Best use case
observe-before-editing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Observe Before Editing
Teams using observe-before-editing should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/observe-before-editing/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How observe-before-editing Compares
| Feature / Agent | observe-before-editing | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Observe Before Editing
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Observe Before Editing Before editing code to fix a bug, confirm what the system *actually produced*. ## Pattern Outputs don't lie. Code might. Check outputs first. ## DO 1. Check if expected directories exist: `ls -la .claude/cache/` 2. Check if expected files were created: `ls -la .claude/cache/learnings/` 3. Check logs for errors: `tail .claude/cache/*.log` 4. Run the failing command manually to see actual error 5. Only then edit code ## DON'T - Assume "hook didn't run" without checking outputs - Edit code based on what you *think* should happen - Confuse global vs project paths (check both: `.claude/` and `~/.claude/`) ## Source Sessions - a541f08a: Token limit error was invisible until manual run revealed it - 6a9f2d7a: Looked in wrong cache path (`~/.claude/` vs `.claude/`), assumed hook failure - a8bd5cea: Confirmed hook worked by finding output files in project cache - 1c21e6c8: Verified Artifact Index indexing by checking DB file exists
Related Skills
workflow-router
Goal-based workflow orchestration - routes tasks to specialist agents based on user goals
wiring
Wiring Verification
websocket-patterns
Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.
visual-verdict
Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS/REVISE/FAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.
verification-loop
Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.
vector-db-patterns
Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.
variant-analysis
Find similar vulnerabilities across a codebase after discovering one instance. Uses pattern matching, AST search, Semgrep/CodeQL queries, and manual tracing to propagate findings. Adapted from Trail of Bits. Use after finding a bug to check if the same pattern exists elsewhere.
validate-agent
Validation agent that validates plan tech choices against current best practices
tracing-patterns
OpenTelemetry setup, span context propagation, sampling strategies, Jaeger queries
tour
Friendly onboarding tour of Claude Code capabilities for users asking what it can do.
tldr-stats
Show full session token usage, costs, TLDR savings, and hook activity
tldr-router
Map code questions to the optimal tldr command by detecting intent and routing to the right analysis layer.