research

Plugin research from marketplace mtrense-skills in mtrense/skills. Commands read from the repo's manifest — today.

Skills (21)

• research-add-chapter

  Add new chapter stubs to an existing directory in the topic tree. Works at any depth — a top-level topic directory or a nested sub-directory. Argument: parent directory path (relative to research/content/).

• research-add-topic

  Add a new topic (directory + chapter stubs) to an existing research project. Use when the project already exists and you want to introduce a new top-level topic area. Arguments: topic name (required), optional summary to seed scoping.

• research-audit-coherence

  Audit research topics for narrative flow and coherence. Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.

• research-audit-consistency

  Audit research topics for cross-topic contradictions and inconsistent terminology. Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.

• research-audit-coverage

  Audit research topics for gaps relative to the research plan. Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.

• research-audit-cycle

  Drive `draft` topics through every audit lens to `audited` status by invoking research-audit-topic — a context:fork skill that audits one topic across all lenses — in parallel batches. One fork per topic; forks run concurrently across distinct topics, and each topic's lenses run serially inside its

• research-audit-graphics

  Audit research topics for opportunities to add graphical representations (diagrams, graphs, schematics, tables, screenshots). Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.

• research-audit-quality

  Audit research topics for depth and sourcing adequacy. Produces AUDIT directive comments for the refine phase. Arguments: optional topic path.

• research-audit-topic

  Audit a single research topic across every lens — consistency, coverage, quality, coherence, and graphics — in one pass, inserting AUDIT directives and advancing the topic to `audited`. Runs as a forked subagent that inlines all lens analysis and CONFIDENCE verification (no nested subagents). Argume

• research-generate-graphics

  Generate graphics (SVG diagrams, charts, tables, schematics) from AUDIT comments with type: graphics. Creates assets in the topic's _assets folder. Arguments: optional topic path or specific file:line.

• research-glossary-sync

  Reconcile glossary.md against current topic content — add new terms, update changed definitions, remove unused terms. Run after any content-changing phase. Fans out per-topic candidate extraction to `term-extractor` subagents in parallel.

• research-inception

  Initialize a research project structure with CLAUDE.md, INDEX.md, DECISIONS.md, glossary.md, and topic stubs. Use when starting a new research effort from scratch.

• research-ingest-source

  Ingest a specific external source (URL or local file) an author already has — vet it for legitimacy the same way investigation does, then weave it into every existing section it substantiates or contradicts across the topic tree. Arguments: source URL or path, optional topic hint.

• research-inquiry-cycle

  Drive all stub topics in the research project to `inquiry` status by spawning research-inquiry-worker subagents in parallel batches — one worker per stub topic, since inquiry never collides at the topic-file level.

• research-inquiry

  Create a detailed section outline with RESEARCH directives for a topic file. Use after inception to structure a stub topic before investigation. Argument: topic file path relative to research/content/.

• research-investigation-cycle

  Drive pending RESEARCH directives across the research project to completion by invoking the research-investigation skill — which forks into a research-investigation-worker subagent — in parallel batches where topic files don't collide, sequentially within a topic.

• research-investigation

  Research and write content for a single section of a topic file based on its RESEARCH directive. Runs as a forked subagent: drives the web search-fetch-verify loop inline, then synthesizes the section. Arguments: topic file path, optional section heading (defaults to the first section still carrying

• research-refine-cycle

  Work through the open AUDIT directives in the research project by spawning research-refine-worker subagents in parallel batches — one worker per topic file, each resolving that file's AUDITs serially via research-refine. Takes a <count|all>@<workers> argument: how many AUDIT directives to resolve an

• research-refine

  Refine a topic file by resolving AUDIT comments or applying content-level corrections. Arguments: topic file path, operation (correct|expand|condense|restructure|cross-reference|update|free-text), optional details.

• research-restructure

  Perform structural changes to the research project layout: split, merge, promote, demote, nest, or flatten chapters. Operates at any depth in the topic tree. Arguments: operation, chapter path, optional target path.

• research-status

  Report the derived status of every chapter in a research project — computed live from frontmatter and the RESEARCH/CONFIDENCE/AUDIT directives on disk, not from a stored enum. Use when the user asks for research status/progress, what's left, or which chapters are stub/inquiry/draft/audited/done. Arg

Subagents (10)

• coherence-auditor

  Per-topic coherence auditor for the research workflow. Given a single topic file path, assesses logical progression, transition smoothness, abstraction-level consistency, intro/setup adequacy, and heading-vs-content match. Returns a structured list of findings keyed to line numbers, with recommended

• confidence-verifier

  Web-verification worker for the four research-audit skills. Given a list of `<!-- CONFIDENCE: low -->` and `<!-- CONFIDENCE: medium -->` markers plus the surrounding claims, runs WebSearch + WebFetch to verify each one, and returns a structured per-marker decision. Every marker resolves to exactly o

• corpus-locator

  Read-only placement scout for the research workflow. Given the claims extracted from a single external source, scans the topic tree under research/content/ and returns, per claim, the existing sections whose subject overlaps it — each tagged with the relationship (corroborates, extends, contradicts,

• quality-auditor

  Per-topic quality auditor for the research workflow. Given a single topic file path, assesses depth-vs-scale, sourcing adequacy, citation presence, reference verification, and example concreteness. Returns a structured list of findings keyed to line numbers, with recommended AUDIT severities. Does N

• research-audit-worker

  Execution environment for the `research-audit-topic` skill when it runs as a forked subagent (via `context: fork`). The skill body — supplied as this subagent's prompt — audits one topic across every lens (consistency, coverage, quality, coherence, graphics) and clears its CONFIDENCE markers inline

• research-inquiry-worker

  Inquiry-cycle worker. Runs `research-inquiry` on a single stub topic file and exits with a parser-friendly report block. Used by `/research-inquiry-cycle` to keep the orchestrator session lean — the outline-design reasoning lives inside this subagent and is discarded on return.

• research-investigation-worker

  Execution environment for the `research-investigation` skill when it runs as a forked subagent (via `context: fork`). The skill body — supplied as this subagent's prompt — drives the entire investigation including the inline web search-fetch-verify loop. This file only declares the tool surface and

• research-refine-worker

  Refine-cycle worker. Resolves the open AUDIT directives in a SINGLE topic file by invoking `research-refine` once per directive, serially, then exits with a parser-friendly report block. Used by `/research-refine-cycle` to keep the orchestrator session lean — the web research and prose edits live in

• source-investigator

  Web-research worker for the research workflow. Given a single RESEARCH directive (query, scale, sources, sources_detail, related), runs WebSearch + WebFetch loops to find and verify sources, then returns a structured report of vetted citations, verbatim quote snippets keyed to citation slugs, per-cl

• term-extractor

  Per-topic glossary candidate extractor for the research workflow. Given one topic file, scans for explicitly defined terms, domain jargon, and key concepts, then returns a structured candidate list with definitions derived from how each term is used in the file. Does NOT edit any files — the orchest

Similar plugins