Agent skill · AI agents · Continuum-AI-Corp

orca-replay agent skill by Continuum-AI-Corp

Answers questions about a past agent run from its recording rather than memory, and replays or forks that run.

View on GitHub Read SKILL.md
Publisher
Continuum-AI-Corp
License
Apache-2.0
Cost
Free and open source
Installs via skills.sh
6
Bundled scripts
None
Credentials
None named
Outside hosts
None
MCP server
No
Security scan
Not scanned by the directory. Third-party audits on skills.sh
Listed since
October 19, 2026 or earlier
XLinkedIn

At a glance

PublisherContinuum-AI-Corp
Repositorygithub.com/Continuum-AI-Corp/OrcaReplay
CategoryAI Agents and LLM Engineering
TopicsAgent Tracing and Observability
CostFree and open source
CapabilitiesQuality badge, SKILL.md only, Declares compatibility, Runs commands
LicenseApache-2.0
Last commitOctober 1, 2026 (repository)
Listed sinceOctober 19, 2026 or earlier
SKILL.md200 lines, 1,910 words
Bundled files1 file
Quality score86/100 · B Passes all seven graded checks
Security scanNot scanned
README badgeGet the badges for this listing

Before you install

Read from the skill's files at the directory's October 22, 2026 assessment: what ships with it, what its code reads, and the terms it is published under.

Install orca-replay

The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.

Skills CLI
npx skills add https://github.com/Continuum-AI-Corp/OrcaReplay/tree/main/skills/orca-replay
Claude Code, project-level copy
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/Continuum-AI-Corp/OrcaReplay.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/orca-replay .claude/skills/
rm -rf "$tmp"
Codex, project-level copy
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/Continuum-AI-Corp/OrcaReplay.git "$tmp/repo"
mkdir -p .agents/skills
cp -R "$tmp/repo/"skills/orca-replay .agents/skills/
rm -rf "$tmp"

For a user-level install, copy the folder to ~/.claude/skills/ (Claude Code) or ~/.agents/skills/ (Codex). Inside Codex, $skill-installer can also fetch a skill from GitHub. New to skills? Read How to install agent skills in Claude Code, Codex and Cursor.

Continuum-AI-Corp/OrcaReplay is third-party code. Read SKILL.md and any bundled scripts before you install it.

Directory summary

orca-replay answers questions about a past agent run from its recording rather than memory, and replays or forks that run. Listed in AI Agents and LLM Engineering, it is built for Claude Code users working on AI agent and LLM engineering. It scores 86/100, grade B, on the Suede Skill Check, with full points for structural checks, recent maintenance and curated-list citations. Continuum-AI-Corp publishes it under Apache-2.0, an open-source or open-content license, so you can use and adapt it at no cost under those terms. It installs in Claude Code, Codex, Cursor and other agents that read the Agent Skills format.

How the author describes it

Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use when asked why an earlier run did something, or to reproduce a failure.

From the description field of SKILL.md. Agents read this line to decide when to load the skill.

Compatibility, from SKILL.md

CompatibilityRequires the `orcareplay` npm package (Node 20+) with its MCP server registered as `orca`, and at least one recorded run in the project's .orca/runs directory.

Sections in SKILL.md

Files in the skill folder

Suede Skill Check: 86/100 · B

Report snapshot · · graded-v2

The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.

Source revision: a9178ca26af9. Report version e2f4996d5c42. Badge URLs follow the latest listing; save the report to keep this version.

Download report · Request a fresh review

What to review next

  • Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
  • Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
  • Reference files: 0 of 3 points. 3 when the skill folder ships a references/, reference/ or docs/ folder.

Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.

orca-replay passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.

