Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/mcp/x-bug-triage/skills/bug-clustering

bug-clustering

Verified

Normalize supplied X post objects, redact common sensitive strings, score heuristic signals, deduplicate similar text, and persist deterministic bug clusters with the repository's Bun libraries. Use when developing or testing the local clustering stage. Trigger with "cluster these supplied bug posts".

Bug Clustering

Exercise the repository's real normalization and clustering libraries on data the operator supplies. This skill does not fetch X posts, infer truth, or provide a packaged end-to-end runner.

Overview

parseCandidate() performs regex-based extraction, classification, redaction, and scoring. deduplicateCandidates() groups similar text with trigram and token-Jaccard similarity. clusterCandidates() writes cluster and cluster-post rows to SQLite. Read the runtime contract before treating any score as evidence.

Prerequisites

  • Work from this repository with Bun installed and dependencies available.
  • Supply X-shaped post objects; do not pass secrets or unredacted private exports.
  • Select a disposable or explicitly approved SQLite database. Initialize it with bun run db:migrate.
  • Back up any non-disposable database before a clustering run.

Authentication

No external authentication is used. This skill reads supplied local data and may write only to the operator-selected SQLite path through the local Bun libraries.

Instructions

  1. Inspect the input count and schema before execution. Refuse unknown binary or private-source files.
  2. Parse each post with parseCandidate(post, runId, approvedAccounts, sourceType?) from lib/parser.ts.
  3. Verify raw_text_redacted and pii_flags. The redactor covers configured patterns, not every possible sensitive value; stop if the sample still exposes private content.
  4. Pass { post_id, text, public_metrics } objects to deduplicateCandidates(). Its default threshold is 0.70; record any override.
  5. Insert the triage run and only the approved candidates into the selected database.
  6. Call clusterCandidates(db, candidates, runId, threshold?). It clusters only four eligible classification families and skips non-clustering classifications.
  7. Report new, updated, skipped, and suppressed counts. Do not invent audit rows: this function writes clusters and links, but does not itself emit the audit events claimed by older documentation.
  8. Run the relevant Bun tests after changing library behavior.

Output

Return:

  • input, parsed, forwarded, skipped, and suppressed counts;
  • duplicate groups and the threshold used;
  • new and updated cluster identifiers;
  • the exact database path and whether it was disposable;
  • warnings about residual sensitive content, weak classifications, or missing surface/feature data.

Examples

Input: tests/fixtures/x-api/mentions-response.json
Database: /tmp/x-bug-triage-demo.db
Threshold: 0.70
Result: 3 parsed; 3 forwarded; 2 new clusters; 1 skipped; 0 suppressed
Warning: scores are deterministic heuristics, not verified bug truth.
No execution performed: the requested database was data/triage.db and no backup or mutation approval
was provided.

Error Handling

SituationResponse
Input is not X-shaped JSONStop and report the missing fields.
Redaction leaves sensitive textDo not persist that candidate.
Database is not explicitly selectedUse a disposable path or request a path; never assume production data.
Candidate references a missing runInsert the run first or stop on the foreign-key error.
One library call throwsRoll back the caller-managed batch and report the exact stage.

Guardrails

  • Never claim the classifier is an ML model; it is a fixed regex/keyword heuristic.
  • Never treat reporter reliability as identity verification or factual truth.
  • Never store original private text merely because configured patterns did not match it.
  • Never run bun run db:reset without explicit approval; it deletes the configured database.

Resources

finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall