bug-predict
/bug-predict
Predict likely bug locations from code patterns and complexity. Triggers on: predict bugs, find bugs, risky code, code risk, what might break, likely bugs, bug hotspots.
- Author
- smart-ai-memory ↗
- Repository
- attune-ai ↗
- Licence
- Apache-2.0
- Last repository change
- 24.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Predict likely bug locations from code patterns and complexity. Triggers on: predict bugs, find bugs, risky code, code risk, what might break, likely bugs, bug hotspots.
Original author description
Predict likely bug locations from code patterns and complexity. Triggers on: predict bugs, find bugs, risky code, code risk, what might break, likely bugs, bug hotspots.
How it works
- Scoping
- Execution
- Output
- Detected Patterns
SKILL.md preview
--- name: bug-predict description: "Predict likely bug locations from code patterns and complexity. Triggers on: predict bugs, find bugs, risky code, code risk, what might break, likely bugs, bug hotspots." --- # Bug Prediction **IMPORTANT: Start your response with a context preamble.** Call `help_lookup(topic="bug-predict", mode="preamble")` and display the returned `preamble` text as a blockquote. Then tell the user they can say "tell me more" for a step-by-step guide, or answer the scoping questions below to proceed. If the MCP call fails, fall back to: > **Bug Predict** — Predicts where bugs are most likely based on code patterns, complexity, and change frequency. ## Scoping Before running, ask: 1. **Target path**: "Which files or directory should I scan?" Default to `src/` if not specified. 2. **Severity filter**: "Show all findings, or only HIGH severity?" ## Execution Call the `bug_predict` MCP tool with the scoped path: ``` bug_predict(path="<user-specified path>") ``` Or via CLI: ```bash uv run attune workflow run bug-predict --path <target> ``` ### Shared command workspace (preferred) When the generic command-workspace tools are available, open adapter `bug-predict` with the validated target path and `all`/`high` severity filter. The user's command invocation already authorizes this read-only scan: the workspace enters running state immediately and has no confirmation action. Run the existing `bug_predict` tool, publish optional `progress`, then publish one `scan_result` carrying the real success flag, risk score, findings, suggestions, or error. Present the terminal widget or its returned Markdown. A failed run must render **did not complete**, never a false zero-findings receipt. Fall back to the existing rich panel/Markdown behavior below when the shared tools are unavailable. ## Output **Prefer the rich panel.** If the tool response includes `panel_html`, pass it to `mcp__visualize__show_widget` — the universal report panel (title, score, findings/category sections; from `attune.workflows.report_panel`). It shows an explicit "did not complete" state on failure, never a false "clean". Fall back to the markdown below when the widget surface is unavailable. Present results as a markdown table grouped by severity (HIGH first): | File | Line | Pattern | Severity | |------|------|---------|----------| Include clickable file links and note any false positives (see scanner-patterns for known false positives like `subprocess_exec` matching `dangerous_eval`). ## Detected Patterns | Pattern | Severity | Description | |---------|----------|-------------| | `dangerous_eval` | HIGH | Use of eval() or exec() | | `broad_exception` | MEDIUM | Bare except: or except Exception: | | `incomplete_code` | LOW | TODO/FIXME comments |
Versions
The database has no other skills named bug-predict.
Identical content appears in 1 other GitHub folders. We show one copy with the highest score.
Database snapshot: 13.11.2026 · package version aa7c5424bdaf (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100qa-find-bugs-dashboard
Exercise the running Beancount.io dashboard with headless Playwright, use QA_EMAIL and QA_PASSWORD for login, reproduce bugs, trace fixes to source, and deduplicate findings. Use for dashboard QA or a browser bug hunt. Skip ordinary code review, bug implementation, and… - 100ai-bug-fix-triage
Triage JIRA bugs against repository code to classify AI fixability. Use when reviewing a backlog of bugs to determine which ones an AI agent can fix. - 100triage-bugs
Triage and prioritize bug reports when the user asks to classify bugs, prioritize a bug backlog, triage issues, or sort bugs by severity for sprint planning - 100dev-bug
Use for bugs and debugging. Triggers include "bug", "debug", "why is X happening", "not working", "this is broken". Two entries, both covered - a bug is listed, or debugging only (may find no bug). Reproduces first, explains in plain terms, finds the root cause from evidence,… - 100audit
One-shot audit of a whole repo, folder or package for bugs, security and data risks, load problems, untested risky code, slow paths and dead code. Read-only report. Use when asked to audit the codebase or check its health. Not for a branch diff or a single bug. - 100audit-bugs
Analyze historical bug patterns by mining Claude Code project logs for /investigate skill invocations since a specified date. Identifies recurring root causes, architectural gaps, and proactive detection strategies. Use when user says "audit bugs", "bug patterns", "analyze…