jeremylongshore/tons-of-skills-marketplace / plugins/mcp/x-bug-triage/skills/repo-scanning
repo-scanning
VerifiedExercise the triage server's synthetic repository-evidence contracts and label every result as unverified prototype output. Use when testing evidence schemas, tier assignment, or downstream display behavior without GitHub. Trigger with "simulate a repo scan for this cluster".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.5 KB |
| references/runtime-contract.md | markdown | 1.1 KB |
references/runtime-contract.md
View on GitHub# Repository scanning runtime contract
## Current handlers
- search_issues generates one issue_match object for each of at most five supplied terms. Confidence is
0.6, so assignEvidenceTier() returns Tier 3.
- inspect_recent_commits returns one recent_commit object with confidence 0.5 and Tier 3.
- inspect_code_paths returns one affected_path object with confidence 0.5 and Tier 3.
- check_recent_deploys returns one recent_deploy object with confidence 0.4 and Tier 3.
The descriptive strings say search, scanned, inspected, or checked, but the handlers only interpolate
inputs into those strings. They perform no fetch, GitHub CLI call, filesystem traversal, or API request.
## Evidence policy boundary
assignEvidenceTier() is real deterministic logic over an evidence type and confidence number. It grades
the shape of supplied/generated records; it does not verify their factual basis.
## Future integration
Live GitHub evidence requires new authenticated handlers plus tests that prove returned URLs, SHAs,
paths, and release identifiers came from the requested repository.
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 |