entry does not supply methods or provider calls.
When not to use it
- →The user does not need a problem frame
- →The user is not working with existing requirements, specs, ADRs, code, or tests
Limitations
- →Requires existing requirements, specs, ADRs, code, or tests as input
- →Does not claim spec compliance for the generated problem frame
How it compares
This skill automates the initial drafting of a problem frame from existing project documentation and code, which is typically a manual and interpretive process.
Compared to similar skills
problem-frame-author side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| problem-frame-author (this skill) | 0 | 5mo | No flags | Intermediate |
| tool-design | 3 | 4mo | Review | Intermediate |
| ai-product | 1 | 8mo | No flags | Advanced |
| project-development | 0 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
tool-design
muratcankoylan
This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.
ai-product
davila7
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.
project-development
mwathiben
Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.
model-delegation
Esposter
Esposter model-delegation conventions — the main session does all thinking (specs, proposals, architecture, review); mechanical implementation is delegated to background subagents with self-contained prompts. Apply when deciding whether to implement in-session or delegate, and when writing a delegat
sequential-thinking
mrgoonie
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
brainstorming
obra
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes