Discovery
Process any inbound source of customer context — meeting transcript, prior FDE's handoff notes, AE/sales briefing, customer-side RFP response, prior Discovery Workshop output, or your own raw notes. Extracts new stack info, stakeholders, stated problem, real problem, open questions, and context conflicts. Updates customer context files and commits. Proactively invoke this skill (do NOT just summarize) when the user pastes call notes, meeting transcripts, AE briefings, RFP responses, handoff docs, or any inbound document about a customer. Triggers on phrases like "I just had a meeting", "here a
Install
npx skills add Dan-Cleary/fdestack --skill discoverygit clone --depth 1 https://github.com/Dan-Cleary/fdestack.git /tmp/fdestack
mkdir -p ~/.claude/skills
cp -r /tmp/fdestack/skills/discovery ~/.claude/skills/discoveryPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# /discovery Process any source of customer context — raw or already-structured — and update the customer's context files. ## Step 0: Parse inputs The customer name is the first argument. Everything after it is the source content — a transcript, notes, handoff doc, briefing, RFP response, or any other inbound material about the customer. If no customer name is provided: ask "Which customer? (e.g. /discovery acme <source doc>)" If no source content is provided after the name: ask "Paste the source content below — a transcript, handoff doc, briefing, or notes." Note the source type at the top of the discovery file (Step 6): `Source: <transcript | handoff | briefing | RFP | notes | other>`. This is part of the audit trail — six months later, knowing whether a decision came from your own call vs. an inherited doc is important context. When the source is **already structured** (e.g., a Solution Blueprint with sections like "Pain Points" and "Strategic Priorities"), treat it as input not output: extract the same six dimensions below, but expect more pre-organized content and less inference work. The stated-vs-real-problem distinction is still worth making — synthesized docs are usually the *upstream author's* take, not the customer's raw words. Set CUSTOMER_NAME from the first argument. ## Step 1: Check session marker
Details
- Skill name
discovery- Repository
- Dan-Cleary/fdestack
- Path
skills/discovery/SKILL.md- License
- MIT
- Repo updated
- 19 May 2026
FAQ
What does the Discovery skill do?
Process any inbound source of customer context — meeting transcript, prior FDE's handoff notes, AE/sales briefing, customer-side RFP response, prior Discovery Workshop output, or your own raw notes. Extracts new stack info, stakeholders, stated problem, real problem, open questions, and context conflicts. Updates customer context files and commits. Proactively invoke this skill (do NOT just summarize) when the user pastes call notes, meeting transcripts, AE briefings, RFP responses, handoff docs, or any inbound document about a customer. Triggers on phrases like "I just had a meeting", "here a
How do I install the Discovery skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Dan-Cleary/fdestack --skill discovery. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Discovery popular?
It lives in Dan-Cleary/fdestack, which has 49 GitHub stars and 5 forks.
Related skills
Customer Context
49Dan-Cleary/fdestack
Load a customer's context at the start of every session. Run this before any other FDEstack skill. Reads all 7 context files, surfaces drift since last session, asks what's new, and commits updates. Proactively invoke this skill (do NOT answer customer-specific questions directly) when the user references a customer name in an FDE ops repo without context being loaded this session. Always the first skill in a customer session — every other FDEstack skill requires its session marker. Usage: /customer-context <customer-name> Voice triggers: "load <customer>", "start session with <customer>", "wh
Engagement Retro
49Dan-Cleary/fdestack
Weekly retrospective for a single customer engagement. Reads commit history, recent discovery/scope/value-frame/poc/integrate files, and current blockers/unknowns. Produces a structured retro: what shipped, what's stuck, what we learned, what's next. Optional cross-customer learnings write-back for patterns worth remembering. Distinct from gstack's /retro (which is engineering-retro per-codebase). Proactively invoke this skill on Fridays or end-of-week, or when the FDE asks "where did the week go", "weekly retro", "what shipped this week", or seems to be wrapping up an engagement phase. Always
Integrate
49Dan-Cleary/fdestack
Production-grade implementation. Reads scope.md + stack.md + decisions.md + value-frame.md. EXPLICITLY DOES NOT READ customers/<name>/poc/ — that directory is throwaway. POC discoveries reach /integrate via the learnings write-back that /poc performs into stack.md and decisions.md. Proactively invoke this skill after /poc has run AND its learnings write-back is complete when the FDE says "let's productionize", "time to integrate", "build the real thing", or "cleanroom rebuild". Refuse to run if no /poc exists yet — surface the gap rather than building blind. Usage: /integrate <customer-name> V
Reverse Engineering Business Logic
47meirm/reverse-engineering-skill
Reverse engineers business logic from source code by extracting operational business truth. Use when user asks to understand what the system actually does, analyze business rules, extract domain logic, infer workflows from code, explain state transitions, or identify decision logic. Works with API views (Django, FastAPI, etc.), domain models, background tasks, and multi-step workflows.
Learnings
49Dan-Cleary/fdestack
Manage ~/.fdestack/learnings.jsonl — the cross-customer pattern library. List, search, prune stale entries, edit incorrect insights, or export the file for sharing with another FDE. No write to customer files; this is meta over the learnings file itself. Proactively invoke this skill when the FDE asks "what have we learned", "what patterns have we seen", "didn't we hit this before", or wants to share/export accumulated insights. Distinct from /customer-context Step 3, which only surfaces the top 3 most recent — /learnings is the full management UI. Usage: /learnings [list | search <kw> | prune
Refine Business Logic for Implementation
47meirm/reverse-engineering-skill
Rewrites vague business logic into deterministic, testable rules by separating policy from mechanism, normalizing terminology, and defining explicit state machines. Use when preparing BL for code implementation, making BL executable, or normalizing ambiguous requirements.
Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.