jam-proof-table skill
Generates a summary table linking agent claims to Jam.dev screen recordings, status, and links to provide visual proof of work.
- GitHub stars
- 11
- Files
- 2
- Last commit
- Nov 9, 2026
- License
- MIT
- Allowed tools
- —
What does the jam-proof-table skill do?
jam-proof-table generates a summary table linking agent claims to Jam.dev screen recordings, status, and links to provide visual proof of work.
Summary generated from the skill's SKILL.md.
About the jam-proof-table skill
Providing visual proof for technical claims is what this skill enables for developers and QA engineers. When an agent completes a batch of work, such as fixing multiple tickets or running a test suite, it generates a structured summary table. This table connects every specific claim—like a bug being fixed or a feature working—to a corresponding Jam.dev screen recording, status, and direct link.
Agents use the jam-proof tool to record, name, and file these recordings into organized folders. The skill relies on the jam CLI to search for existing recordings, verify video frames or screenshots, and inspect network or console logs to confirm claims. It distinguishes itself by verifying the content of a Jam before listing it, ensuring that a video actually shows the claim at the correct timestamp. If a recording is a replay without video frames, the agent checks the technical events to settle the status. The final output is a markdown table that allows users to verify any claim with a single click.
What an agent can do with it
- 1Verify batch bug fixesGenerate a summary table linking several ticket fixes to their respective Jam.dev screen recordings.
- 2Organize recording historyCreate folders and name Jams using ticket numbers so they are easy to find in the workspace later.
- 3Link fix checks to original issuesMark a new recording as the official fix for an earlier recorded bug to create a backlink.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the jam-proof-table skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the jam-proof-table skill in Plugin
/plugin marketplace add jamdotdev/skills /plugin install jam@jam-plugins
Install the jam-proof-table skill in Claude Code
~/.claude/skills/jam-proof-table/SKILL.md
$ npx degit jamdotdev/skills/skills/jam-proof-table ~/.claude/skills/jam-proof-tableInstall the jam-proof-table skill in Claude Code (project)
.claude/skills/jam-proof-table/SKILL.md
$ npx degit jamdotdev/skills/skills/jam-proof-table .claude/skills/jam-proof-tableInstall the jam-proof-table skill in Codex
~/.agents/skills/jam-proof-table/SKILL.md
$ npx degit jamdotdev/skills/skills/jam-proof-table ~/.agents/skills/jam-proof-tableInstall the jam-proof-table skill in Gemini CLI
~/.gemini/skills/jam-proof-table/SKILL.md
$ npx degit jamdotdev/skills/skills/jam-proof-table ~/.gemini/skills/jam-proof-tableInstall the jam-proof-table skill in Claude.ai
npx degit jamdotdev/skills/skills/jam-proof-table jam-proof-table && zip -r jam-proof-table.zip jam-proof-table # claude.ai → Customize → Skills → + → Create skill → Upload a skill → jam-proof-table.zip
SKILL.md
View on GitHubjam-proof-table
Many claims in, one table out: each thing you say works or is broken, its status, and the Jam that shows it. The user should be able to check every claim in one click without asking "where's the Jam for this?".
To record a new Jam, use jam-proof. This skill names, files, checks and
reports the Jams.
Set up the CLI
command -v jam >/dev/null || echo "jam is not installed"
export PATH="$HOME/.local/bin:$PATH"
jam auth status --json || jam auth login
If jam is not on PATH, stop and ask the user to install it from
https://jam.dev/docs/cli, then continue. Do not install it yourself.
Exit code 3 means not signed in. With no browser (CI, a cloud agent), ask the
user to set JAM_TOKEN to a personal access token from
https://jam.dev/s/settings/mcp as a secret. Never write a token to a file.
jam agent-context prints every command and flag.
1. One claim, one Jam
A row is one claim: "the price no longer truncates", "sign-in works after
sign-out". Each row gets a Jam that shows that claim. When one Jam covers
several claims, give each row the time it shows up (at 0:48).
A claim with no Jam stays in the table as "not recorded". Never list a local video file or screenshot path as a Jam.
2. Name and file every Jam
Titles are how people find Jams later. Use <ticket or source> <what it shows>. A Jam that checks a fix for an earlier Jam reuses that Jam's title
with "fix check: " in front, so both show up in one search.
jam list folders --query "Release 4.2 checks" --json # reuse it if it exists
jam create folder "Release 4.2 checks" --json # otherwise; returns its id
jam update jam "$ID" --folder "$FOLDER_ID" --title "ENG-412 fix check: Pro price wraps"
jam create folder makes a new folder on every call, even with a name that
exists, so look first and pass the id afterwards. One folder per run.
