savage-research

Plugin savage-research from marketplace savage-researcher in AliBassam/savage-researcher. Commands read from the repo's manifest — 1 month ago.

Skills (4)

• claim-extraction

  The structured-claim-list format produced by the claim-extractor agent. Defines the exact schema every downstream specialist consumes. Read before extracting claims from a repo.

• research-orchestrator

  The 8-stage pipeline driver for the savage-research plugin. Takes a local repo path, runs ingest → claim extraction → parallel specialists → synthesis → adversary → revision → self-audit → emit, and produces the final markdown report. Invoked by the /research slash command.

• research-rubric

  The canonical source-tier system (T1-T5) and the 7 hard tone invariants every agent in the savage-research pipeline must follow. Read this before producing any output in a research run.

• savage-synthesis

  Merge rules for the synthesizer agent that combines five specialist scratchpads into a draft report without softening findings. Read before synthesizing or revising drafts.

Slash commands (1)

• /savage-research:research

  Run the savage-research framework on a local repo. Usage: /research <local-path>. Produces a no-bullshit, self-critiquing markdown report at <repo>/.research/.

Subagents (9)

• adversary

  Stage 5. Reads the synthesizer's draft with one goal — find every remaining piece of bullshit. Produces a kill-list of hedges, unsupported adjectives, T3-resting conclusions, omitted counter-evidence, shined findings. Never rewrites; only critiques.

• claim-auditor

  Stage 3 specialist. Takes every claim from claims.md and verifies it against independent web evidence. Tags each claim Supported / Partially Supported / Contradicted / Unverifiable with source tier and confidence.

• claim-extractor

  Stage 2 agent. Reads the repo ingest summary and produces a structured, neutral, fully-sourced list of every claim the repo makes — problem, target user, proposed solution, quantitative claims, qualitative claims, differentiation claims, hedges.

• failure-mode-hunter

  Stage 3 specialist. Enumerates how the idea breaks in practice — known failure patterns in the space, adversarial use cases, things the pitch omits, reasons comparable efforts died.

• prior-art-hunter

  Stage 3 specialist. Hunts for existing solutions to the problem the repo claims to solve. Identifies incumbents, cheaper/free alternatives, and historical attempts. Writes findings with source tiers and confidence tags.

• question-critic

  Stage 3 specialist. Interrogates the repo's own framing — is the problem real, well-defined, a real user segment, a fantasy, or a straw man? Produces a framing critique separate from claim audits.

• self-auditor

  Stage 7. Enforces hard invariants on the post-revision draft. Returns pass or fail with a list of remaining violations. Does not rewrite.

• synthesizer

  Stages 4 and 6. Merges five specialist scratchpads into a draft report (Stage 4), and revises the draft against the adversary's kill-list (Stage 6). Does not call the web. Does not soften findings.

• traction-checker

  Stage 3 specialist. Assesses adoption and market reality via web signals — is anyone using it, is the space dead/saturated/growing, what happened to comparable efforts. Does not use GitHub API (web only).

Similar plugins