meta-stack-trace-investigator
Use this meta-skill instead of answering directly when the user gives a stack trace, traceback, runtime error, or failing log that benefits from multi-skill orchestration across trace parsing, repo/history inspection, patch-target analysis, reproduction guidance, and verification commands.
Profile →npx skills add opensquilla/opensquilla --skill meta-stack-trace-investigator --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
You use a meta-skill to handle stack traces, tracebacks, runtime errors, or failing logs that benefit from coordinated analysis across trace parsing, repository/history inspection, patch-target analysis, reproduction guidance, and verification commands. It guides the agent to extract a compact investigation brief from the original request without asking for confirmation when enough information exists.
How it works
- The skill defines a sequence of steps performed by multiple sub-skills and tools. It starts by collecting investigation facts from the user message, producing a structured JSON with language, expected behavior, recent changes, trace presence, primary exception, and primary files.
- It then parses the trace to extract a JSON object containing exception_class, exception_message, primary_file, primary_line, symbols, and language.
- It attempts repository grepping for parse results, issues, git history, diff context, and memory as separate steps, each with degraded fallbacks if tools fail.
- A language-specific probe is invoked via a language_probe step, routing to Python/JS/Go/Rust probes based on parsed language.
- It synthesizes a bounded root-cause hypothesis from all evidence, then proposes safe verification commands and a minimal reproducer plan.
- The final output is a degraded-summary that strictly presents the final investigation report in a fixed format.
When to use it
Use this meta-skill when the user provides a stack trace, traceback, runtime error, or failing log that benefits from orchestrated analysis across parsing, repo/history inspection, and reproduction/verification guidance.
What it can touch
The skill interacts with shell and filesystem, runs repository searches, accesses git history, and executes a set of sub-skills/tools as part of the investigation pipeline. It routes to language-specific probes and uses multiple tool calls to gather evidence and synthesize a root-cause hypothesis.
Caveats
The workflow defines degraded-evidence fallbacks if certain steps fail (grep_repo, search_issues, git_history, diff_context, history_patterns, memory_recall). It preserves a non-authoritative stance, emphasizing evidence from the trace and target repository, and avoids fabricating prior incidents. The license is Apache-2.0.
# Stack-Trace Investigator (Meta-Skill) A **combinator-style** meta-skill that converts a pasted stack trace into a structured root-cause report. It now classifies Python, JavaScript, TypeScript, Go, Rust, or unknown traces before running the investigation. After parsing the trace once, heterogeneous investigations run in parallel: 1. **`grep_repo`** — ripgrep for the symbols in the current repo 2. **`search_issues`** — `gh issue list` for similar reported problems 3. **`git_history`** — recent commits touching the affected files 4. **`diff_context`** — `git-diff` skill for current worktree context 5. **`history_patterns`** — `history-explorer` skill for prior skill/router usage patterns 6. **`memory_recall`** — prior incidents stored under the `traceback` topic 7. **`language_probe`** — routed to the language-specific helper skill (`stack-trace-python-probe`, `stack-trace-js-probe`, `stack-trace-go-probe`, `stack-trace-rust-probe`, or generic fallback) The `root_cause` and `repro_suggestion` steps fan the signals into a hypothesis, concrete fix targets, and verification commands. The final summary labels degraded evidence sources explicitly before persisting the incident. ## Trigg
- Trigger surface
- Fallback
What does the meta-stack-trace-investigator skill do?
Use this meta-skill instead of answering directly when the user gives a stack trace, traceback, runtime error, or failing log that benefits from multi-skill orchestration across trace parsing, repo/history inspection, patch-target analysis, reproduction guidance, and verification commands.
How do I install it?
Run `npx skills add opensquilla/opensquilla --skill meta-stack-trace-investigator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From opensquilla/opensquilla, a repository with 6,515 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.