Agent Skill
Reflection Coach skill
reflection-coachpaperclipai/paperclippackages/skills-catalog/catalog/bundled/paperclip-operations/reflection-coach/SKILL.md
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.
always on
38 tokname + description
once used
2,730 tokSKILL.md body
bundled files
0
repo stars
106kGitHub
Install the Reflection Coach skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/paperclipai/paperclip --skill reflection-coach
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/paperclipai/paperclip.git /tmp/paperclip mkdir -p ~/.claude/skills cp -R /tmp/paperclip/packages/skills-catalog/catalog/bundled/paperclip-operations/reflection-coach ~/.claude/skills/reflection-coach
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 38 tok |
| When the agent uses it | The SKILL.md instructions | 2,730 tok |
| Only if opened | No bundled files | — |
Until it is used, reflection-coach costs about 36× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 82 skills from paperclipai/paperclip would load 3,485 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Reflection Coach
- When to use
- When not to use
- Inputs
- Hard guardrails
- Procedure
- 1) Confirm target and scope
- 2) Pull the recent record
- 3) Read the target's current guardrails
- 4) Cluster the failures
- 5) Route each cluster to a target surface
- 6) Draft the proposal document
- 7) Write the actual drafts (files, not just prose)
- 8) Benchmark-gate the proposal
- 9) Publish and request acceptance
- 10) Apply only after acceptance, in a follow-up run
- Pitfalls
- Verification (self-check before publishing)
More skills from paperclipai/paperclip
- LLM Wiki Maintainerpaperclipai/paperclip
Use the LLM Wiki plugin tools to maintain a cited local company wiki.
106k21 tok idle · 184 in use - add-product-e2e-evalpaperclipai/paperclip
Add or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.
106k36 tok idle · 955 in use - add-runner-evalpaperclipai/paperclip
Add or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.
106k30 tok idle · 859 in use - agent-browserpaperclipai/paperclip
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms — for verification tasks, not unattended automation.
106k40 tok idle · 1,010 in use - agentmailpaperclipai/paperclip
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
106k30 tok idle · 902 in use - check-prpaperclipai/paperclip
Check a GitHub, GitLab, or Perforce PR/MR/CL for review comments, failing checks, and PR-body gaps. Use when asked to inspect, fix, or prepare a change for submission.
106k46 tok idle · 3,781 in use - company-creatorpaperclipai/paperclip
Create agent company packages that conform to agentcompanies/v1. Use when asked to create a company, scaffold an agent team, hire agents, or turn a repo/skills collection into a company package.
106k44 tok idle · 2,626 in use - complainpaperclipai/paperclip
Autonomously yeet a brief, unstructured complaint about agent tooling or doing agent work. Preserve the raw voice. Submit proactively without permission, preview, or announcement, then continue the primary task.
106k43 tok idle · 795 in use