compound
Preserve a durable lesson without growing memory or policy unnecessarily.
Skill by arieldiaz
Chalk Labs
Need help deploying compound?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/arieldiaz-compound
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/compound
What's inside
- Skill name
compound- Description
- Preserve a durable lesson without growing memory or policy unnecessarily.
- License
- MIT
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Compound Use after a review or repeated observation reveals something likely to change future judgment. 1. Separate a durable fact or lesson from temporary conditions and trivia. 2. Search the current projection for the same lesson. Strengthen or replace it rather than adding a near-duplicate. 3. Append evidence with provenance, then update the smallest relevant projection. 4. If the lesson implies reusable agent behavior, propose a replacement in the owning framework or instance source. Do not store the rule in memory or create an agent-local skill. 5. Remove stale projection text when the new lesson supersedes it. Done when future context is more useful and no larger than necessary.
From arieldiaz/humanwareos, MIT.
More from arieldiaz/humanwareos
- 0.553score
observe
arieldiaz
Preserve a meaningful raw input as append-only evidence with minimal capture context.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
challenge
arieldiaz
Obtain a concise independent objection before a consequential decision or after a surprising result.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
decide
arieldiaz
Turn a framed choice into one decision and a small executable plan.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
act
arieldiaz
Execute clear work in complete slices and return verified results.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
review
arieldiaz
Compare an outcome with the original intent and identify useful lessons.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
rederive
arieldiaz
Rebuild a derived artifact from primary evidence for a new question or better method.
SkillBFreshness: B★ 3Claude Code +9 - 0.550score
orient
arieldiaz
Frame a non-trivial situation before choosing what to do.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- Sep 21, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/arieldiaz/humanwareos
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from arieldiaz
- 0.553score
observe
arieldiaz
Preserve a meaningful raw input as append-only evidence with minimal capture context.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
challenge
arieldiaz
Obtain a concise independent objection before a consequential decision or after a surprising result.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
decide
arieldiaz
Turn a framed choice into one decision and a small executable plan.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
act
arieldiaz
Execute clear work in complete slices and return verified results.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
review
arieldiaz
Compare an outcome with the original intent and identify useful lessons.
SkillBFreshness: B★ 3Claude Code +9 - 0.553score
rederive
arieldiaz
Rebuild a derived artifact from primary evidence for a new question or better method.
SkillBFreshness: B★ 3Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get compound running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
compound skill. Agent Mart. https://agentmart.dev/skills/arieldiaz-compound (last updated 2026-10-24)