publish-results — Claude Code skill: what it does, how to install
publish-results is a Claude Code skill that propagates benchmark figures across project docs and site files. Runs before merging release PRs or after altering public metrics.
MIT ★ 80 updated 2026-11-17
npx skills add mralexivy/AutoMode --skill publish-results -a claude-codeWhat publish-results does
publish-results coordinates benchmark reporting from bench/results/headline.json across documentation, comparisons, marketing posts, and the Next.js site in site/. When a metric changes, all referenced files must be updated together in the same pull request rather than across staggered commits.
Verification relies on Node test runners executing tests/claims.test.mts and tests/site.test.mts. CI fails builds whenever numbers drift from committed rows in bench/results/ or when metadata descriptions fall outside the 100 to 165 character boundary. Retired claims are appended to the banned key in headline data.
The routine requires building the site via npm run build inside site/, verifying dark-mode layouts in site/out/, and inspecting the deployed GitHub Pages URL using curl.
What it helps with
- Propagate benchmark stats across documentation, README, and website
- Block obsolete claims during CI test suites
- Validate meta description lengths between 100 and 165 characters
- Audit published metrics against committed data rows in
bench/results/
Example prompts for the agent
- Update all benchmark figures across docs and site using publish-results
- Check current numbers against headline.json and run claims.test.mts
- Prepare the benchmark updates across all surfaces for this release PR
How to install publish-results
1Skills CLI (Vercel)
npx skills add mralexivy/AutoMode --skill publish-results -a claude-code2Manually: put the files in place
~/.claude/skills/publish-results/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/publish-results/
1Skills CLI (Vercel)
npx skills add mralexivy/AutoMode --skill publish-results -a codex2Manually: put the files in place
.agents/skills/publish-results/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mralexivy/AutoMode --skill publish-results -a cursor2Manually: put the files in place
.cursor/skills/publish-results/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mralexivy/AutoMode .claude/skills/publish-results2Manually: put the files in place
.github/skills/publish-results/SKILL.md1Skills CLI (Vercel)
npx skills add mralexivy/AutoMode --skill publish-results -a gemini-cli2Platform CLI
gemini skills install https://github.com/mralexivy/AutoMode --path .claude/skills/publish-resultsManually: put the files in place
.devin/skills/publish-results/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about publish-results
How to install publish-results in Claude Code?
Run npx skills add mralexivy/AutoMode --skill publish-results -a claude-code. Alternatively, place the skill at ~/.claude/skills/publish-results/SKILL.md.
What does publish-results do?
It enforces a checklist ensuring benchmark results, feature comparisons, and documentation metrics stay synchronized across every surface before release branches merge.
What is required to run the publish-results checks?
You need Node.js to execute tests/claims.test.mts and tests/site.test.mts, raw rows in bench/results/, and npm dependencies inside site/.
Source text
SKILL.md · MIT
--- name: publish-results description: Required after any benchmark run that changes a public number, before any release PR merges, and for any edit to the README benchmark section, docs/compare.md or the website. It carries one result to every place a reader sees it, the README, docs, comparison, website, FAQ data and report, so no page is left stale. CI enforces it through tests/claims.test.mts. --- # Publish results everywhere A result is not delivered until every reader sees the same numbers. One stale page makes the whole project look careless. This skill lists every place a result lives. `tests/claims.test.mts` fails CI when a page drifts from the rows or carries a stale claim, so a forgotten page cannot merge. ## When to run it - A benchmark run changes a number you publish: a cost, a pass count, a ratio, a competitor's result. - A release PR is about to merge. - A change alters what the docs promise: a default, a review rule, a model choice. ## 1. Update the source of truth `bench/results/headline.json` holds every public number, the rows it comes from, the pages that must show it, and the stale phrases that must not appear. - Point each entry at the committed rows and the arm, and set `shown` to the value the pages print. - Add every new page that shows a number to `surfaces`. - When a claim stops being true, add its old wording to `banned`. Run `node --test tests/claims.test.mts`. It recomputes each number from the rows, so a typo or a stale total fails here. ## 2. Update every surface Change all of them in the same PR. Never one now and the rest later. | Surface | What to update | |---|---| | `README.md` | The table cell under the banner, the `## Benchmarks` tables, "Where AutoMode does not win", the `## How it compares` paragraph and any review or model claim | | `docs/compare.md` | The feature table's cost row, "Measured on the same sessions", "Where the others are ahead" and the switch section | | `site/app/(home)/page.tsx` | `RESULTS` (the chart widths come from it), the stat cards, `#fit`, the FAQ list, which also feeds the FAQ schema that search engines and AI assistants read | | `site/content/docs/benchmarks/results.mdx`, `site/content/docs/compare.mdx` | The tables, "Where AutoMode does not win" and the byline dates | | `site/content/docs/guides/*.mdx`, `faq.mdx`, `concepts/prompt-cache.mdx` | Any number, and any claim about reviews or models. The calculator's per-step costs live in `site/components/calculator.tsx` | | `bench/experiments/<report>.md` | The results section, the fixes and the limits | | `marketing/posts/*.md` | Every post that is not `sent`. `tests/marketing.test.mts` fails on a number that left the README or `headline.json` | | `CHANGELOG.md` | A line under `[Unreleased]` when the shipped behavior changed | ## 3. Keep it honest - Every number comes from committed rows in `bench/results/`. Never round in AutoMode's favor, and never invent a competitor result. Use our own run, or the project's published result, cited as theirs. - Lead with the most common usage: mixed sessions, and people who run Opus. - Keep the "where it does not win" section. A claim without its limit is marketing, not evidence. - Meta descriptions stay between 100 and 165 characters (`tests/site.test.mts`). ## 4. Check, then verify live ```bash node --test tests/claims.test.mts tests/site.test.mts git ls-files '*.md' '*.html' | xargs grep -nE "<an old number or claim>" ``` - Build the site (`npm run build` in `site/`), serve `site/out/` under `/AutoMode/`, and look at it at desktop and phone widths. The site is dark only. - After the merge, wait for the `pages` workflow, then fetch the live site and confirm it shows the new numbers: `curl -s https://mralexivy.github.io/AutoMode/ | grep '<a new number>'`. Then follow `ship-change` for the issue, branch and PR.
© mralexivy · MIT · mralexivy/AutoMode