improve-harness SKILL.md skillA

improve-harness from dvasyliev/claude-code-tip-calculator is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dvasyliev/claude-code-tip-calculator/improve-harness@git:20261028.131ba1d

Pins git:20261028.131ba1d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dvasyliev/claude-code-tip-calculator
Path
.claude/skills/improve-harness/SKILL.md
Versions recorded
1
Latest version
git:20261028.131ba1d, committed Oct 28, 2026
Size
2,863 bytes
Repository stars
4
License
none declared

Use at the end of a feature, or when a hook, rule or skill did not work as expected, to find harness problems from this session and fix the ones the user approves.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Improve the harness

<!-- Collect: the agent checks the session against the symptoms file, adds what the user asked to fix, and keeps only the problems that will come back. -->

## 1. Collect

Find harness problems in this session from three sources:

- Symptoms: read `references/symptoms.md` and note every symptom that happened in this session, for example a hook that did not run or an instruction that was ignored.
- User requests: everything the user corrected in chat or asked to fix in the harness.
- Code review findings that a lint rule or a project rule could have caught.

Do not write a log; the session already holds these signals.
Keep only problems likely to repeat in the next feature. Drop one-offs and matters of taste.

<!-- Ask: the agent explains each problem in plain words and lets the user decide whether and how to fix it. -->

## 2. Ask

Sort by how often the problem repeated in this session, broken harness before missing rules.
Ask about four at most, in one `AskUserQuestion` call.
List the rest in one line each under "Not fixed this time".

Each problem is one question. The question text is one to three connected
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dvasyliev/claude-code-tip-calculator/improve-harness@sha256:ac906f9b68950db2

The line at the top of this page pins the label git:20261028.131ba1d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_37zicdqsnetxpprv.svg)](https://markdownregistry.com/a/art_37zicdqsnetxpprv)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 28, 2026.

versioncommittedcommitsizeaudit
git:20261028.131ba1d latest2026-10-28 131ba1d 2,863 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2863 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

dvasyliev/claude-code-tip-calculator · 4 stars · license none declared · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_37zicdqsnetxpprv
GET https://markdownregistry.com/api/v1/resolve?ref=dvasyliev/claude-code-tip-calculator/improve-harness
GET https://markdownregistry.com/api/v1/blob/ac906f9b68950db25bd3594c1e81d46e68286d9f2d562cf304ddbf9d7abd05ab

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dvasyliev/claude-code-tip-calculator

AGENTS.md@.agents/skills/vercel-composition-patterns AGENTS.md file
dvasyliev/claude-code-tip-calculator · .agents/skills/vercel-composition-patterns/AGENTS.md
git:20261027.8098a65 · audit A · 4 stars
vercel-composition-patterns SKILL.md skill
dvasyliev/claude-code-tip-calculator · .agents/skills/vercel-composition-patterns/SKILL.md
v1.0.0 · audit B · 4 stars
AGENTS.md@.agents/skills/vercel-react-best-practices AGENTS.md file
dvasyliev/claude-code-tip-calculator · .agents/skills/vercel-react-best-practices/AGENTS.md
git:20261027.8098a65 · audit B · 4 stars
vercel-react-best-practices SKILL.md skill
dvasyliev/claude-code-tip-calculator · .agents/skills/vercel-react-best-practices/SKILL.md · React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing…
v1.0.0 · audit A · 4 stars
web-design-guidelines SKILL.md skill
dvasyliev/claude-code-tip-calculator · .agents/skills/web-design-guidelines/SKILL.md · Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit…
v1.0.0 · audit A · 4 stars
committing-with-commitlint SKILL.md skill
dvasyliev/claude-code-tip-calculator · .claude/skills/committing-with-commitlint/SKILL.md · Use when writing a git commit message in a repository that uses commitlint — read the enforced convention first, write…
git:20261028.03017e5 · audit A · 4 stars
context7-mcp SKILL.md skill
dvasyliev/claude-code-tip-calculator · .claude/skills/context7-mcp/SKILL.md · This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples…
git:20261022.13d13e9 · audit A · 4 stars
playwright-cli SKILL.md skill
dvasyliev/claude-code-tip-calculator · .claude/skills/playwright-cli/SKILL.md · Automate browser interactions, test web pages and work with Playwright tests.
git:20261027.130d068 · audit A · 4 stars
AGENTS.md AGENTS.md file
dvasyliev/claude-code-tip-calculator · AGENTS.md
git:20261027.7063e2d · audit A · 4 stars
CLAUDE.md CLAUDE.md file
dvasyliev/claude-code-tip-calculator · CLAUDE.md
git:20261028.c821237 · audit A · 4 stars

Every file in dvasyliev/claude-code-tip-calculator

Browse by kind, by grade A, or by owner.