New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Compound Learnings

by parcadei in parcadei/Continuous-Claude-v3

Transform session learnings into permanent capabilities (skills, rules, agents).

MITAuto-check: notes

Install Compound Learnings

skills CLI
$ npx skills add parcadei/Continuous-Claude-v3 --skill compound-learnings -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install parcadei/Continuous-Claude-v3 compound-learnings --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/compound-learnings .claude/skills/compound-learnings && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
compound-learnings
GitHub stars
3.9k
Used in
1 other repo
Token cost
~1.6k tokens
SKILL.md length
439 words
Files
1
Skills in repo
141
Repo updated
First seen
Licence
MIT

At a glance

Transform session learnings into permanent capabilities (skills, rules, agents).

  • Works in 8 steps: Gather Learnings → Extract Patterns (Structured) → Detect Meta-Patterns → …
  • Asked to improve setup
  • SKILL.md covers When to Use, Process, Quality Checks and Files Reference
  • Calls node

What it does

Compound Learnings is an agent skill from parcadei/Continuous-Claude-v3. Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. The licence is MIT.

When your agent uses it

  • Asked to improve setup
  • Learn from sessions
  • Compound learnings
  • What patterns should become skills

Example prompts

  • “improve setup”
  • “learn from sessions”
  • “compound learnings”
  • “/compound-learnings”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Gather Learnings
  2. Extract Patterns (Structured)
  3. Detect Meta-Patterns
  4. Categorize (Decision Tree)
  5. Apply Signal Thresholds
  6. Propose Artifacts
  7. Create Approved Artifacts
  8. Summary Report

What it can do on your machine

Read from SKILL.md and the folder at commit d07ff4b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Write
    • Edit
    • Bash
    • AskUserQuestion

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Compound Learnings loads about 1.6k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 439 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from parcadei/Continuous-Claude-v3 at commit d07ff4b, republished under its MIT licence (© parcadei). 439 words, ~1,604 tokens.

Download SKILL.mdSave it as .claude/skills/compound-learnings/SKILL.md (or your agent's skills folder).
name
compound-learnings
description
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
allowed-tools
Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion

Compound Learnings

Transform ephemeral session learnings into permanent, compounding capabilities.

When to Use

  • "What should I learn from recent sessions?"
  • "Improve my setup based on recent work"
  • "Turn learnings into skills/rules"
  • "What patterns should become permanent?"
  • "Compound my learnings"

Process

Step 1: Gather Learnings
bash
# List learnings (most recent first)
ls -t $CLAUDE_PROJECT_DIR/.claude/cache/learnings/*.md | head -20

# Count total
ls $CLAUDE_PROJECT_DIR/.claude/cache/learnings/*.md | wc -l

Read the most recent 5-10 files (or specify a date range).

Step 2: Extract Patterns (Structured)

For each learnings file, extract entries from these specific sections:

Section HeaderWhat to Extract
## Patterns or Reusable techniquesDirect candidates for rules
**Takeaway:** or **Actionable takeaway:**Decision heuristics
## What WorkedSuccess patterns
## What FailedAnti-patterns (invert to rules)
## Key DecisionsDesign principles

Build a frequency table as you go:

markdown
| Pattern | Sessions | Category |
|---------|----------|----------|
| "Check artifacts before editing" | abc, def, ghi | debugging |
| "Pass IDs explicitly" | abc, def, ghi, jkl | reliability |
Step 2b: Consolidate Similar Patterns

Before counting, merge patterns that express the same principle:

Example consolidation:

  • "Artifact-first debugging"
  • "Verify hook output by inspecting files"
  • "Filesystem-first debugging" → All express: "Observe outputs before editing code"

Use the most general formulation. Update the frequency table.

Step 3: Detect Meta-Patterns

Critical step: Look at what the learnings cluster around.

If >50% of patterns relate to one topic (e.g., "hooks", "tracing", "async"): → That topic may need a dedicated skill rather than multiple rules → One skill compounds better than five rules

Ask yourself: "Is there a skill that would make all these rules unnecessary?"

Step 4: Categorize (Decision Tree)

For each pattern, determine artifact type:

Is it a sequence of commands/steps?
  → YES → SKILL (executable > declarative)
  → NO ↓

Should it run automatically on an event (SessionEnd, PostToolUse, etc.)?
  → YES → HOOK (automatic > manual)
  → NO ↓

Is it "when X, do Y" or "never do X"?
  → YES → RULE
  → NO ↓

Does it enhance an existing agent workflow?
  → YES → AGENT UPDATE
  → NO → Skip (not worth capturing)

Artifact Type Examples:

