reflection-coach SKILL.md skillA

reflection-coach from paperclipai/paperclip is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add paperclipai/paperclip/reflection-coach@git:20260807.5da382f

Pins git:20260807.5da382f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
paperclipai/paperclip
Path
packages/skills-catalog/catalog/bundled/paperclip-operations/reflection-coach/SKILL.md
Versions recorded
3
Latest version
git:20260807.5da382f, committed Aug 7, 2026
First version recorded
Jul 9, 2026
Size
12,028 bytes
Repository stars
105,684
License
MIT

Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change. Use for evidence-backed coaching proposals, never hot-swaps.

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

# Reflection Coach

You are coaching another agent. You are **not** that agent. Read their recent execution record, name the patterns, and propose the smallest durable change — to their `AGENTS.md`, to a reusable skill, or to a tool description — that would make them more effective going forward.

This skill runs **on a target agent** and produces a reviewable proposal. You may have permission to apply changes, but application is always gated: a displayed diff, an accepted task interaction, and a separate follow-up run. You never propose and apply in the same run.

Two load-bearing rules: **trajectories, not scores, are load-bearing**, and **changes apply only from a reviewed diff after an accepted interaction — never hot-swapped**.

## When to use

- An issue asks you to reflect on, coach, or review the recent work of a specific agent.
- A routine (e.g. `recent-agent-reflection`) hands you a bounded set of agents to review.
- Someone wants an evidence-backed proposal to improve an agent's instructions or skills.

## When not to use

- The target agent id is your own. Refuse — no self-reflection.
- You are asked to rewrite product code or shared infra. That is out of scope.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add paperclipai/paperclip/reflection-coach@sha256:083d5fa8dc43c3ce

The line at the top of this page pins the label git:20260807.5da382f, 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_zl4tbdwe5wmi2c7e.svg)](https://markdownregistry.com/a/art_zl4tbdwe5wmi2c7e)

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

Versions

The registry has recorded 3 versions of this file, between Jul 9, 2026 and Aug 7, 2026, about one every 14 days.

versioncommittedcommitsizeaudit
git:20260807.5da382f latest2026-08-07 5da382f 12,028 BA view · diff
git:20260710.953b3152026-07-10 953b315 11,837 BA view · diff
git:20260709.8b6a06e2026-07-09 8b6a06e 11,903 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 (12028 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

paperclipai/paperclip · 105,684 stars · license MIT · pushed 2026-10-22 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_zl4tbdwe5wmi2c7e
GET https://markdownregistry.com/api/v1/resolve?ref=paperclipai/paperclip/reflection-coach
GET https://markdownregistry.com/api/v1/blob/083d5fa8dc43c3ce7747e89c1afb6f6f42d0603a31808bffc5f8e56735f2d865

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 paperclipai/paperclip

add-product-e2e-eval SKILL.md skill
paperclipai/paperclip · .agents/skills/add-product-e2e-eval/SKILL.md · Add or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or…
git:20260916.18989a9 · audit A · 105,684 stars
add-runner-eval SKILL.md skill
paperclipai/paperclip · .agents/skills/add-runner-eval/SKILL.md · Add or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance…
git:20260916.18989a9 · audit A · 105,684 stars
check-pr SKILL.md skill
paperclipai/paperclip · .agents/skills/check-pr/SKILL.md · Check a GitHub, GitLab, or Perforce PR/MR/CL for review comments, failing checks, and PR-body gaps. Use when asked to…
v1.3 · audit A · 105,684 stars
company-creator SKILL.md skill
paperclipai/paperclip · .agents/skills/company-creator/SKILL.md · Create agent company packages that conform to agentcompanies/v1. Use when asked to create a company, scaffold an agent…
git:20260710.953b315 · audit A · 105,684 stars
create-agent-adapter SKILL.md skill
paperclipai/paperclip · .agents/skills/create-agent-adapter/SKILL.md · Create or modify Paperclip agent adapters across server, UI, and CLI surfaces. Use when adding support for a new CLI…
git:20260914.f1d5786 · audit A · 105,684 stars
create-external-bot-integration SKILL.md skill
paperclipai/paperclip · .agents/skills/create-external-bot-integration/SKILL.md · Build and qualify external bots such as Dot in Paperclip. Use for two-way work, invitation, identity, wakeup, Runner…
git:20261013.69f4bfc · audit A · 105,684 stars
create-issue-interaction-ui SKILL.md skill
paperclipai/paperclip · .agents/skills/create-issue-interaction-ui/SKILL.md · Add a new Paperclip issue-thread interaction kind end-to-end. Use when repo work introduces or extends interaction…
git:20261012.88bf4c6 · audit A · 105,684 stars
create-paperclip-bundled-skill SKILL.md skill
paperclipai/paperclip · .agents/skills/create-paperclip-bundled-skill/SKILL.md · Turn an idea, tweet, or task into a skill in the Paperclip skills catalog (packages/skills-catalog). Use when asked to…
git:20260730.c62fa8d · audit A · 105,684 stars
create-verification-skill SKILL.md skill
paperclipai/paperclip · .agents/skills/create-verification-skill/SKILL.md · Generate a project-local verification skill that drives your app the way a user does — any language, framework, or…
git:20261012.7d9b93a · audit A · 105,684 stars
deal-with-security-advisory SKILL.md skill
paperclipai/paperclip · .agents/skills/deal-with-security-advisory/SKILL.md · Handle confidential GitHub Security Advisory response for Paperclip. Use when coordinating advisory triage…
git:20260710.953b315 · audit A · 105,684 stars
diagnose-why-work-stopped SKILL.md skill
paperclipai/paperclip · .agents/skills/diagnose-why-work-stopped/SKILL.md · Diagnose stalled, looping, or over-recovered Paperclip issue trees and propose a no-code product-rule plan. Use when…
git:20260710.953b315 · audit A · 105,684 stars
doc-maintenance SKILL.md skill
paperclipai/paperclip · .agents/skills/doc-maintenance/SKILL.md · Audit README, SPEC, and PRODUCT docs against recent git history for drift and make minimal PR-ready edits. Use when…
git:20260710.953b315 · audit A · 105,684 stars

Every file in paperclipai/paperclip

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