orca-replay SKILL.md skillA

orca-replay from davepoon/buildwithclaude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add davepoon/buildwithclaude/orca-replay@git:20260915.d1cc3fd

Pins git:20260915.d1cc3fd in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
davepoon/buildwithclaude
Path
plugins/all-skills/skills/orca-replay/SKILL.md
Versions recorded
1
Latest version
git:20260915.d1cc3fd, committed Sep 15, 2026
Size
4,165 bytes
Repository stars
3,724
License
MIT

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.

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

# OrcaReplay Run Reader

Coding agents are confidently wrong about their own history. A summary written from memory is
missing the tool results, the exit codes, and the files that changed without anyone mentioning
them.

This skill enforces one rule: **when a question is about something that already happened, read the
trace before answering.** Do not reconstruct it. If a recording exists, guessing is the wrong move
even when the guess would have been right.

## When to Use This Skill

- "Why did you delete / overwrite / move X?"
- "What changed this file?" or "Which step broke the build?"
- "Can you reproduce yesterday's failure?"
- "Would a different model have got this right?"

## What This Skill Does

1. **Finds the run** — `orca_list_runs`, newest first, naming the run each fork came from.
2. **Narrows to the cause** — `orca_graph` with `to: <event seq>` returns only the chain that
   produced one event. That is the shape of an answer to *why*; the full timeline
   (`orca_show_run`) is the shape of an answer to *what*.
3. **Separates evidence from inference** — every edge is labelled `recorded` (the recorder watched
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add davepoon/buildwithclaude/orca-replay@sha256:a92b194acc6ac875

The line at the top of this page pins the label git:20260915.d1cc3fd, 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_tr2d2flmsqoubivu.svg)](https://markdownregistry.com/a/art_tr2d2flmsqoubivu)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 15, 2026.

versioncommittedcommitsizeaudit
git:20260915.d1cc3fd latest2026-09-15 d1cc3fd 4,165 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 (4165 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

davepoon/buildwithclaude · 3,724 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tr2d2flmsqoubivu
GET https://markdownregistry.com/api/v1/resolve?ref=davepoon/buildwithclaude/orca-replay
GET https://markdownregistry.com/api/v1/blob/a92b194acc6ac8753fc80a0deb4bdafb8350d01caa25ae86263446f51c826973

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 davepoon/buildwithclaude

code-health SKILL.md skill
davepoon/buildwithclaude · plugins/agent-triforce/skills/code-health/SKILL.md · Scans the codebase for dead code, tech debt, outdated dependencies, and code quality issues. Delegates to the Centinela…
git:20260307.756e327 · audit A · 3,724 stars
feature-spec SKILL.md skill
davepoon/buildwithclaude · plugins/agent-triforce/skills/feature-spec/SKILL.md · Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to…
git:20260307.756e327 · audit A · 3,724 stars
implement-feature SKILL.md skill
davepoon/buildwithclaude · plugins/agent-triforce/skills/implement-feature/SKILL.md · Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to…
git:20260307.756e327 · audit A · 3,724 stars
release-check SKILL.md skill
davepoon/buildwithclaude · plugins/agent-triforce/skills/release-check/SKILL.md · Pre-release verification checklist. Validates features, tests, docs, security, and quality gates before shipping…
git:20260307.756e327 · audit A · 3,724 stars
review-findings SKILL.md skill
davepoon/buildwithclaude · plugins/agent-triforce/skills/review-findings/SKILL.md · Addresses and fixes findings from a QA code review. Reads the review report, fixes critical and warning issues, and…
git:20260307.756e327 · audit A · 3,724 stars
security-audit SKILL.md skill
davepoon/buildwithclaude · plugins/agent-triforce/skills/security-audit/SKILL.md · Deep security audit covering OWASP Top 10, authentication, authorization, data protection, dependency vulnerabilities…
git:20260307.756e327 · audit A · 3,724 stars
uctm-init SKILL.md skill
davepoon/buildwithclaude · plugins/agents-uc-taskmanager/skills/init/SKILL.md · Initialize uc-taskmanager for the current project. Creates works/ directory and configures Bash permissions in…
git:20260328.6a2bce8 · audit A · 3,724 stars
sdd-pipeline SKILL.md skill
davepoon/buildwithclaude · plugins/agents-uc-taskmanager/skills/sdd-pipeline/SKILL.md
git:20260328.7298433 · audit C · 3,724 stars
work-pipeline SKILL.md skill
davepoon/buildwithclaude · plugins/agents-uc-taskmanager/skills/work-pipeline/SKILL.md · Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use…
git:20260328.7298433 · audit A · 3,724 stars
work-status SKILL.md skill
davepoon/buildwithclaude · plugins/agents-uc-taskmanager/skills/work-status/SKILL.md · Shows WORK progress and TASK status. Use when the user asks about WORK list, WORK progress, TASK status, or pipeline…
git:20260328.7298433 · audit A · 3,724 stars
close SKILL.md skill
davepoon/buildwithclaude · plugins/aigent-os/skills/close/SKILL.md · Commit the session to durable vault memory and prepare a clean resume point
git:20260711.3c94e0c · audit A · 3,724 stars
open SKILL.md skill
davepoon/buildwithclaude · plugins/aigent-os/skills/open/SKILL.md · Boot the session, load context from the vault, and surface what matters
git:20260711.3c94e0c · audit A · 3,724 stars

Every file in davepoon/buildwithclaude

Other files named orca-replay

orca-replay SKILL.md skill
iflytek/skillhub · builtin-skills/skills/orca-replay/SKILL.md · Answers questions about a past agent run from its recording rather than from memory, and replays or forks that run. Use…
v1.0.0 · audit A · 5,373 stars
orca-replay SKILL.md skill
mxyhi/ok-skills · orca-replay/SKILL.md · Answer questions about an earlier agent run from its recording rather than from memory, and replay or fork that run…
git:20261018.6c7e207 · audit A · 510 stars

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