PatternTypeWhy
"Run linting before commit"Hook (PreToolUse)Automatic gate
"Extract learnings on session end"Hook (SessionEnd)Automatic trigger
"Debug hooks step by step"SkillManual sequence
"Always pass IDs explicitly"RuleHeuristic
Show full SKILL.md (183 more words)Show less
Step 5: Apply Signal Thresholds
OccurrencesAction
1Note but skip (unless critical failure)
2Consider - present to user
3+Strong signal - recommend creation
4+Definitely create
Step 6: Propose Artifacts

Present each proposal in this format:

markdown
---

## Pattern: [Generalized Name]

**Signal:** [N] sessions ([list session IDs])

**Category:** [debugging / reliability / workflow / etc.]

**Artifact Type:** Rule / Skill / Agent Update

**Rationale:** [Why this artifact type, why worth creating]

**Draft Content:**
\`\`\`markdown
[Actual content that would be written to file]
\`\`\`

**File:** `.claude/rules/[name].md` or `.claude/skills/[name]/SKILL.md`

---

Use AskUserQuestion to get approval for each artifact (or batch approval).

Step 7: Create Approved Artifacts
For Rules:
bash
# Write to rules directory
cat > $CLAUDE_PROJECT_DIR/.claude/rules/<name>.md << 'EOF'
# Rule Name

[Context: why this rule exists, based on N sessions]

## Pattern
[The reusable principle]

## DO
- [Concrete action]

## DON'T
- [Anti-pattern]

## Source Sessions
- [session-id-1]: [what happened]
- [session-id-2]: [what happened]
EOF
For Skills:

Create .claude/skills/<name>/SKILL.md with:

  • Frontmatter (name, description, allowed-tools)
  • When to Use
  • Step-by-step instructions (executable)
  • Examples from the learnings

Add triggers to skill-rules.json if appropriate.

For Hooks:

Create shell wrapper + TypeScript handler:

bash
# Shell wrapper
cat > $CLAUDE_PROJECT_DIR/.claude/hooks/<name>.sh << 'EOF'
#!/bin/bash
set -e
cd "$CLAUDE_PROJECT_DIR/.claude/hooks"
cat | node dist/<name>.mjs
EOF
chmod +x $CLAUDE_PROJECT_DIR/.claude/hooks/<name>.sh

Then create src/<name>.ts, build with esbuild, and register in settings.json:

json
{
  "hooks": {
    "EventName": [{
      "hooks": [{
        "type": "command",
        "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/<name>.sh"
      }]
    }]
  }
}
For Agent Updates:

Edit existing agent in .claude/agents/<name>.md to add the learned capability.

Step 8: Summary Report
markdown
## Compounding Complete

**Learnings Analyzed:** [N] sessions
**Patterns Found:** [M]
**Artifacts Created:** [K]

### Created:
- Rule: `explicit-identity.md` - Pass IDs explicitly across boundaries
- Skill: `debug-hooks` - Hook debugging workflow

### Skipped (insufficient signal):
- "Pattern X" (1 occurrence)

**Your setup is now permanently improved.**

Quality Checks

Before creating any artifact:

  1. Is it general enough? Would it apply in other projects?
  2. Is it specific enough? Does it give concrete guidance?
  3. Does it already exist? Check .claude/rules/ and .claude/skills/ first
  4. Is it the right type? Sequences → skills, heuristics → rules

Files Reference

  • Learnings: .claude/cache/learnings/*.md
  • Skills: .claude/skills/<name>/SKILL.md
  • Rules: .claude/rules/<name>.md
  • Hooks: .claude/hooks/<name>.sh + src/<name>.ts + dist/<name>.mjs
  • Agents: .claude/agents/<name>.md
  • Skill triggers: .claude/skills/skill-rules.json
  • Hook registration: .claude/settings.json → hooks section

© parcadei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/compound-learnings of parcadei/Continuous-Claude-v3.

Open the folder on GitHubat commit d07ff4b

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in parcadei/Continuous-Claude-v3, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Compound Learnings next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Compound Learnings compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Compound Learnings this skillparcadei/Continuous-Claude-v33.9k1 repos~1.6kAutomated safety check: NotesMIT
Learning to Learn (OpenMAIC)THU-MAIC/OpenMAIC40k—~502Automated safety check: PassMIT
Transformers JSsickn33/agentic-awesome-skills47k1 repos~444Automated safety check: PassApache-2.0
Compound Learning WriterEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT
Compound Learnings RefreshEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT
TransformersK-Dense-AI/scientific-agent-skills48k1 repos~2.8kAutomated safety check: NotesApache-2.0

Similar skills

  • Learning to Learn (OpenMAIC)

    THU-MAIC/OpenMAIC

    A Chinese-language skill that embeds learning strategies like retrieval practice and self-explanation as a parallel goal inside an OpenMAIC subject lesson, without making study skills the topic.

    40k GitHub stars~502 tokensUpdated today
    EducationAuto-check passed

  • Transformers JS

    sickn33/agentic-awesome-skills

    Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript.

