agentleFS
Sign inStart free
dmzoneilldmzoneill/skills/gather-context/SKILL.md

gather-context

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Gather relevant context for a task using code search, knowledge base, and known issues. Use at the start of skills that need context about a Jira issue, feature, bug, or code review.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Create a free account to mount
Files
SKILL.md

Gather Context

Consolidates: code_search, knowledge_query, and check_known_issues into structured context.

Inputs

InputTypeDefaultPurpose
querystringrequiredWhat to search (issue description, feature name, error message)
projectstring"automation-analytics-backend"Project for knowledge lookup
tool_namestring-Tool to check for known issues
code_limitint5Max code search results
include_architecturebooltrueInclude architecture overview
include_gotchasbooltrueInclude project gotchas
include_patternsbooltrueInclude coding patterns

Workflow

1. Code Search

  • code_search(query=query, project=project, limit=code_limit)
  • Parse into structured results (file paths, relevance)

2. Load Gotchas (if include_gotchas)

  • knowledge_query(project=project, section="gotchas")
  • Parse list items into actionable gotchas

3. Load Patterns (if include_patterns)

  • knowledge_query(project=project, section="patterns.coding")
  • Parse into coding patterns list

4. Load Architecture (if include_architecture)

  • knowledge_query(project=project, section="architecture.overview")

5. Check Known Issues

  • check_known_issues(tool_name=tool_name, error_text=query[:100])
  • Parse into known issues list

6. Build Combined Context

Output object with:

  • code: found, count, results
  • gotchas: found, count, items
  • patterns: found, count, items
  • architecture: found, overview
  • known_issues: found, count, items
  • summary: has_code, has_gotchas, has_patterns, total_items

7. Log

  • memory_session_log("Gathered context for: {query[:50]}", "Code: X, Gotchas: Y, Patterns: Z")

Key MCP Tools

  • code_search — semantic code search
  • knowledge_query — gotchas, patterns, architecture
  • check_known_issues — known fixes for tools/errors
  • memory_session_log — session logging

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free