بنقرة واحدة
improve-skill
// Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.
// Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.
| name | improve-skill |
| description | Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history. |
This skill helps analyze coding agent sessions to improve or create skills. It is meant to work across the main local coding-agent CLIs you use, with examples for common setups such as pi, Claude Code, Codex, and Gemini when session logs are available.
Extract the current session and generate an improvement prompt:
# Auto-detect agent and extract current session
./scripts/extract-session.js
The extract-session.js script finds and parses session files from multiple agent CLIs:
# Auto-detect (uses most recent session for current working directory)
./scripts/extract-session.js
# Specify agent type
./scripts/extract-session.js --agent claude
./scripts/extract-session.js --agent pi
./scripts/extract-session.js --agent codex
# Specify a different working directory
./scripts/extract-session.js --cwd /path/to/project
# Use a specific session file
./scripts/extract-session.js /path/to/session.jsonl
Known session file locations:
~/.claude/projects/<encoded-cwd>/*.jsonl~/.pi/agent/sessions/<encoded-cwd>/*.jsonl~/.codex/sessions/YYYY/MM/DD/*.jsonlIf auto-detection misses the agent, pass the session file path explicitly.
When asked to improve a skill based on a session:
Extract the session transcript:
./scripts/extract-session.js > /tmp/session-transcript.txt
Find the existing skill in the relevant skill directory for the current agent or shared dotfiles repo. Common locations include:
~/.codex/skills/<skill-name>/SKILL.md~/.claude/skills/<skill-name>/SKILL.md~/.pi/agent/skills/<skill-name>/SKILL.md~/.../dot_agents/skills/<skill-name>/SKILL.mdGenerate an improvement prompt for a new session:
═══════════════════════════════════════════════════════════════════════════════
COPY THE FOLLOWING PROMPT INTO A NEW AGENT SESSION:
═══════════════════════════════════════════════════════════════════════════════
I need to improve the "<skill-name>" skill based on a session where I used it.
First, read the current skill at: <path-to-skill>
Then analyze this session transcript to understand:
- Where I struggled to use the skill correctly
- What information was missing from the skill
- What examples would have helped
- What I had to figure out on my own
<session_transcript>
<paste transcript here>
</session_transcript>
Based on this analysis, improve the skill by:
1. Adding missing instructions or clarifications
2. Adding examples for common use cases discovered
3. Fixing any incorrect guidance
4. Making the skill more concise where possible
Write the improved skill back to the same location.
═══════════════════════════════════════════════════════════════════════════════
When asked to create a new skill from a session:
Extract the session transcript:
./scripts/extract-session.js > /tmp/session-transcript.txt
Generate a creation prompt for a new session:
═══════════════════════════════════════════════════════════════════════════════
COPY THE FOLLOWING PROMPT INTO A NEW AGENT SESSION:
═══════════════════════════════════════════════════════════════════════════════
Analyze this session transcript to extract a reusable skill called "<skill-name>":
<session_transcript>
<paste transcript here>
</session_transcript>
Create a new skill that captures:
1. The core capability or workflow demonstrated
2. Key commands, APIs, or patterns used
3. Common pitfalls and how to avoid them
4. Example usage for typical scenarios
Write the skill to the appropriate shared or agent-specific skill path, for example: ~/.../dot_agents/skills/<skill-name>/SKILL.md
Use this format:
---
name: <skill-name>
description: "<one-line description>"
---
# <Skill Name> Skill
<overview and quick reference>
## <Section for each major capability>
<instructions and examples>
═══════════════════════════════════════════════════════════════════════════════
The improvement prompt is meant to be copied into a fresh coding-agent session because:
When analyzing a transcript, look for:
Keep skills concise - focus on the most important information and examples.
Reference for the features supported by presenterm, a terminal-based markdown slideshow tool. Use this skill whenever the user works with presenterm: building or editing a presenterm deck, asking which presenterm features/commands/themes exist, how slides/columns/code blocks/diagrams/images/themes/exports work, what a comment command does, or mentions "presenterm", "terminal slides", or "markdown presentation" rendered in the terminal. This skill documents what presenterm supports — it does not prescribe slide content, wording, or presentation design.
Convert an article, newsletter, or document into a short Kokoro-narrated audio read-up and upload it as a private episode to the user's "📥 Listen Later" Spotify show. ONLY trigger on explicit phrases like "listen later", "read-up", "save as audio for the commute", "add to my listen-later feed". Do NOT trigger on generic summarize, TTS, save-to-spotify, podcast, or cover-art requests — those route to the `save-to-spotify` skill.
Low-level provider web search via codex, claude-code, or openai-cli. Use only when user names ai-search/codex/claude/openai-cli search, compares providers, or wants native search; otherwise use web-search.
Default for web lookup/research/latest/current/URL/package/docs questions. Uses kagi→codex→claude-code→openai-cli→perplexity, escalating only if needed. Prefer this over provider skills unless user explicitly names kagi, perplexity, codex/claude-code/openai-cli, or ai-search.
Manage and deploy projects on exe.dev VMs. Use this whenever the user mentions exe.dev, exe.xyz hosts, `ssh exe.dev`, deploying Docker/GHCR apps to exe.dev, replacing or updating VMs, configuring exe.dev proxy/public access/custom domains, or setting up GitHub Actions/secrets/API tokens for exe.dev deployments.
Must read guide on creating/editing mermaid charts with valiation tools