Agent skill

Replay Session

by fullsend-ai in fullsend-ai/fullsend

A skill your agent uses when the user wants to replay a Claude Code session from a GitHub Actions artifact link.

Apache-2.0Auto-check passedDevOps & Cloud

Install Replay Session

skills CLI
$ npx skills add fullsend-ai/fullsend --skill replay-session -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install fullsend-ai/fullsend replay-session --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/fullsend-ai/fullsend.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/replay-session .claude/skills/replay-session && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
replay-session
GitHub stars
149
Token cost
~884 tokens
SKILL.md length
385 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user wants to replay a Claude Code session from a GitHub Actions artifact link.

  • Works in 6 steps: Get the artifact → Ask clarifying questions → Download the artifact → …
  • The user wants to replay a Claude Code session from a GitHub Actions artifact link
  • SKILL.md covers Prerequisites, Workflow and Notes
  • Calls gh and npm; reaches github.com

What it does

Replay Session is an agent skill from fullsend-ai/fullsend. Use when the user wants to replay a Claude Code session from a GitHub Actions artifact link. Downloads the artifact, finds JSONL files, generates an interactive HTML replay with claude-replay, and serves it locally.

Its SKILL.md is about 880 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires claude-replay (npm install -g claude-replay) and gh CLI authenticated with access to the target repository

It sits in DevOps & Cloud, covering CI/CD and HTML artifacts. It works with GitHub Actions. The repository describes itself as: On the path to fully autonomous agentic engineering. The licence is Apache-2.0.

When your agent uses it

  • The user wants to replay a Claude Code session from a GitHub Actions artifact link
  • Tasks that involve CI/CD
  • Tasks that involve HTML artifacts

Example prompts

  • “/replay-session”

Requirements

  • Node.js
  • Compatibility (from SKILL.md): Requires claude-replay (npm install -g claude-replay) and gh CLI authenticated with access to the target repository

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Get the artifact
  2. Ask clarifying questions
  3. Download the artifact
  4. Find the JSONL file(s)
  5. Generate and serve the replay
  6. Multiple JSONL files

What it can do on your machine

Read from SKILL.md and the folder at commit 6c6be1e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires claude-replay (npm install -g claude-replay) and gh CLI authenticated with access to the target repository

    From compatibility in the SKILL.md frontmatter.

Context cost

Replay Session loads about 884 tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 385 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~884

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from fullsend-ai/fullsend at commit 6c6be1e, republished under its Apache-2.0 licence (© fullsend-ai). 385 words, ~884 tokens.

Download SKILL.mdSave it as .claude/skills/replay-session/SKILL.md (or your agent's skills folder).
name
replay-session
description
Use when the user wants to replay a Claude Code session from a GitHub Actions artifact link. Downloads the artifact, finds JSONL files, generates an interactive HTML replay with claude-replay, and serves it locally.
compatibility
Requires claude-replay (npm install -g claude-replay) and gh CLI authenticated with access to the target repository

Replay Session from GitHub Actions Artifact

Generate an interactive HTML replay from a JSONL transcript stored in a GitHub Actions artifact.

Prerequisites

  • claude-replay installed globally (npm install -g claude-replay)
  • gh CLI authenticated with access to the target repository

Workflow

1. Get the artifact

The user provides a GitHub Actions run URL. Extract the owner, repo, and run ID from it.

