.cursor/skills/task-analysis/SKILL.md
Analyse task description, performs gap analysis, expand the context for the task, analyse the current state of the system in the context of the task, helps build PRD, creates a context for the task, gathers information about the task from different sources.
npx skillsauth add imvanzen/strava-kudosik task-analysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill helps you gather and expand context about a specific task to be developed, looks for gaps in the task description and helps to understand the current state of the system.
Use the checklist below and track your progress:
Analysis progress:
- [ ] Step 0: Determine input source
- [ ] Step 1: Look for available external sources of information
- [ ] Step 2: Gather information from all sources
- [ ] Step 3: Identify gaps and ask clarification questions
- [ ] Step 4: Based on the answers and gathered information finalize the research report
Step 0: Determine input source
Before gathering information, determine how the task context was provided:
*.research.md, *.plan.md): Read them as the primary source of requirements, acceptance criteria, scope, and definition of done.This determination affects how much of Steps 1–2 you need to execute — if the context is already fully provided inline or in files, skip redundant external lookups.
Step 1: Look for available external sources of information
Check what tools are available. Look for common task and knowledge management tools like:
Check if GitHub tools is available and look for Spaces matching task and project.
Step 2: Gather information
For each available tool look for task related information on it. Make sure to look for by ID if provided and in case it being absent look by task domain and jobs to be done. When having access to task management tools make sure to focus not only on a current task but also connected tasks, subtasks and epic.
In case of any external links, knowledge base link or designs, make sure to thoroughly check them through.
Analyse the code base based on task requirements. Look for areas that will be related to given task.
Find relevant information on knowledge base tools.
Step 3: Identify gaps and ask clarification questions
Based on the gathered information and task description, look for ambiguities or missing information. Create the questions and ask them to the user. Don't proceed until all questions are answered or you are directly told to continue.
Step 4: Based on the answers and gathered information finalize the research report
Generate a report following the ./research.example.md structure. Make sure to provide all necessary information that you gathered, all findings and all answered questions.
Don't add or remove any sections from the template. Follow the structure and naming conventions strictly to ensure clarity and consistency.
codebase-analysis - for analyzing the existing codebase in the context of task requirementsimplementation-gap-analysis - for understanding what already exists vs what needs to be builtdevelopment
Discover and establish technical context before implementing any feature. Prioritize project instructions, existing codebase patterns, and external documentation in that order. Use for any task requiring understanding of project conventions, coding standards, architecture patterns, and established practices before writing code.
testing
Resolves dependency audit (security) issues and updates outdated packages with prioritization by breaking-change risk and security/value. Prefer security fixes and non-breaking updates; defer or flag major upgrades. Use when the user asks to fix audit, update packages, resolve vulnerabilities, or run maintenance.
testing
Implementation gap analysis. Verify what has to be implemented. Verify what was implemented. Compare plan to current state.
development
E2E testing patterns, verification procedures, and CI readiness checklists using Playwright. Use for writing, debugging, or reviewing end-to-end tests, fixing flaky tests, creating Page Objects, mocking external APIs.