Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add 45ck/skill-harness --skill qa-to-demogit clone --depth 1 https://github.com/45ck/skill-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/45ck/skill-harness/qa-to-demo)<a href="https://agentmods.dev/skills/45ck/skill-harness/qa-to-demo"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/qa-to-demo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/45ck/skill-harness/qa-to-demo"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/qa-to-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.00466 |
| Opus 5 | $0.00034 | $0.00233 |
| Sonnet 5 | $0.00014 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
qa-to-demo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
QA To Demo
Overview
Use this skill to bridge quality evidence and demo production. The goal is a reproducible spec or clip plan grounded in QA artifacts, not a marketing retelling that hides failures.
Inputs
qa-report.jsonandqa-report.md- manual-qa-machine flow JSON
- screenshots, snapshots, console logs, network logs, page errors, accessibility reports, and performance reports
- bug reproduction notes or Beads/GitHub issue context
- target app URL and startup command, if a new demo spec must be drafted
Conversion Workflow
- Read the QA verdict and evidence before selecting moments.
- Choose the target output:
- product demo for a passing flow
- repro clip for a failing flow
- release proof for a certified flow
- exploratory finding package for triage
- Map QA steps to demo-machine actions using stable targets first: role, label, text, test id, then CSS only as a fallback.
- Preserve assertions as demo checkpoints or review notes.
- Draft a
.demo.yamlonly when the source has enough target and timing detail; otherwise produce a demo plan with missing inputs. - If rendering or capture is run, package output with
demo-story-packager.
Evidence Rules
- Do not convert
failorinconclusiveQA results into positive product demos. - Keep console, network, accessibility, and performance warnings visible in the handoff.
- For bug repro media, show the shortest path that proves the issue.
- For release proof media, include the certification attempt or report path.
Output
Return one of:
.demo.yamldraft plus run command- repro clip plan plus source evidence
- release proof package plan
- list of missing details blocking a reliable demo
Always include the QA report path, source flow path, selected steps, and evidence files.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 50 lines · 68 tokens per session scan A 0350574885a7
qa-to-demo is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 466 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.