workflow-from-chats
Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly articulates both what the skill does and when to use it. It uses third person voice, provides specific concrete actions, includes natural trigger terms, and occupies a distinct niche. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Extract durable working preferences from recent Cursor chats' and 'convert them into skills, rules, or workflow docs.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Extract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs') and when ('Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'learn preferences', 'mine feedback', 'personalize workflows', 'generate team/person-specific agent guidance', 'Cursor chats'. These cover a good range of terms a user would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: extracting preferences specifically from Cursor chats and converting to skills/rules/workflow docs. The combination of 'Cursor chats', 'working preferences', and 'agent guidance' creates a clear, unique identity unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that clearly defines a multi-step workflow for extracting preferences from chat transcripts. Its strengths are token efficiency, clear sequencing, and well-defined decision frameworks (confidence levels, artifact choice). The main weakness is the lack of concrete examples—a sample preference atom, a sample output synthesis, or a sample artifact draft would significantly improve actionability.
Suggestions
Add a concrete example of a 'preference atom' showing what trigger, workflow step, decision rule, quality bar, stop condition, evidence, and confidence look like when filled in.
Include a brief example of the expected output synthesis format, showing what the evidence corpus, preference profile, and proposed artifacts sections look like with sample data.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose—scope, workflow steps, confidence taxonomy, artifact choice, and output format. There's no explanation of concepts Claude already knows, no filler, and no unnecessary context. | 3 / 3 |
Actionability | The workflow steps are clearly enumerated and specific (e.g., scan for markers like 'I prefer', 'always', 'never'), and the confidence/artifact frameworks are concrete decision aids. However, there are no concrete examples of what a preference atom looks like, what a final output artifact looks like, or example input/output, which would make this more copy-paste actionable. | 2 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with logical progression from scoping to inventory to scanning to extraction to clustering to artifact choice to drafting. The confidence rating system acts as a validation checkpoint, and the 'contradicted' level explicitly includes a stop condition (ask the user before writing files). | 3 / 3 |
Progressive Disclosure | The content is well-organized into clear sections (Scope, Workflow, Confidence, Artifact Choice, Output), but everything is in a single file with no references to supporting materials. An example template for output artifacts or a reference file with sample preference atoms would improve discoverability without bloating the main skill. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cursor/plugins
- Commit
7dd9fea
- Reviewed
Table of Contents
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.