skilld
All skills
google avatar

/mantis-pipeline-adapter

@27467b3
by googlegoogle/mantis1.7k stars
170

Interactively guides the design and implementation of custom deterministic orchestrator harnesses. Use when a user wants to build their own pipeline to wrap and run Mantis skills reliably. Don't use for executing the default pipeline directly.

Requires /mantis-plan /mantis-researcher /mantis-architecture /mantis-dedupe /mantis-reproduce /mantis-critic

Ask your Agent

Use this Skill: https://skilld.dev/gh/google/mantis/mantis-pipeline-adapter

This session only. Nothing lands on disk.

referencesmantis-structural-index.md

≈385 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Reference Blueprint: mantis-structural-index Skill

This is a reference pointer that documents the real mantis-structural-index skill. For the complete specification — including System Goal, Command Definition, Input/Output Contract, Instructions, data structures (manifest schema, SQLite schema, cache key computation, canonical symbol IDs), query interface, and safety invariants — see the single source of truth:

→ ../../mantis-structural-index/SKILL.md

Builders should read that file directly. This blueprint does not duplicate the spec. If implementation details are needed that are not in the SKILL.md, they should be added to the SKILL.md first, then referenced here.

Key Architecture (summary)

The structural index is a content-addressed semantic-unit index with:

  • Manifest-based atomic publishing (manifest.json) — written LAST as the atomic commit point
  • SQLite serving store (catalog.sqlite) with bidirectional indexes
  • Capability-based per-partition backend selection (6 tiers)
  • Canonical symbol IDs (scoped, overload-aware, corpus-qualified)
  • Bounded query interface with pagination and coverage metadata
  • Baseline plus delta overlay architecture (CI baseline + local overlay)
  • Deterministic partial coverage (priority queue, no discovery-order truncation)

See the SKILL.md for full details.

Safety guardrails are defined in the canonical ../../mantis-structural-index/SKILL.md under ## Safety.

Source: SKILL.md on GitHub

Third-party checks

1 warning17d3 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill provides a comprehensive framework for designing deterministic security audit pipelines. It includes several security considerations, primarily the runtime generation and execution of scripts and the ingestion of untrusted external data. While these patterns are integral to the skill's function as a security tool architect, they warrant review to ensure proper isolation and sanitization.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at 27467b3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated last month

README badge

README badge for google/mantis/mantis-pipeline-adapter