skills/showcase/SKILL.md
Turn a working repo into credible external-facing proof: demoability audit, deterministic demo path, marketing site, case study, screenshots, demo video, launch copy, and consulting portfolio assets. Use when: "productize this", "make this demoable", "make this polished", "make a marketing site", "show this off", "demo video", "case study", "portfolio piece", "consulting asset", "launch page", "sales demo". Trigger: /showcase, /productize, /demoability.
npx skillsauth add phrazzld/spellbook showcaseInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Make a real product showable without laundering weak truth.
This skill owns the gap between "it works locally" and "a serious buyer, client, collaborator, or prospect can understand and trust it." It is not a marketing checklist. The primitive is showable proof: a deterministic demo surface, evidence-backed story, polished product moments, and assets that make the operator look credible.
| Need | Load |
|---|---|
| Decide if the repo is demoable yet | references/demoability-audit.md |
| Position for consulting or portfolio use | references/consulting-positioning.md |
| Plan a marketing site or launch page | references/launch-page-contract.md |
| Script or verify a demo video | references/demo-video-contract.md |
| Keep external copy tied to real proof | references/evidence-gate.md |
| Write a reusable execution plan | templates/showcase-plan.md |
| Draft a landing page outline | templates/landing-page-outline.md |
| Draft a demo video script | templates/demo-script.md |
| Draft a case study | templates/case-study.md |
Use /shape when product direction is unsettled. Use /design for visible
artifact critique or implementation polish. Use /qa for live surface
verification. Use /deliver to build the shaped slice. This skill decides what
showcase work is worth doing and what proof must exist before it is public.
Audit: ranked gaps with proof gap / demo gap / polish gap / story gap,
the smallest next slice, and the verification path.
Plan: a showcase-plan.md style packet: audience, offer, demo scenario,
asset list, gates, non-goals, and first deliverable.
Build: shaped tickets for demo harness, product polish, site, video, or case study. Keep each slice independently verifiable.
Review: adversarial pass over public assets: what would embarrass us if a prospect clicked, ran, or asked for proof?
Delegate per the shared Roster contract in harnesses/shared/AGENTS.md.
Useful lanes:
Critics get the artifact plus the evidence map. They do not get the author's intent trail.
See harnesses/shared/AGENTS.md (Completion Evidence) for the shared evidence
core. Showcase adds:
## Showcase Gate
- Audience and offer: who this is for, and what action the asset asks for.
- Demo path: exact command, route, fixture, seed/reset flow, or waiver.
- Proof artifacts: screenshots, video, logs, CI, dogfood, release, or case-study evidence.
- Evidence map: each public assertion mapped to proof or labeled as vision.
- Product polish: visible product moment inspected, not just marketing wrapper.
- Design/copy review: artifact-backed critique result and unresolved findings.
- Fresh verifier: cold run or adversarial review result.
- Public risk: what a prospect could click, ask, or run that would still fail.
testing
Capture one compounding repo-technical learning while a solved problem is still fresh. Use when: after a bug fix, diagnosis, delivery, review, or incident reveals a reusable pattern worth adding to `docs/solutions/`. Trigger: /compound, /capture-learning, /learning.
testing
Route Misty Step factory application capabilities. Use when choosing, auditing, integrating, or operating Canary, Powder, Landmark, Aesthetic, or Bitterblossom: production observability, incidents, health checks, error logging, backlog/work-card state, release intelligence, UI/UX system adoption, or supervised/unsupervised agent dispatch. Trigger: /factory-apps, /factory-stack.
testing
Prove a skill beats no-skill with a falsifiable A/B eval, or retire it. Design, generate, run, and maintain a skill-specific eval: name the one claim the skill must earn, run it skill-on vs raw same-model, grade blind with objective checks first, return a keep/adapt/cut verdict. Use when: "eval this skill", "does this skill help", "prove the skill beats no skill", "write an eval for", "benchmark a skill", "is this skill worth it", "skill A/B", "skill regression test", "generate skill evals". Trigger: /skill-eval, /eval-skill, /prove-skill.
tools
> Template. Copy to `<target-repo>/.agents/skills/<repo>-<domain>/SKILL.md` > and fill every bracketed placeholder from the live target repo. Delete this > line and every other `> ` guidance line before committing. See > `../../references/repo-local-skill-generation.md` for the full process. --- name: <repo>-<domain> description: | [One paragraph: what this skill verifies/runs/operates for <repo>, stated in terms of the repo's real shape (service/CLI/library/etc.), not generic process. En