See the checks and points
CheckResult
Frontmatter parses and declares a name and a descriptionPass
Name uses lowercase letters, digits and hyphens, 64 characters or fewerPass
Name matches the skill's folder namePass
Description is between 50 and 1,024 charactersPass
Description says when an agent should use the skillPass
SKILL.md body is 500 lines or fewerPass
A license is declared in the frontmatter or the repositoryPass
Repository has a commit in the last 12 monthsPass
Score componentPoints
Structural checks56 of 56
Description length5 of 5
Boundary clause0 of 4
Example request0 of 3
Instruction depth7 of 7
Reference files0 of 3
Bundled scripts0 of 2
Recent maintenance9 of 9
Curated-list citations7 of 7
Tool permissions declared0 of 2
Compatibility declared2 of 2

Where this skill is cited

Continuum-AI-Corp/OrcaReplay appears in 4 curated lists: VoltAgent/awesome-agent-skills, heilcheng/awesome-agent-skills, hesreallyhim/awesome-claude-code, karanb192/awesome-claude-skills.

Strengths and open points

What it does well

  • Full points for structural checks (56 of 56).
  • Full points for recent maintenance (9 of 9).
  • Full points for instruction depth (7 of 7).
  • Full points for curated-list citations (7 of 7).
  • Full points for description length (5 of 5).
  • Full points for compatibility declared (2 of 2).
  • Its repository is cited by 4 curated lists.

What to check

  • Boundary clause: 0 of 4 points.
  • Example request: 0 of 3 points.
  • Reference files: 0 of 3 points.
  • Bundled scripts: 0 of 2 points.
  • Tool permissions declared: 0 of 2 points.
  • Security scan: not scanned by the directory. Read SKILL.md and any scripts before you install.

Reviews and ratings

Directory rating: 86/100 · B on the Suede Skill Check, computed from the skill's published files.

Used orca-replay? Reader reviews are published on GitHub as issues credited to their authors. They never change the score.

Write a review Read reviews of orca-replay

Questions and answers

What does orca-replay do?

Answers questions about a past agent run from its recording rather than memory, and replays or forks that run. It is listed in AI Agents and LLM Engineering on SuedeAI.directory.

Is orca-replay free?

Yes. Continuum-AI-Corp publishes orca-replay under Apache-2.0, an open-source or open-content license, and its files name no paid service, API key or hosted account.

How do I install orca-replay?

Run npx skills add https://github.com/Continuum-AI-Corp/OrcaReplay/tree/main/skills/orca-replay from your project, or copy the folder into .claude/skills/ for Claude Code or .agents/skills/ for Codex. The install section lists each route.

Does orca-replay need credentials, an MCP server or network access?

No. At the October 22, 2026 assessment its files read no credential, connect to no MCP server and call no outside host.

How good is orca-replay?

It scores 86/100, grade B, on the Suede Skill Check, which adds structure, description quality, instruction depth, bundled files, maintenance and curated-list citations from its published files.

What are alternatives to orca-replay?

Skills that share its topics include bmad-run-inspector from tronghieu/agent-skills, hn-summarize from ykdojo/claude-code-tips and agenttrace-session-audit from luoyuctl/agenttrace.

Similar skills

Skills from other publishers that share the most topics with orca-replay.

All AI agent and LLM engineering skills

Two badges for orca-replay

Suede Skill Check: 86/100Suede Skill Check: Grade B

Choose the numeric badge, the letter badge, or both. Each links to this skill’s Suede AI listing; either valid linked badge can qualify for the feature offer.

Markdown
[![Suede Skill Check: 86/100](https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/score.svg)](https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/)
[![Suede Skill Check: Grade B](https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/badge.svg)](https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/)
HTML
<a href="https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/"><img src="https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/score.svg" alt="Suede Skill Check: 86/100" width="160" height="175"></a>
<a href="https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/"><img src="https://suedeai.directory/continuum-ai-corp/orcareplay/orca-replay/badge.svg" alt="Suede Skill Check: Grade B" width="160" height="175"></a>

Suede Certified on the shield refers to this published structural quality check. Security scan: not scanned. Read the methodology.

Limited-time feature offer: Display either quality badge in your repository or skill README, linked to your listing, then request verification. Suede AI checks the rendered README at a recorded commit. Eligible skills scoring 80–99 with a verified badge can receive a featured placement while the offer is open. Request badge verification.

Publishers: read How to get your agent skill found in search and cited by AI assistants.