research
Skill9 starsChanged 3 months agoMITView on GitHub
Deep online research on any topic. Produces structured reports with citations and confidence scores. Three depth modes — quick scan, standard investigation, or deep dive.
189 other projects use a version of this.
Adopted by
Most recently taken up by
- bamlab/flashlighttheir own version, first seen Nov 16, 2026
- lhotwll217/owner-operatortheir own version, first seen Nov 16, 2026
- Suge8/friedbuntheir own version, first seen Nov 15, 2026
- Fractera/Agent-Engineering-Infrastructuretheir own version, first seen Nov 15, 2026
- Fractera/Agentic-Engineering-Infrastructuretheir own version, first seen Nov 15, 2026
- iha2/superlitetheir own version, first seen Nov 15, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新
Also in 5 projects that use this
LambenthanSkillexp-eval
实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
truongtv22SkillProblem-Solving Techniques
Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.
Also in 5 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
skyllwtSkillexp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
- +5 more from Lambenthan
- +1 more from skyllwt
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- mattpocock/skills★ 325ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- udecode/plate★ 17ksame name
- openai/plugins★ 7.8ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- withcoral/coral★ 5ksame name
179 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository56 other files it gives its agents.
- .claude/agents/CLAUDE.mdCLAUDE.md
- .claude/hooks/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .claude/prompts/CLAUDE.mdCLAUDE.md
- .claude/rules/CLAUDE.mdCLAUDE.md
- .claude/skills/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- vision/CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- scaffold/llms.txtllms.txt
- architecture-checkSkill
- backlog-reviewSkill
- bootstrapSkill
- brainstormSkill
- buildSkill
- claude-sense-checkSkill
- code-qualitySkill
- commitSkill
- continueSkill
- custom-hooksSkill
- dashboardSkill
- debug-sessionSkill
- deploySkill
- discoverSkill
- doctorSkill
- fix-issueSkill
- framework-upgradeSkill
- handoffSkill
- help-meSkill
- ideateSkill
- lanesSkill
- manual-testSkill
- merge-downSkill
- merge-upSkill
- optimizeSkill
- parallel-workSkill
- performance-checkSkill
- phase-reviewSkill
- pr-statusSkill
- quality-checkSkill
- quickstartSkill
- refine-loopSkill
- retrospectiveSkill
- security-auditSkill
- skill-createSkill
- skill-evalSkill
- sprint-endSkill
- sprint-startSkill
- story-cycleSkill
- testing-cycleSkill
- test-validatorSkill
- UAT-cycleSkill
- undo-workSkill
- uninstallSkill
- weekly-maintenanceSkill
- wrap-upSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
28 rules. 0 are common, 25 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
25
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Before starting research, assess whether the query is specific enough:
- Distinctive: line 29
Ask 1–2 focused clarifying questions using AskUserQuestion
- Distinctive: line 30
Ask about scope: "What specific aspect of [topic] are you interested in?"
- Distinctive: line 31
Ask about context: "Is this for a specific project/technology, or a general investigation?"
- Distinctive: line 35
Ask about depth: if not obvious from the query:
- Distinctive: line 36
Use AskUserQuestion with options: "Quick scan (2-3 searches, fast answer)", "Standard (parallel research, 2-3 min)", "Deep dive …
- Distinctive: line 37
If the query clearly implies depth (e.g., "comprehensive analysis of..." → deep), skip asking
- Distinctive: line 41
Before doing new research, check if this topic has been investigated before:
- Very specific: line 43
Search docs/research/ for matching topics (Grep on title/tags in frontmatter)
- Very specific: line 44
Search docs/solutions/ for related findings
- Very specific: line 45
Search docs/brainstorms/ for related design explorations
- Distinctive: line 47
If prior research exists:
- Distinctive: line 49
If it's recent and relevant: present it to the user, ask if they want fresh research or if prior findings suffice
- Distinctive: line 50
If it's outdated or partially relevant: note it as context for the new research
- Distinctive: line 74
Do NOT dispatch research agents until the user approves the research plan.
- Distinctive: line 79
After plan approval, execute using the deep-research methodology:
- Distinctive: line 88
After dispatch: "Researching [N] sub-questions in parallel..."
- Distinctive: line 89
After collection: "Collected findings from [N] sub-questions.
- Distinctive: line 102
Ask user: "These areas have low confidence: [gaps].
- Distinctive: line 103
If yes: apply Phase 4 (Deepen) from deep-research methodology — targeted follow-up research
- Distinctive: line 104
If no: proceed with current findings, noting confidence gaps
- Distinctive: line 160
NEVER skip the clarification gate for vague queries — bad input produces bad research
- Distinctive: line 161
NEVER present training-data knowledge as research findings — all claims must come from web sources
- Distinctive: line 162
NEVER dispatch research without user approval of the plan
- Distinctive: line 163
ALWAYS save research reports for future reference (they prevent redundant research)
- Distinctive: line 164
ALWAYS show the executive summary inline — don't make users open the file to see results
- Distinctive: line 165
ALWAYS check for prior research before starting new research
- Distinctive: line 166
Keep the research plan visible and the user in control of depth and scope
“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
research
Skill metrics: Emit a start event to the activity log:
echo "{\"type\":\"skill\",\"event\":\"start\",\"skill\":\"research\",\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" >> docs/sessions/.activity-log.jsonlResearching: $ARGUMENTS
Phase 1: Clarification Gate
Before starting research, assess whether the query is specific enough:
If the query is vague (single word, no clear question, ambiguous scope):
- Ask 1–2 focused clarifying questions using AskUserQuestion
- Ask about scope: "What specific aspect of [topic] are you interested in?"
- Ask about context: "Is this for a specific project/technology, or a general investigation?"
If the query is specific enough — proceed directly.
Ask about depth if not obvious from the query:
- Use AskUserQuestion with options: "Quick scan (2-3 searches, fast answer)", "Standard (parallel research, 2-3 min)", "Deep dive (comprehensive, 5-10 min)"
- If the query clearly implies depth (e.g., "comprehensive analysis of..." → deep), skip asking
Phase 2: Check Prior Research
Before doing new research, check if this topic has been investigated before:
- Search
docs/research/for matching topics (Grep on title/tags in frontmatter) - Search
docs/solutions/for related findings - Search
docs/brainstorms/for related design explorations
If prior research exists:
- Load it and assess: is it still current? Does it answer the query?
- If it's recent and relevant: present it to the user, ask if they want fresh research or if prior findings suffice
- If it's outdated or partially relevant: note it as context for the new research
Phase 3: Plan Research
Compose the deep-research methodology (.claude/prompts/deep-research.md):
- Classify depth — Auto-classify using depth profile heuristics, or use the user's explicit choice
- Decompose query — Break into sub-questions per Phase 1 of deep-research methodology
- Present plan to user — Show the sub-questions and depth before executing
Present the research plan:
Research plan for: [query]
Depth: [quick/standard/deep]
Sub-questions:
1. [sub-question 1] — [web/code/hybrid]
2. [sub-question 2] — [web/code/hybrid]
3. [sub-question 3] — [web/code/hybrid]
Estimated: [N] searches, [time estimate]<HARD-GATE>
Do NOT dispatch research agents until the user approves the research plan. The user may want to adjust sub-questions, change depth, or add specific areas to investigate.
</HARD-GATE>Phase 4: Execute Research
After plan approval, execute using the deep-research methodology:
- Quick depth: Execute inline — search sequentially, no subagent dispatch
- Standard/Deep depth: Dispatch parallel subagents per sub-question using the Agent tool
- Each subagent is a
research-analyst(general-purpose agent with the research-analyst prompt) - Each receives: sub-question, search strategy, tool budget, output format instructions
- Launch ALL subagents in a single message for parallel execution
- Each subagent is a
Communicate progress to the user between phases:
- After dispatch: "Researching [N] sub-questions in parallel..."
- After collection: "Collected findings from [N] sub-questions. Synthesizing..."
Phase 5: Synthesize & Evaluate
Apply Phase 3 (Synthesize) from the deep-research methodology:
- Merge all subagent reflections into a coherent answer
- Resolve contradictions explicitly
- Assess overall confidence (weighted average of sub-question confidences)
- Compile knowledge gaps
If confidence is below threshold (70 for standard, 80 for deep):
- Present initial findings with low-confidence areas highlighted
- Ask user: "These areas have low confidence: [gaps]. Want me to dig deeper on any of them?"
- If yes: apply Phase 4 (Deepen) from deep-research methodology — targeted follow-up research
- If no: proceed with current findings, noting confidence gaps
Phase 6: Output & Persist
- Generate report using the
research-reportformat fromreferences/research-report-template.md - Save to
docs/research/<topic-slug>.mdwith full YAML frontmatter - Present key findings to the user — don't just say "report saved", show the executive summary and top findings inline
Topic Slug Generation
- Lowercase the topic
- Replace spaces with hyphens
- Remove special characters
- Truncate to 50 characters
- Example: "Modern auth token rotation" →
modern-auth-token-rotation
Phase 7: Cross-Reference & Next Steps
After presenting findings:
- Check backlog impact — Search
docs/reference/BACKLOG_INDEX.mdfor stories that might be affected by these findings - Check solution overlap — Search
docs/solutions/for existing learnings that should be updated - Check ADR relevance — Search
docs/adr/for accepted decisions about the researched topic. If the research contradicts an accepted ADR, flag it explicitly ("Research suggests X, but ADR-NNNN chose Y because Z — consider whether to supersede"). If the research validates an accepted ADR, note the confirmation. - Suggest next steps based on findings:
- "These findings suggest a brainstorm:
/brainstorm [topic]" - "This could become stories:
/ideate [idea based on findings]" - "A spike story would help validate: [specific uncertainty]"
- "Findings are informational only — no action needed"
- "These findings suggest a brainstorm:
Skill metrics: Emit a completion event:
echo "{\"type\":\"skill\",\"event\":\"end\",\"skill\":\"research\",\"outcome\":\"success\",\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" >> docs/sessions/.activity-log.jsonlExample
Input: /research "Compare SQLAlchemy vs Tortoise ORM for async Python APIs"
Phase 1: Query is specific, implies comparison → auto-depth: Standard
Phase 2: No prior research found
Phase 3: Plan presented —
Sub-questions:
1. SQLAlchemy async capabilities and maturity
2. Tortoise ORM async capabilities and maturity
3. Performance benchmarks and community adoption
4. Migration path and ecosystem compatibility
Phase 4: 4 subagents dispatched in parallel
Phase 5: Confidence 82/100 — all sub-questions well-covered
Phase 6: Report saved to docs/research/sqlalchemy-vs-tortoise-orm.md
Phase 7: No backlog impact. Suggested: /brainstorm if choosing ORM for new projectRules
- NEVER skip the clarification gate for vague queries — bad input produces bad research
- NEVER present training-data knowledge as research findings — all claims must come from web sources
- NEVER dispatch research without user approval of the plan
- ALWAYS save research reports for future reference (they prevent redundant research)
- ALWAYS show the executive summary inline — don't make users open the file to see results
- ALWAYS check for prior research before starting new research
- Keep the research plan visible and the user in control of depth and scope
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