    47k GitHub starsUsed in 1 repo~444 tokens
    AI & LLM EngineeringAuto-check passed

  • Compound Learning Writer

    EveryInc/compound-engineering-plugin

    Records one solved and verified problem as a durable learning in the repository, but only when the reasoning is not already clear from the final code, tests or docs.

    25k GitHub stars~2k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Compound Learnings Refresh

    EveryInc/compound-engineering-plugin

    Audits a repo's stored learnings against the current codebase, fixes stale, overlapping or superseded docs and reports on every document.

    25k GitHub stars~2k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Transformers

    K-Dense-AI/scientific-agent-skills

    Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks.

    48k GitHub starsUsed in 1 repo~2.8k tokens
    AI & LLM EngineeringAuto-check: notes

  • Scikit Learn

    K-Dense-AI/scientific-agent-skills

    Supports machine learning in Python with scikit-learn. An agent skill from K-Dense-AI/scientific-agent-skills.

    48k GitHub starsUsed in 1 repo~3.3k tokens
    Data & AnalyticsAuto-check: notes

More from parcadei/Continuous-Claude-v3

All 141 skills in this repo

  • Debug Hooks

    parcadei/Continuous-Claude-v3

    Systematic hook debugging workflow. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~863 tokens
    Auto-check: notes

  • Tldr Deep

    parcadei/Continuous-Claude-v3

    Full 5-layer analysis of a specific function. An agent skill from parcadei/Continuous-Claude-v3.

    3.9k GitHub starsUsed in 1 repo~677 tokens
    Auto-check passed

  • Gradient Methods

    parcadei/Continuous-Claude-v3

    Problem-solving strategies for gradient methods in optimization

    3.9k GitHub starsUsed in 2 repos~1k tokens
    Auto-check: notes

  • Math

    parcadei/Continuous-Claude-v3

    Unified math capabilities - computation, solving, and explanation.

    3.9k GitHub starsUsed in 2 repos~1.6k tokens
    Auto-check: notes

  • Math Model Selector

    parcadei/Continuous-Claude-v3

    Routes problems to appropriate mathematical frameworks using expert heuristics

    3.9k GitHub starsUsed in 2 repos~841 tokens
    Auto-check passed

  • Agentica Claude Proxy

    parcadei/Continuous-Claude-v3

    Guide for integrating Agentica SDK with Claude Code CLI proxy

    3.9k GitHub starsUsed in 1 repo~1k tokens
    Auto-check: notes

Questions about Compound Learnings

What does Compound Learnings do?

Transform session learnings into permanent capabilities (skills, rules, agents). Compound Learnings is an agent skill from parcadei/Continuous-Claude-v3. Transform session learnings into permanent capabilities (skills, rules, agents).

When should I use Compound Learnings?

Compound Learnings fits situations like: asked to improve setup; learn from sessions; compound learnings; what patterns should become skills.

How do I install Compound Learnings in Claude Code?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill compound-learnings -a claude-code`. Or copy the skill folder (.claude/skills/compound-learnings in parcadei/Continuous-Claude-v3) into .claude/skills/compound-learnings in your project. Claude Code loads it when a task matches its description.

How do I install Compound Learnings in Codex?

Run `npx skills add parcadei/Continuous-Claude-v3 --skill compound-learnings -a codex`. Or copy the skill folder (.claude/skills/compound-learnings in parcadei/Continuous-Claude-v3) into .agents/skills/compound-learnings in your project. Codex loads it when a task matches its description.

Can I use Compound Learnings in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add parcadei/Continuous-Claude-v3 --skill compound-learnings -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compound-learnings, .gemini/skills/compound-learnings, .github/skills/compound-learnings and .opencode/skills/compound-learnings in your project.

What does Compound Learnings need to run?

Going by SKILL.md and its folder, Compound Learnings needs the command-line tools its instructions call (node). Its frontmatter pre-approves these tools: Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion.

Does Compound Learnings access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Compound Learnings safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Compound Learnings use?

Compound Learnings is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Compound Learnings use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Compound Learnings?

Skills that share tags, products or a category with Compound Learnings: Learning to Learn (OpenMAIC) (THU-MAIC/OpenMAIC, 40k stars), Transformers JS (sickn33/agentic-awesome-skills, 47k stars), Compound Learning Writer (EveryInc/compound-engineering-plugin, 25k stars) and Compound Learnings Refresh (EveryInc/compound-engineering-plugin, 25k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Compound Learnings?

parcadei (a GitHub user) maintains it in parcadei/Continuous-Claude-v3, which has 3,943 GitHub stars. The repository holds 141 skills in this directory. The repository was last updated on January 26, 2026.

Source: parcadei/Continuous-Claude-v3 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.