FDE Consultants Protocoles Docs - Install and use the open-source skill

Install

Field thesis: install once as a Claude Code plugin, or symlink skill/ manually. No hosted account is required for the open-source skill.

Claude Code â one commandrecommended

# Add the marketplace, then install the plugin (skill + Modex MCP)
/plugin marketplace add selectess/fde-consultants-protocoles
/plugin install fde-consultant@fde-consultant

# Then ask your agent
/fde-consultant scope this new AI project idea

Claude Code â manuallocal

# Or symlink from the repository root
mkdir -p ~/.claude/skills
ln -s "$(pwd)/skill" ~/.claude/skills/fde-consultant

Every FDE deliverable ends with an FDE Assurance Score (0â100, DeepSCR-verified). Browse the public, hash-chained FDE Assurance Registry.

Local MCP server (free) — the Skill ships a 7-tool MCP server (run python3 -m mcp_server from skill/): fde_recon · fde_decompose · fde_roi · fde_scientific_search · fde_evals · fde_ontology · fde_trust_score.

Agent runtime compatibility

Runtime	Recommended use today	Future path
Claude Code	Install `skill/` into `~/.claude/skills/fde-consultant`.	Native skill workflow plus community examples.
Codex	Load `skill/SKILL.md` as project guidance and keep references available.	Packaged skill distribution once public repo URL is finalized.
Cursor / Windsurf	Add `skill/` as project context and invoke the role explicitly.	MCP wrapper when the hosted Beta matures.
Hermes / open agents	Use the Markdown entrypoint plus scripts/templates as callable local assets.	Adapters for agent skill loaders and local tool execution.

Usage pattern

Trigger the skill when the work needs a real delivery artifact: scoping report, prototype spec, architecture, eval framework, production handoff, productization memo, or roadmap.

Example requestsoperator prompts

/fde-consultant scope a customer-support AI triage project
/fde-consultant architect a production RAG system for legal docs
/fde-consultant evaluate this prototype handoff
/fde-consultant productize the reusable parts of this engagement

Repository structure

Path	Purpose	Why it matters
`skill/SKILL.md`	Activation rules, loop, anti-patterns, distribution, scoring.	The agent entrypoint.
`skill/references/`	FDE, AI agents, SaaS, business AI, evals, benchmarks.	Deep context without bloating every prompt.
`skill/prompts/`	Domain research, discovery interview, strategic questions.	Reliable scoping behavior.
`skill/scripts/`	6-Q validator, ROI calculator, ontology extractor, eval runner, scientific hypothesis refinement.	Executable rigor, not pure text.
`skill/templates/`	Scoping, prototype, production handoff, productization memo.	Consistent output contracts.
`skill/examples/`	Multi-industry examples.	Fast onboarding and proof.

Output contracts

Scoping report

Executive summary, stakeholder map, 6-Q answers, pain matrix, ROI, constraints, recommendation.

Prototype spec

Candidate architecture, selected stack, eval baseline, integration plan, failure modes.

Production handoff

Runbook, security, observability, deployment, cost, ownership, incident paths.

Productization memo

Reusable IP candidates, extraction effort, ROI, strategic fit, field insights.

Scripts and verification

`scripts/decompose_problem.py`: validates whether the problem is concrete enough to build.
`scripts/roi_calculator.py`: calculates annual impact, payback, NPV, and sensitivity.
`scripts/ontology_extractor.py`: extracts actors, systems, processes, objects, and metrics.
`scripts/evals_runner.py`: scores deliverables against the 6-trait FDE rubric.
`scripts/scientific_search.py`: runs candidate architecture refinement before promotion.

Testslocal

python3 -m pytest skill/tests -q

Quality gates

Every FDE output should pass six traits: customer curiosity, ownership, decomposition, empathy, product sense, and communication. Auto-reject generic AI advice, slide-only deliverables, no numbers, no evals, no owner, or no production path.

Contribute

Best contributions add proof: better examples, sharper templates, new benchmark references, platform adapters, tests, bug fixes, and real field lessons. The method should compound with every serious use.