URL formats to expect:

  • https://github.com/OWNER/REPO/actions/runs/RUN_ID
  • https://github.com/OWNER/REPO/actions/runs/RUN_ID/attempts/N
  • https://github.com/OWNER/REPO/actions/runs/RUN_ID/artifacts/ARTIFACT_ID
  • Or the user may just give a run ID and repo name separately
2. Ask clarifying questions

Before downloading, interactively ask the user:

  • Which artifact? Run gh run view <run-id> -R OWNER/REPO to list the artifacts available in that run. If there are multiple artifacts, ask which one to use.
  • Which JSONL? After downloading, list the JSONL files grouped by iteration with their sizes. Each artifact represents a single agent — all JSONL files inside belong to that agent across its iterations. Default to replaying all files. Only ask the user to narrow down if they want a specific iteration or subset.
  • Replay options? Ask if they want any special options (turn range, theme, hide thinking blocks, redact strings). Defaults are fine for most cases — don't over-ask.
3. Download the artifact
bash
TMPDIR=$(mktemp -d /tmp/replay-XXXXXX)
gh run download <run-id> -R OWNER/REPO -n "<artifact-name>" -D "$TMPDIR/artifact"
4. Find the JSONL file(s)

The downloaded artifact represents a single agent run. Its top-level directory (e.g., agent-code-2446-1776439672/) is the agent identifier. All JSONL files inside — across all iteration-N/ subdirectories — belong to this agent. There is no need to ask the user which agent to replay.

bash
find "$TMPDIR/artifact" -name "*.jsonl" -type f

List the files to the user grouped by iteration, with sizes, so they can choose "all" (default) or a specific subset.

Show full SKILL.md (121 more words)Show less
5. Generate and serve the replay
bash
claude-replay <path-to-jsonl> --no-compress -o "$TMPDIR/replay.html" [extra options]
claude-replay <path-to-jsonl> --no-compress --serve --port 7331

Always use --no-compress — compressed replays fail to render in some browsers.

If port 7331 is busy, try 7332, 7333, etc.

Present the URL to the user: http://127.0.0.1:<port>

6. Multiple JSONL files

If the user wants to replay multiple files (e.g., main + subagents), chain them:

bash
claude-replay file1.jsonl file2.jsonl file3.jsonl -o "$TMPDIR/replay.html"

Notes

  • Always use /tmp for downloaded artifacts and generated HTML — never pollute the working directory.
  • The --serve flag works even though the process appears to exit immediately in the background. The server stays up — don't retry or switch to a different HTTP server.
  • Kill the previous server's port before starting a new one: kill $(lsof -ti:<port>) 2>/dev/null
  • Remind the user that the server will stop when the Claude Code session ends.

© fullsend-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/replay-session of fullsend-ai/fullsend.

Open the folder on GitHubat commit 6c6be1e

Compare with similar skills

Replay Session next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Replay Session compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Replay Session this skillfullsend-ai/fullsend149—~884Automated safety check: PassApache-2.0
Analyze GitHub Action Logswithastro/astro63k1 repos~1.3kAutomated safety check: PassCustom licence
GitHub Actions Templatesbartstc/vite-ts-react-template12214 repos~1.9kAutomated safety check: PassMIT
Nushellccusage/ccusage19k—~938Automated safety check: PassCustom licence
Repo Hygiene Scan and FixQwenLM/qwen-code28k—~1.7kAutomated safety check: PassApache-2.0
Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit2606 repos~1.1kAutomated safety check: NotesCustom licence

Similar skills

  • Official

    Analyze recent GitHub Actions workflow runs to identify patterns, mistakes, and improvements.

    63k GitHub starsUsed in 1 repo~1.3k tokens
    DevOps & CloudAuto-check passed
  • GitHub Actions Templates

    bartstc/vite-ts-react-template

    Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications.

    122 GitHub starsUsed in 14 repos~1.9k tokens
    DevOps & CloudAuto-check passed
  • Nushell

    ccusage/ccusage

    Guides ccusage Nushell scripts. An agent skill from ccusage/ccusage.

    19k GitHub stars~938 tokensUpdated today
    DevOps & CloudAuto-check passed
  • Scheduled CI skill that scans a repository for small, certain docs, test and code hygiene issues and fixes them on one branch with a commit per finding.

