- Home
- Skills
- Shinpr
- Claude Code Workflows
- Task Analyzer
task-analyzer_skill
102
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill shinpr/claude-code-workflows --skill task-analyzer- SKILL.md4.4 KB
Overview
This skill performs metacognitive task analysis and recommends the right skills with confidence scores and metadata. I analyze task essence, estimate scale, identify type, and return a prioritized set of skills and reasons to guide execution. The output is structured for direct consumption by agent workflows or human planners.
How this skill works
I parse the task description to extract tags and the fundamental purpose behind the request. I estimate task scale by likely file count and impact, classify the task type, and match tags to a skills index to select and prioritize relevant skills. The result includes taskAnalysis metadata, selectedSkills with priorities and reasons, and a small set of metacognitive questions and warnings when risks are detected.
When to use it
- Deciding which specialized agents or skills to assign for a given development task
- Estimating task complexity and likely scope before planning work or creating tickets
- Selecting testing, documentation, and process skills for larger changes
- Identifying hidden dependencies or quality risks before implementation
- Generating focused review checklists and phased work plans
Best practices
- Start by stating the desired outcome, not just the surface action
- Provide indicators of scope (affected files, modules, teams) to improve scale estimates
- Use tag-rich task descriptions to improve skill matching accuracy
- Prioritize tests and QA for anything beyond trivial changes
- Split large changes into phased deliveries to reduce risk
Example use cases
- Analyze a ticket: convert 'Fix login bug' into a structured plan with skills for debugging, testing, and security.
- Estimate effort: classify a merge request as small/medium/large and surface process skills for large changes.
- Skill routing: choose which agent skills (coding, testing, documentation) to invoke for a feature request.
- Risk detection: flag implementation without tests and recommend TDD and review steps.
- Refactor planning: identify refactoring goals, required skills, and a phased migration approach.
FAQ
I return structured YAML/JSON-style analysis: essence, type, scale, tags, estimatedFiles, plus selectedSkills with priority, reason, and skill metadata.
How do you estimate scale?
Scale is inferred from described scope and indicators (file count, cross-cutting impact). Defaults: small 1–2 files, medium 3–5, large 6+.