Creating a folder can upgrade a Viewer to a Creator, which can change seat
billing; on a Viewer account, ask first.
Rename and move only the Jams this run recorded, unless asked.
3. Find Jams that already exist
Before recording again, look for the Jam. A run's folder is the most reliable way to find all of its Jams:
jam list folders --query "checks" --json
jam list jams --folder "$FOLDER_ID" --json
jam list jams --created-at -P1D --json # created in the last day
jam list jams --query "price" --order-by createdAt --limit 20 --json
jam list jams --url "https://example.com/pricing" --json
--query is a fuzzy search, not a title filter: read each title before
using a hit. --order-by createdAt lists newest first, so --limit drops
the oldest.
"What was the Jam I gave you?" means the conversation first: search it for
jam.dev/c/ before searching the workspace.
4. Check each Jam before listing it
jam get jam "$ID" --json # reads back, type, duration
Then check it by its type; the other types have no video frames:
jam get frames "$ID" --at 48000 --size medium --out "$(mktemp -d)" # video; outside the repo
jam get screenshots "$ID" --out "$(mktemp -d)" # screenshot
A replay has no frames or screenshots: check it in its events, console and network, and mark the row unconfirmed when they cannot settle the claim.
For a video, open the frame at the moment the claim shows up; --at must be
below the Jam's duration. A blank page, a single frozen frame, or the wrong
tab is not proof. A screenshot is one still image by design: it is proof when
the claim is visible in it. When the Jam does not show the claim, record it
again with jam-proof and say that you did.
Some claims happen off screen: an API status, a count, a sent message. Check
those in jam get network, jam get console or jam get user-events, and
say in the table which part the video shows and which part the events show.
5. Write the table
Keep the order the work was done in. Status is the claim's, one of: works, broken, unconfirmed (the Jam does not settle it), not recorded.
| # | Claim | Status | Jam | Source |
|---|-------|--------|-----|--------|
| 1 | Pro price wraps on narrow cards | works | [ENG-412 fix check](https://jam.dev/c/...) | [ENG-412](...) · [original Jam](https://jam.dev/c/...) |
| 2 | Sign-in after sign-out | broken | [ENG-415 repro](https://jam.dev/c/...) | [ENG-415](...) |
Under the table, one line per row that is not "works", saying why.
After
Offer one comment on each original Jam whose row settles something (works or broken), with the status and the link to its fix check. Skip unconfirmed and not-recorded rows:
jam create comment "$ORIGINAL_ID" "Fix check: works. https://jam.dev/c/<id>"
Post on a yes, or right away when the user already asked.
Mark a fix check as the fix of its original Jam only when its row says
works (markRelated over MCP); the original then shows a "fixed by"
backlink:
jam update jam <fix check id> --mark-related "$ORIGINAL_ID" --type fixes
Use --type proves for a Jam that shows a claim rather than a fix. A broken
or unconfirmed row gets --type relates_to at most, never fixes.
Post the table in chat. Post it to a pull request or ticket only when the user asks.
Send feedback to Jam
When this skill, a Jam MCP tool, a jam command or a Jam doc was wrong,
stale or confusing, or worked unusually well, tell Jam. Send it yourself:
Jam's agents read it, so it needs no approval.
Call the submitFeedback MCP tool with body, category and subject.
When MCP is unavailable, use the CLI:
jam feedback "<what you were doing, what you expected, what happened, the mistake>" --category <skills|mcp|cli|docs> --subject <skill name, tool name or command>
- Jam surfaces only, not the user's code or other tools.
- At most once per session, and never for a slip you corrected yourself.
- No secrets, customer data, source code, stack traces or recording content.
Files in this skill
2jam-proof-table skill questions
How do I install the jam-proof-table skill in Claude Code?
Run npx degit jamdotdev/skills/skills/jam-proof-table ~/.claude/skills/jam-proof-table. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the jam-proof-table skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How do I record a new Jam for a claim?
To record a new Jam, use the jam-proof tool.
What should I do if the jam CLI is not installed?
If the jam command is not on your PATH, you should ask the user to install it from the Jam documentation; do not attempt to install it yourself.
How are claims without a recording handled in the table?
A claim that does not have an associated Jam will remain in the table with a status of 'not recorded'.