hivefiver-mcp-research-loop
Skill51 starsChanged 7 months agoMITView on GitHub
Run iterative MCP-backed research with provider readiness checks, confidence scoring, contradiction control, and fallback governance.
In this repository17 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- .github/get-shit-done/templates/copilot-instructions.mdCopilot instructions
- context-first-gatekeepingSkill
- debug-orchestrationSkill
- delegation-intelligenceSkill
- hivefiver-bilingual-tutorSkill
- hivefiver-domain-pack-routerSkill
- hivefiver-gsd-compatSkill
- hivefiver-persona-routingSkill
- hivefiver-ralph-taskingSkill
- hivefiver-skill-auditorSkill
- hivefiver-spec-distillationSkill
- hivemind-architect-strategistSkill
- hivemind-governanceSkill
- parallel-debugging-hivemindSkill
- sequential-orchestrationSkill
- systematic-debugging-hivemindSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when planning or architecture decisions require evidence-backed research.
- Distinctive: line 11
Run provider readiness check.
- Distinctive: line 28
If any provider is unavailable, continue but downgrade confidence.
- Distinctive: line 40
Use transformed context layers for control.
- Distinctive: line 41
Keep output structure stable.
- Distinctive: line 42
Treat TODO/task updates as first-class state.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
HiveFiver MCP Research Loop
Use this skill when planning or architecture decisions require evidence-backed research.
Workflow
- Run provider readiness check.
- Build query matrix by domain lane.
- Retrieve evidence in grounded order:
- DeepWiki + Repomix (repository grounding)
- Context7 (official semantics)
- Tavily + Exa (external corroboration)
- Build contradiction register.
- Score confidence and emit setup TODOs.
Provider Contract
Required providers:
- Context7
- DeepWiki
- Repomix
- Tavily
- Exa (MCP or provider-native)
If any provider is unavailable, continue but downgrade confidence.
Confidence Contract
full: corroborated, no critical gaps.partial: usable with non-critical gaps.low: critical gaps or unresolved contradictions.
Retry Contract
- Validate contradictions up to 10 iterations.
- At attempt 10, force explicit caveat block.
DeepWiki QA Translation
- Use transformed context layers for control.
- Keep output structure stable.
- Treat TODO/task updates as first-class state.
References
references/provider-matrix.md
Template
templates/evidence-table.md
Scripts
scripts/check-mcp-readiness.mjsscripts/score-confidence.sh
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.