learn

Name: learn
Author: giuseppe-trisciuoglio

1.2kinstalls36forks

How to install learn?

giuseppe-trisciuoglio/developer-kit/learn

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill learn

Installs into the current project.

Summary

Provides autonomous project pattern learning by analyzing the codebase to discover development conventions, architectural patterns, and coding standards, then generates project rule files in .claude/rules/. Use when user asks to "learn from project", "extract project rules", "ana

Files · 1

View on GitHub

SKILL.md

1	# Learn
2
3	Autonomously analyzes a project's codebase to discover development patterns, conventions, and architectural decisions, then generates project rule files in `.claude/rules/` for Claude Code to follow.
4
5	## Overview
6
7	This skill acts as the Orchestrator in a two-agent architecture. It coordinates the overall workflow: gathering project context, delegating deep analysis to the `learn-analyst` sub-agent, filtering and ranking results, presenting findings to the user, and persisting approved rules to `.claude/rules/`.
8
9	The separation of concerns ensures the analyst operates with a focused forensic prompt while the orchestrator manages user interaction and file persistence.
10
11	## When to Use
12
13	Use this skill when:
14
15	- User asks to "learn from this project" or "understand project conventions"
16	- User wants to auto-generate `.claude/rules/` files from the existing codebase
17	- User asks to "extract project rules" or "discover patterns"
18	- User wants Claude Code to learn the project's coding standards
19	- After joining a new project and wanting to codify existing conventions
20	- Before starting a large feature to ensure Claude follows project patterns
21
22	Trigger phrases: "learn from project", "extract rules", "analyze conventions", "discover patterns", "generate project rules", "learn codebase", "auto-generate rules"
23
24	## Instructions
25
26	### Phase 1: Project Context Assessment
27
28	Before delegating to the analyst, gather high-level project context:
29
30	1. Verify project root: Confirm the current working directory is a project root (has `package.json`, `pom.xml`, `pyproject.toml`, `go.mod`, `.git/`, or similar markers)
31
32	2. Check existing rules: Scan for pre-existing rule files to understand what is already documented:
33
34	```bash
35	# Check for existing rules
36	ls -la .claude/rules/ 2>/dev/null \|\| echo "No .claude/rules/ directory found"
37	cat CLAUDE.md 2>/dev/null \|\| echo "No CLAUDE.md found"
38	cat AGENTS.md 2>/dev/null \|\| echo "No AGENTS.md found"
39	ls -la .cursorrules 2>/dev/null \|\| echo "No .cursorrules found"
40	```
41
42	3. Assess project size: Get a quick overview of the project scope:
43
44	```bash
45	# Quick project overview
46	find . -maxdepth 1 -type f -name ".json" -o -name ".toml" -o -name ".xml" -o -name ".gradle" -o -name "Makefile" -o -name ".yaml" -o -name "*.yml" \| head -20
47	find . -type f -name ".ts" -o -name ".js" -o -name ".java" -o -name ".py" -o -name ".go" -o -name ".php" \| wc -l
48	```
49
50	4. Inform the user: Briefly tell the user what you found and that you are about to start analysis:
51	- "I found a [TypeScript/NestJS] project with [N] source files and [M] existing rules. Starting deep analysis..."
52
53	### Phase 2: Delegate to Analyst Sub-Agent
54
55	Invoke the `learn-analyst` sub-agent to perform the deep codebase analysis.
56
57	Use the Task tool to delegate analysis to the `learn-analyst` agent:
58
59	- Agent: `learn-analyst`
60	- Prompt: "Analyze the codebase in the current working directory. Follow your full process: discovery, pattern extraction, classification, and prioritization. Return your findings as a JSON report."
61	- Mode: Run synchronously to receive the JSON report directly
62
63	The analyst will return a structured JSON report with classified findings.
64
65	### Phase 3: Review and Filter Results
66
67	Process the analyst's report:
68
69	1. Parse the JSON report returned by the analyst
70	2. Validate findings: Ensure each finding has:
71	- A clear title
72	- Evidence from at least 2 files
73	- Impact score ≥ 4 (discard low-impact findings)
74	- Well-formed markdown content
75	3. Deduplicate against existing rules: Compare each finding title and content against existing `.claude/rules/` files. Skip findings that duplicate existing rules.
76	4. Select top 3: From the remaining findings, select the top 3 by impact score. If fewer than 3 remain after filtering, present whatever is left.
77	5. If zero findings remain: Inform the user that the project is already well-documented or no significant undocumented patterns were found.
78
79	### Phase 4: Present to User
80
81	Present the filtered findings to the user in a clear, structured format:
82
83	```
84	I analyzed your codebase and found N patterns worth documenting as project rules:
85
86	1. [RULE] <Title> (Impact: X/10)
87	<One-line explanation>
88
89	2. [RULE] <Title> (Impact: X/10)
90	<One-line explanation>
91
92	3. [RULE] <Title> (Impact: X/10)
93	<One-line explanation>
94	```
95
96	Then ask the user for confirmation using AskUserQuestion:
97
98	- Present choices: "Save all N rules", "Le