    28k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Senior DevOps Toolkit

    maslennikov-ig/claude-code-orchestrator-kit

    Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…

    260 GitHub starsUsed in 6 repos~1.1k tokens
    DevOps & CloudAuto-check: notes
  • CI Failure Triage and Repair

    Chachamaru127/claude-code-harness

    Diagnoses failing CI pipelines and tests, deciding first whether the test or the implementation is at fault, and hands hard cases to a dedicated fixer subagent.

    3.2k GitHub starsUsed in 1 repo~1.1k tokens
    DevOps & CloudAuto-check: notes

More from fullsend-ai/fullsend

All 15 skills in this repo
  • Cutting Releases

    fullsend-ai/fullsend

    A skill your agent uses when the user wants to tag a release, cut a release candidate, or ship a new version.

    149 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Topissues

    fullsend-ai/fullsend

    Build a merged RICE priority table: top unassigned backlog issues plus issues assigned to the current user.

    149 GitHub stars~523 tokensUpdated today
    Auto-check passed
  • User Forum Whats New

    fullsend-ai/fullsend

    A skill your agent uses when preparing the Fullsend user forum "What's New" agenda, a Tuesday-to-Tuesday recap, forum-host talk-track notes, or copy-paste HTML of shipped changes for users.

    149 GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Adr Corner

    fullsend-ai/fullsend

    Find open GitHub pull requests that add or change Architecture Decision Records and report attribution, summaries, discussion points, and dates.

    149 GitHub stars~654 tokensUpdated today
    Auto-check passed
  • Nextwork

    fullsend-ai/fullsend

    Build a readiness-oriented queue of open issues/PRs — assigned work plus their open GitHub blockers — and recommend the next action for each.

    149 GitHub stars~5.3k tokensUpdated today
    Auto-check passed
  • Analyze Transcript

    fullsend-ai/fullsend

    Analyze fullsend agent run transcripts from GitHub Actions artifacts.

    149 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Replay Session

What does Replay Session do?

A skill your agent uses when the user wants to replay a Claude Code session from a GitHub Actions artifact link. Replay Session is an agent skill from fullsend-ai/fullsend. Use when the user wants to replay a Claude Code session from a GitHub Actions artifact link.

When should I use Replay Session?

Replay Session fits situations like: the user wants to replay a Claude Code session from a GitHub Actions artifact link; tasks that involve CI/CD; tasks that involve HTML artifacts.

How do I install Replay Session in Claude Code?

Run `npx skills add fullsend-ai/fullsend --skill replay-session -a claude-code`. Or copy the skill folder (skills/replay-session in fullsend-ai/fullsend) into .claude/skills/replay-session in your project. Claude Code loads it when a task matches its description.

How do I install Replay Session in Codex?

Run `npx skills add fullsend-ai/fullsend --skill replay-session -a codex`. Or copy the skill folder (skills/replay-session in fullsend-ai/fullsend) into .agents/skills/replay-session in your project. Codex loads it when a task matches its description.

Can I use Replay Session in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fullsend-ai/fullsend --skill replay-session -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/replay-session, .gemini/skills/replay-session, .github/skills/replay-session and .opencode/skills/replay-session in your project.

What does Replay Session need to run?

Going by SKILL.md and its folder, Replay Session needs the command-line tools its instructions call (gh and npm). Our summary lists: Node.js. Compatibility (from SKILL.md): Requires claude-replay (npm install -g claude-replay) and gh CLI authenticated with access to the target repository.

Does Replay Session access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Replay Session safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Replay Session use?

Replay Session is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Replay Session use?

About 884 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Replay Session?

Skills that share tags, products or a category with Replay Session: Analyze GitHub Action Logs (withastro/astro, 63k stars), GitHub Actions Templates (bartstc/vite-ts-react-template, 122 stars), Nushell (ccusage/ccusage, 19k stars) and Repo Hygiene Scan and Fix (QwenLM/qwen-code, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Replay Session?

fullsend-ai (a GitHub organization) maintains it in fullsend-ai/fullsend, which has 149 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.

Source: fullsend-ai/fullsend on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.