/ase-code-insight
Give insights into the source code.
$ npx -y skills add rse/ase --skill ase-code-insight --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/ase-code-insight
Context preview
The summary Claude sees to decide when to auto-load this skill.
Give insights into the source code.
SKILL.md
ase-code-insight.SKILL.mdname: ase-code-insight
argument-hint: "[--help|-h] <code-references>"
description: >
Give insights into the source code.
user-invocable: true
disable-model-invocation: false
effort: high
allowed-tools:
- "Bash(git *)"
- "Bash(grep *)"
- "Bash(sort *)"
- "Bash(uniq *)"
- "Bash(head *)"
- "Bash(git log * | grep * | sort * | uniq * | sort * | head *)"
- "Agent"@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
<purpose name="ase-code-insight"> Project Insight </purpose>
<expand name="getopt" arg1="ase-code-insight"> $ARGUMENTS </expand>
<objective> Give *insights* into the project through the source code of <getopt-arguments/>. </objective>
<flow> 1. <step id="STEP 1: PROJECT ABSTRACT">
<if condition="<ase-project-boxing/> is equal `black`">
The project source artifacts are classified as a *black box*, so the user does *not* want them inspected or their internals surfaced. *Skip* the entire insight gathering: do *not* read any source, only output the following <template/> and then *SKIP* the remaining steps STEP 2 through STEP 4:
<template> <ase-tpl-bullet-normal/> **PROJECT INSIGHT**: *suppressed* (`project.boxing` is `black`) </template>
</if>
Determine an <abstract/> summary of this project. For this, check a potentially existing `README.*` file or scan the source files and figure it out indirectly.
Display the results with the following <template/>:
<template> <ase-tpl-bullet-normal/> **PROJECT ABSTRACT**:
<abstract/> </template> </step>
2. <step id="STEP 2: PROJECT AUTHOR"> Determine the <author/> of this project. For this, run the following command...
git shortlog -sn --no-merges HEAD
...and then display the results with the following <template/>:
<template> <ase-tpl-bullet-normal/> **PROJECT AUTHOR**:
<author/> </template> </step>
3. <step id="STEP 3: SOURCE CHURN"> Display the source files which caused the most churn by figuring out which source files have the most commits. Display the following <template/>:
<template> <ase-tpl-bullet-normal/> **SOURCE CHURN**: </template>
Then run the following command...
git log --format=format: --name-only --since="1 year ago" | grep -v '^$' | sort | uniq -c | sort -nr | head -10
...and then display its result as a table with a table head and columns named "Commits" and "Source File". Do not display any further explanation of this result. </step>
4. <step id="STEP 4: MODULE STRUCTURE"> Display the following <template/>:
<template> <ase-tpl-bullet-normal/> **MODULE STRUCTURE**: </template>
Find all modules (or OOP classes) and build a Mermaid specification <mermaid-spec/> for a `flowchart TB` diagram with all modules as boxes and the imports between modules as the directed edges. Then dispatch the rendering to the `ase-meta-diagram` sub-agent by calling the tool `Agent(description: "Diagram Rendering", subagent_type: "ase:ase-meta-diagram", prompt: <mermaid-spec/>, run_in_background: false)` and reproduce its returned fenced code block verbatim in the response text. Do not display any further explanation except for this diagram. </step> </flow>
Read more
name: ase-code-insight
argument-hint: "[--help|-h] <code-references>"
description: >
Give insights into the source code.
user-invocable: true
disable-model-invocation: false
effort: high
allowed-tools:
- "Bash(git *)"
- "Bash(grep *)"
- "Bash(sort *)"
- "Bash(uniq *)"
- "Bash(head *)"
- "Bash(git log * | grep * | sort * | uniq * | sort * | head *)"
- "Agent"@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
<purpose name="ase-code-insight"> Project Insight </purpose>
<expand name="getopt" arg1="ase-code-insight"> $ARGUMENTS </expand>
<objective> Give *insights* into the project through the source code of <getopt-arguments/>. </objective>
<flow> 1. <step id="STEP 1: PROJECT ABSTRACT">
<if condition="<ase-project-boxing/> is equal `black`">
The project source artifacts are classified as a *black box*, so the user does *not* want them inspected or their internals surfaced. *Skip* the entire insight gathering: do *not* read any source, only output the following <template/> and then *SKIP* the remaining steps STEP 2 through STEP 4:
<template> <ase-tpl-bullet-normal/> **PROJECT INSIGHT**: *suppressed* (`project.boxing` is `black`) </template>
</if>
Determine an <abstract/> summary of this project. For this, check a potentially existing `README.*` file or scan the source files and figure it out indirectly.
Display the results with the following <template/>:
<template> <ase-tpl-bullet-normal/> **PROJECT ABSTRACT**:
<abstract/> </template> </step>
2. <step id="STEP 2: PROJECT AUTHOR"> Determine the <author/> of this project. For this, run the following command...
git shortlog -sn --no-merges HEAD
...and then display the results with the following <template/>:
<template> <ase-tpl-bullet-normal/> **PROJECT AUTHOR**:
<author/> </template> </step>
3. <step id="STEP 3: SOURCE CHURN"> Display the source files which caused the most churn by figuring out which source files have the most commits. Display the following <template/>:
<template> <ase-tpl-bullet-normal/> **SOURCE CHURN**: </template>
Then run the following command...
git log --format=format: --name-only --since="1 year ago" | grep -v '^$' | sort | uniq -c | sort -nr | head -10
...and then display its result as a table with a table head and columns named "Commits" and "Source File". Do not display any further explanation of this result. </step>
4. <step id="STEP 4: MODULE STRUCTURE"> Display the following <template/>:
<template> <ase-tpl-bullet-normal/> **MODULE STRUCTURE**: </template>
Find all modules (or OOP classes) and build a Mermaid specification <mermaid-spec/> for a `flowchart TB` diagram with all modules as boxes and the imports between modules as the directed edges. Then dispatch the rendering to the `ase-meta-diagram` sub-agent by calling the tool `Agent(description: "Diagram Rendering", subagent_type: "ase:ase-meta-diagram", prompt: <mermaid-spec/>, run_in_background: false)` and reproduce its returned fenced code block verbatim in the response text. Do not display any further explanation except for this diagram. </step> </flow>
Repo: rse/ase
Other skills on ase.
- /hello
Show a nice greeting message with a timestamp. Use this, when the user wants to greet or say hello, optionally to a certain subject <subject> and in a certain language <language>.
Open skill - /ase-arch-analyze
Review software architecture, including package cohesion and inter-package coupling
Open skill - /ase-arch-discover
Discover additional, third-party components (libraries/frameworks) for the technology stack to provide needed functionality.
Open skill - /ase-code-analyze
Analyze the source code for problems in either the logic and semantics and its related control flow, performance and efficiency, or security.
Open skill - /ase-code-craft
Craft Source Code: Use when user wants to "create", "add", or "craft" a new feature from scratch.
Open skill - /ase-code-dissect
Dissect the current Git change set, treated as an epic, domain-wise and logically into cohesive parts and materialize each part in its own dedicated Git WorkTree. Use when the user calls to "dissect", "split", "break up", or "decompose" a large change set into atomic, separately
Open skill