People who liked this also viewed

6 picks

Type

learn

1.2kinstalls36forks

View on GitHub

How to install learn?

giuseppe-trisciuoglio/developer-kit/learn

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill learn

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Learn
2
3	Autonomously analyzes a project's codebase to discover development patterns, conventions, and architectural decisions, then generates project rule files in `.claude/rules/` for Claude Code to follow.
4
5	## Overview
6
7	This skill acts as the Orchestrator in a two-agent architecture. It coordinates the overall workflow: gathering project context, delegating deep analysis to the `learn-analyst` sub-agent, filtering and ranking results, presenting findings to the user, and persisting approved rules to `.claude/rules/`.
8
9	The separation of concerns ensures the analyst operates with a focused forensic prompt while the orchestrator manages user interaction and file persistence.
10
11	## When to Use
12
13	Use this skill when:
14
15	- User asks to "learn from this project" or "understand project conventions"
16	- User wants to auto-generate `.claude/rules/` files from the existing codebase
17	- User asks to "extract project rules" or "discover patterns"
18	- User wants Claude Code to learn the project's coding standards
19	- After joining a new project and wanting to codify existing conventions
20	- Before starting a large feature to ensure Claude follows project patterns
21
22	Trigger phrases: "learn from project", "extract rules", "analyze conventions", "discover patterns", "generate project rules", "learn codebase", "auto-generate rules"
23
24	## Instructions
25
26	### Phase 1: Project Context Assessment
27
28	Before delegating to the analyst, gather high-level project context:
29
30	1. Verify project root: Confirm the current working directory is a project root (has `package.json`, `pom.xml`, `pyproject.toml`, `go.mod`, `.git/`, or similar markers)
31
32	2. Check existing rules: Scan for pre-existing rule files to understand what is already documented:
33
34	```bash
35	# Check for existing rules
36	ls -la .claude/rules/ 2>/dev/null \|\| echo "No .claude/rules/ directory found"
37	cat CLAUDE.md 2>/dev/null \|\| echo "No CLAUDE.md found"
38	cat AGENTS.md 2>/dev/null \|\| echo "No AGENTS.md found"
39	ls -la .cursorrules 2>/dev/null \|\| echo "No .cursorrules found"
40	```
41
42	3. Assess project size: Get a quick overview of the project scope:
43
44	```bash
45	# Quick project overview
46	find . -maxdepth 1 -type f -name ".json" -o -name ".toml" -o -name ".xml" -o -name ".gradle" -o -name "Makefile" -o -name ".yaml" -o -name "*.yml" \| head -20
47	find . -type f -name ".ts" -o -name ".js" -o -name ".java" -o -name ".py" -o -name ".go" -o -name ".php" \| wc -l
48	```
49
50	4. Inform the user: Briefly tell the user what you found and that you are about to start analysis:
51	- "I found a [TypeScript/NestJS] project with [N] source files and [M] existing rules. Starting deep analysis..."
52
53	### Phase 2: Delegate to Analyst Sub-Agent
54
55	Invoke the `learn-analyst` sub-agent to perform the deep codebase analysis.
56
57	Use the Task tool to delegate analysis to the `learn-analyst` agent:
58
59	- Agent: `learn-analyst`
60	- Prompt: "Analyze the codebase in the current working directory. Follow your full process: discovery, pattern extraction, classification, and prioritization. Return your findings as a JSON report."
61	- Mode: Run synchronously to receive the JSON report directly
62
63	The analyst will return a structured JSON report with classified findings.
64
65	### Phase 3: Review and Filter Results
66
67	Process the analyst's report:
68
69	1. Parse the JSON report returned by the analyst
70	2. Validate findings: Ensure each finding has:
71	- A clear title
72	- Evidence from at least 2 files
73	- Impact score ≥ 4 (discard low-impact findings)
74	- Well-formed markdown content
75	3. Deduplicate against existing rules: Compare each finding title and content against existing `.claude/rules/` files. Skip findings that duplicate existing rules.
76	4. Select top 3: From the remaining findings, select the top 3 by impact score. If fewer than 3 remain after filtering, present whatever is left.
77	5. If zero findings remain: Inform the user that the project is already well-documented or no significant undocumented patterns were found.
78
79	### Phase 4: Present to User
80
81	Present the filtered findings to the user in a clear, structured format:
82
83	```
84	I analyzed your codebase and found N patterns worth documenting as project rules:
85
86	1. [RULE] <Title> (Impact: X/10)
87	<One-line explanation>
88
89	2. [RULE] <Title> (Impact: X/10)
90	<One-line explanation>
91
92	3. [RULE] <Title> (Impact: X/10)
93	<One-line explanation>
94	```
95
96	Then ask the user for confirmation using AskUserQuestion:
97
98	- Present choices: "Save all N rules", "Le

People who liked this also viewed

6 picks

Type