Skip to content

dvy1987/agent-loom / .agents/skills/customer-discovery

customer-discovery

Verified

Run Mom Test–style customer-discovery interviews to validate or kill an unbuilt idea — generate a non-leading interview guide, conduct or coach the conversations, and synthesize signal vs compliments. Load when the user asks to do customer discovery, run problem interviews, validate an idea with users, run a Mom Test, design an interview guide, or says "talk to customers", "validate the problem", "interview users", "Mom Test this", "did real users want it", "synthesize my interviews", "I just talked to N people". Sub-skill of `venture-exploration`. Hard-bans "would you use this?", solution-pitching, friend/family-only ICP, and treating compliments as validation. Calls `secure-*` before synthesizing any pasted external transcripts.

references/examples.md

View on GitHub
# Customer Discovery — Full Worked Examples

Skill: `customer-discovery` | Enriched from SKILL.md (improve-skills pass, SKIP_RESEARCH).

## Example 1 — Documented workflow

**Input:** I want to validate that freelance designers actually pay to chase late invoices. Design my interview guide.

**Output:**
```
Two questions before I draft the guide:

1. What's the most specific past-behaviour signal that would convince you the assumption is real — paying for software, hiring a bookkeeper, switching workflows, or something else?
2. Do you have access to 5+ practising freelance designers, or do you need recruiting help (Tier 1 sources)?
```

## Example 2 — Step-by-step execution

**Input:** "Run `customer-discovery` on [concrete task]"

**Agent actions:**
1. Inputs
2. Define the learning goal
3. Recruit (if mode = design guide)
4. Design the interview guide
5. Coach the live interview (if mode = coach live)
6. Synthesize (if mode = synthesize OR after every batch)
7. Update hypotheses
8. Write and log

**Impact Report shape:**
```
Customer discovery complete: <idea>
File saved: docs/ventures/discovery/YYYY-MM-DD-<slug>-interviews.md
Mode: design / coach / synthesize
Interviews: N (target M)
Painful-problem reports: M/N
Currency evidence: M/N
Verdict: CONFIRMED / WEAKENED / KILLED / NEED-MORE
Assumption updates pushed: N
Logged to: docs/skill-outputs/SKILL-OUTPUTS.md
```

## Example 3 — Gotcha application

**Input:** Task hits a non-obvious edge case

**Apply:**
- **The goal is not to validate. The goal is to learn.** A kill is a win — it saves months.
- **Past behaviour beats predicted behaviour every time.** Future-tense answers are noise.
- **Currency questions are the gold.** "Have you ever spent money / time / built a workaround?" filters real pain from polite agreement.
- **Compliments are seductive.** Code them and move on. Three "cool idea"s is not three confirmations.

---

See `SKILL.md` for hard rules and verification checklist.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall