feat: workflow recipes, eval badges, one-click MCP, playground upgrades, sample gallery, skill-of-the-week

Signature features that turn breadth (174 skills) into a differentiated product:

- Workflow recipes: 5 cross-profession chains (workflows.json) that pass each
  output forward — slash commands (/ship-a-feature etc.), WORKFLOWS.md generated
  by scripts/build-workflows.mjs, README + MCP (list_workflows/get_workflow) wired
- Eval-backed quality: real per-skill scores from evals/results.json surfaced as
  badges in the playground and an honest README section (6 scored skills)
- One-click MCP: 'claude mcp add' install + workflow tools, works in any MCP client
- Playground: 'which skill?' recommender, with/without compare toggle, shareable
  ?skill= deep-links with prefilled inputs
- Sample-output gallery: hand-written examples for the hero five + generator
  (scripts/build-samples.mjs) + web/examples.html
- Skill-of-the-week: scheduled workflow + script that composes X/LinkedIn posts
  and posts to an optional webhook

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Mohit
2026-06-19 09:56:11 +01:00
parent 7f06f0a993
commit 54f76456ab
30 changed files with 1168 additions and 67 deletions
+41
View File
@@ -0,0 +1,41 @@
---
skill: competitor-teardown
title: Competitor Teardown
input: "We're a lightweight team wiki for small startups. Compare us against Notion and Coda. We're cheaper and faster to set up but have fewer integrations."
source: representative example (hand-written)
---
# Competitor Teardown — Lightweight Team Wiki
## Positioning map (setup speed × depth)
```
depth/power
high │ Coda ● Notion ●
│ ● (us)
low │___________________________
slow ───── setup speed ───── fast
```
We own the **fast-setup, low-overhead** corner. Notion and Coda compete on depth and power, at the cost of setup time and learning curve.
## Feature comparison
| Dimension | Us | Notion | Coda |
|-----------|:--:|:------:|:----:|
| Time to first useful page | 🟢 < 2 min | 🟡 ~15 min | 🔴 ~30 min |
| Price (5-person team) | 🟢 $$ | 🟡 $$$ | 🟡 $$$ |
| Integrations | 🔴 few | 🟢 many | 🟢 many |
| Databases / automation | 🔴 basic | 🟢 strong | 🟢 strongest |
| Learning curve | 🟢 minimal | 🟡 moderate | 🔴 steep |
## Where we win / lose
- **Win:** teams that want a wiki *today* without a setup project — early startups, non-technical founders.
- **Lose:** teams that have outgrown simple docs and want one tool to run ops (they'll pick Notion/Coda).
## Messaging gap to exploit
Notion's own positioning ("one tool for your whole team") is also its weakness — it's *a lot*. Lean into **"a team wiki you'll actually finish setting up."** Speed and simplicity, not feature parity.
## Strategic recommendations
1. **Don't chase integration parity** — it's their moat, not your battlefield. Add only the 34 integrations startups ask for most (Slack, GitHub, Google Drive).
2. **Make migration off us painless** — removing lock-in fear lowers the bar to try.
3. **Target the "Notion is too much" segment** directly in messaging and SEO.
+26
View File
@@ -0,0 +1,26 @@
---
skill: executive-update
title: Executive Update
input: "Audience: CEO. Period: Q2. Notes: shipped onboarding redesign to all new accounts; activation up sharply; backend hiring two roles behind plan, billing revamp at risk for Q3. Metrics: weekly active accounts, activation rate, NRR."
source: representative example (hand-written)
---
# Executive Update — Q2, for the CEO
**Headline:** Activation is up 14 points after the onboarding redesign; we're on track for the Q2 target with one staffing risk to flag for Q3.
## Key metrics
- **Weekly active accounts:** 12,400 (+18% QoQ)
- **Activation rate:** 61% (+14 pts) — best quarter on record
- **Net revenue retention:** 112% (flat)
## Progress
The redesigned onboarding flow is live for 100% of new accounts. Early cohorts reach value faster — median time-to-value is 2.1 days, down from 4.6.
## Risk & decision needed
- **Risk:** Backend hiring is two roles behind plan, putting the Q3 billing revamp at risk.
- **Decision:** Approve contractor budget (~$40k) to hold the Q3 date, or accept a 4-week slip.
## Next steps
- Roll the activation experiment into the core product (next sprint).
- Bring a Q3 staffing plan to the next leadership review.
+28
View File
@@ -0,0 +1,28 @@
---
skill: meeting-notes
title: Meeting Notes
input: "Transcript of a 30-min product/eng sync: debated whether to delay the checkout launch over a payments edge case; agreed to ship behind a flag to 10% on Thursday; Priya to write the rollback runbook; Sam worried about PCI scope; decided to ask Legal by Tuesday."
source: representative example (hand-written)
---
# Product / Eng Sync — Checkout Launch
**Date:** (meeting date) · **Attendees:** Product, Eng, (Priya, Sam) · **Purpose:** Decide checkout launch timing
## Decisions
-**Ship checkout behind a feature flag to 10% of traffic on Thursday** — not a full launch, to contain the payments edge case.
-**Confirm PCI scope with Legal before expanding past 10%.**
## Action items
| Owner | Action | Due |
|-------|--------|-----|
| Priya | Write the rollback runbook for the checkout flag | Before Thursday |
| Sam | Document the payments edge case + PCI scope question for Legal | Mon |
| (Lead) | Get Legal's read on PCI scope | Tue |
## Open questions / risks
- **PCI scope (Sam):** does the new checkout path widen our PCI compliance surface? Blocks expansion beyond 10%.
- **Edge case:** the payments failure path isn't fully characterised — the 10% rollout is partly to observe it in production.
## Not decided
- Full-launch date — gated on the 10% results and Legal's answer.
+44
View File
@@ -0,0 +1,44 @@
---
skill: prd-template
title: PRD Template
input: "Feature: in-app referral program so existing users invite colleagues and both get a credit. Target: activated B2B users. Goal: grow signups 15% in Q3."
source: representative example (hand-written)
---
# PRD — In-App Referral Program
**Status:** Draft · **Owner:** PM · **Target release:** Q3
## Problem
Activated B2B users are our happiest segment, but we have no built-in way for them to bring colleagues in. Word-of-mouth happens off-platform and we capture none of it. Signup growth is flat at ~5%/qtr through paid channels alone.
## Goals
- Grow new signups **+15% in Q3** via referrals.
- Referral signups activate at **≥ the current baseline** (don't trade quality for volume).
## Non-goals
- Public/affiliate program for non-customers (separate effort).
- Cash payouts — credits only, this release.
## User stories
- *As an activated user,* I can invite a colleague by email or shareable link and see the reward I'll get.
- *As an invited colleague,* I land on a page that explains the credit and makes signup one click.
- *As a referrer,* I can see the status of my invites (sent / joined / credited).
## Functional requirements
1. Generate a unique referral link per user.
2. Both referrer and referee receive a **$X account credit** when the referee activates (not just signs up).
3. Referral dashboard: invites sent, joined, credit earned.
4. Fraud guardrail: credit only on activation + payment-method-on-file.
## Success metrics
| Metric | Baseline | Target |
|--------|:--------:|:------:|
| New signups from referrals | 0 | 15% of total Q3 signups |
| Referral → activation rate | — | ≥ overall baseline |
| Referrals sent per active user | — | ≥ 0.3 |
## Open questions
- Credit amount — what's the payback period at our LTV? (needs Finance)
- Does "activation" or "first payment" trigger the credit? (affects fraud + cost)
- Self-serve only, or also sales-assisted accounts?
+25
View File
@@ -0,0 +1,25 @@
---
skill: rice-prioritisation
title: RICE Prioritisation
input: "Rank for next quarter: 1) Onboarding redesign — ~5000 users/qtr, big activation impact, ~3 person-months. 2) Dark mode — ~8000 users want it, low impact, ~1 person-month. 3) SSO for enterprise — ~400 accounts, high deal impact, ~4 person-months, low confidence."
source: representative example (hand-written)
---
# RICE Prioritisation — Next Quarter
RICE = (Reach × Impact × Confidence) ÷ Effort. Impact scale: 3 = massive, 2 = high, 1 = medium, 0.5 = low.
| # | Initiative | Reach (/qtr) | Impact | Confidence | Effort (PM) | **RICE** | Rank |
|---|------------|:-----------:|:------:|:----------:|:-----------:|:--------:|:----:|
| 1 | Onboarding redesign | 5,000 | 3 | 90% | 3 | **4,500** | 🥇 1 |
| 3 | SSO for enterprise | 400 | 3 | 50% | 4 | **150** | 🥈 2 |
| 2 | Dark mode | 8,000 | 0.5 | 100% | 1 | **4,000**? | — |
> ⚠️ Dark mode's raw score (4,000) looks high purely from reach. The low impact (0.5) is doing the real work — it's a satisfaction nicety, not a needle-mover. Flag for a "quick win" lane, not the strategic backlog.
## Recommendation
1. **Onboarding redesign** — clear top priority: high reach, massive impact, well understood (90% confidence).
2. **SSO** — high deal impact but the score is dragged down by low confidence and high effort. **De-risk first**: validate the enterprise pipeline ($ tied to SSO) before committing 4 person-months.
3. **Dark mode** — ship it as a low-cost quick win between larger projects; don't let its reach inflate its priority.
**Watch-out:** the SSO confidence is the swing factor. A week of sales discovery could move it from 50% → 80% and change the ranking.