jeremylongshore/tons-of-skills-marketplace / plugins/mcp/x-bug-triage/skills/bug-clustering
bug-clustering
VerifiedNormalize 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".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.9 KB |
| references/runtime-contract.md | markdown | 1.4 KB |
references/runtime-contract.md
View on GitHub# Bug clustering runtime contract
## Implemented stages
- `parseCandidate()` extracts symptoms, error strings, reproduction hints, URLs, surface, and feature
with regular expressions. It selects one of 12 classifications through fixed phrase rules.
- `redactPii()` replaces matching email, token-like, phone, account-ID, and URL-token strings. Media is
represented by keys and a boolean; there is no separate media-redaction detector.
- `scoreReporter()` uses fixed arithmetic over text length, extracted details, engagement, and reply
shape. Historical accuracy is currently always `0.5`.
- `deduplicateCandidates()` performs pairwise text comparison and returns canonical IDs; it does not
modify candidate rows.
- `clusterCandidates()` reads active suppression rules, groups only eligible families, and writes
cluster plus cluster-post rows. New severity is always `low`.
## Not implemented as one command
There is no checked-in CLI that runs parse, deduplicate, candidate persistence, cluster persistence,
and audit logging as one transaction. The caller owns orchestration and rollback. `clusterCandidates()`
does not insert candidates or audit events and does not persist deduplication groups.
## Data boundaries
The SQLite schema stores redacted text, but pattern matching is not a complete data-loss-prevention
control. Treat source selection and operator review as separate security boundaries.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |