research
starsforks
How to install research?
fusengine/agents/research
$npx -y skills add fusengine/agents --skill researchTechnical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.
SKILL.md
| 1 | **Session:** ${CLAUDE_SESSION_ID} |
| 2 | |
| 3 | **Research Topic:** $ARGUMENTS |
| 4 | |
| 5 | # Research Skill |
| 6 | |
| 7 | ## Research Workflows |
| 8 | |
| 9 | ### Standard Query |
| 10 | ``` |
| 11 | 1. THINK → Sequential Thinking decomposition |
| 12 | 2. RESOLVE → Context7 resolve-library-id |
| 13 | 3. DOCUMENT → Context7 query-docs (5000-10000 tokens) |
| 14 | 4. SUPPLEMENT → Exa code context search |
| 15 | 5. SYNTHESIZE → Structured answer with sources |
| 16 | ``` |
| 17 | |
| 18 | ### Complex Investigation |
| 19 | ``` |
| 20 | 1. DEEP THINK → Multi-hypothesis Sequential Thinking |
| 21 | 2. DEEP RESEARCH → Exa deep researcher (45s-2min) |
| 22 | 3. MONITOR → Check status until completed |
| 23 | 4. VALIDATE → Cross-check Context7 official sources |
| 24 | 5. REPORT → Comprehensive solution |
| 25 | ``` |
| 26 | |
| 27 | ### Technology Trends |
| 28 | ``` |
| 29 | 1. WEB SCAN → Exa search latest developments |
| 30 | 2. CODE PATTERNS → Exa code context for practices |
| 31 | 3. ECOSYSTEM → Company research for key players |
| 32 | 4. ANALYSIS → Sequential Thinking for implications |
| 33 | 5. RECOMMENDATIONS → Actionable insights |
| 34 | ``` |
| 35 | |
| 36 | --- |
| 37 | |
| 38 | ## Multi-Source Synthesis |
| 39 | |
| 40 | **Parallelization**: |
| 41 | - Run `resolve-library-id` + `web_search_exa` simultaneously |
| 42 | - Launch multiple Exa searches concurrently |
| 43 | - Execute Context7 docs + Exa code search in parallel |
| 44 | |
| 45 | **Source Priority**: |
| 46 | 1. Official documentation (Context7) |
| 47 | 2. Recent tutorials (Exa, <6 months) |
| 48 | 3. Older content (with version verification) |
| 49 | |
| 50 | --- |
| 51 | |
| 52 | ## Forbidden Behaviors |
| 53 | |
| 54 | - ❌ Guess library IDs without `resolve-library-id` |
| 55 | - ❌ Start deep researcher without checking completion |
| 56 | - ❌ Mix opinions with facts without distinction |
| 57 | - ❌ Provide code without version verification |
| 58 | - ❌ Ignore WebFetch redirects |
| 59 | - ❌ Recommend without citing sources |
| 60 | - ❌ Skip Sequential Thinking for multi-step problems |
| 61 | |
| 62 | --- |
| 63 | |
| 64 | ## Detailed References (Load on Demand) |
| 65 | |
| 66 | - `references/tool-usage.md` — Load when calling Context7, Exa, or Sequential Thinking (exact call patterns, models, and per-tool error handling) |
| 67 | - `references/response-format.md` — Load when writing the final research report |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
