Stats
Actions
Tags
From research
Research codebase comprehensively, emit SHA-tracked research doc at docs/research/. Updates existing doc if same topic.
How this command is triggered — by the user, by Claude, or both
Slash command
/research:research <research-query>opusThe summary Claude sees in its command listing — used to decide when to auto-load this command
Run the `research` skill from this plugin to investigate:
$ARGUMENTS
Follow the skill's full workflow:
1. Read any explicitly mentioned files first (no offset/limit).
2. Dedupe via `${CLAUDE_PLUGIN_ROOT}/scripts/find_existing.py` (slug + topic) — if a match exists, UPDATE that doc instead of creating a new one.
3. Ultrathink and decompose the query into independent investigation lanes.
4. Spawn parallel sub-agents (Explore / general-purpose) — one message, multiple Agent calls.
5. Synthesize findings; resolve contradictions by re-reading code.
6. Compute `git hash-object` for every refer...Run the research skill from this plugin to investigate:
$ARGUMENTS
Follow the skill's full workflow:
${CLAUDE_PLUGIN_ROOT}/scripts/find_existing.py (slug + topic) — if a match exists, UPDATE that doc instead of creating a new one.git hash-object for every referenced file; capture HEAD SHA, branch, repo, researcher, ISO date.docs/research/YYYY-MM-DD-<slug>.md with the exact frontmatter schema in the skill, OR append a ## Follow-up Research <ts> section to the matched existing doc and bump last_updated* fields.If no $ARGUMENTS were provided, ask the user for their research question, then proceed.
npx claudepluginhub fkesheh/fmk-plugins --plugin research/researchPerforms adaptive deep web research on a query with configurable --depth and --strategy options. Outputs markdown report with executive summary, analysis, confidence scores, and cited sources.
/researchPerforms structured multi-LLM research using configurable breadth (light/standard/exhaustive) and intensity (quick/standard/deep) with web search and multi-source synthesis.
/researchConducts multi-turn deep research on a codebase topic over 5 iterations, tracing code paths with citations, Mermaid diagrams, tables, and confidence ratings.
/researchUnderstand the opportunity and landscape: keyword demand, SERP intent, competitors, content gaps, and site/topic/entity maps. Supports --competitors and --map flags.
/researchConducts a multi-database scientific research investigation using ToolUniverse, calling tools to look up specific claims, cross-validate, and report honest INDETERMINATE results when evidence is insufficient.
/researchGathers external knowledge on a given topic, citing sources so builds stay grounded in facts. Spawns sub-agents for broad sweeps, distills findings into cited rows.