Agent skill

Project Knowledge

by JanDeDobbeleer in JanDeDobbeleer/oh-my-posh

Accumulated project memory: verified gotchas and prior findings for oh-my-posh work.

MITAuto-check passedAgent Workflows

Install Project Knowledge

skills CLI
$ npx skills add JanDeDobbeleer/oh-my-posh --skill project-knowledge -a claude-code

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

GitHub CLI
$ gh skill install JanDeDobbeleer/oh-my-posh project-knowledge --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/JanDeDobbeleer/oh-my-posh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/project-knowledge .claude/skills/project-knowledge && 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
project-knowledge
GitHub stars
24k
Token cost
~748 tokens
SKILL.md length
302 words
Files
9 (incl. references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Accumulated project memory: verified gotchas and prior findings for oh-my-posh work.

  • Works in 3 steps: Identify which topics the task touches… → Read those reference files before… → Treat entries as point-in-time…
  • Tasks that involve Agent memory
  • SKILL.md covers How to use, Topics and How to maintain
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Project Knowledge is an agent skill from JanDeDobbeleer/oh-my-posh. Accumulated project memory: verified gotchas and prior findings for oh-my-posh work. Consult BEFORE touching shell integration scripts (zsh, pwsh, fish, bash, cmd/Clink), terminal or pty behavior, WSL-based shell testing, or internals (cache, segments, streaming, serve daemon). Read only the topic files relevant to the task at hand.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `references/bash.md`, `references/cmd-clink.md` and `references/codebase.md`).

It sits in Agent Workflows, covering Agent memory. It works with Bash and PowerShell. The repository describes itself as: The most customisable and low-latency cross platform/shell prompt renderer. The licence is MIT.

When your agent uses it

  • Tasks that involve Agent memory

Example prompts

  • “/project-knowledge”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Identify which topics the task touches (a zsh script change touches zsh and probably
  2. Read those reference files before writing code or designing an experiment.
  3. Treat entries as point-in-time observations: they carry dates, and code moves. Verify a claim

What it can do on your machine

Read from SKILL.md and the folder at commit 1d6bd96. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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

Project Knowledge loads about 748 tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 302 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~748
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

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 passed

The automated check found no risky patterns in SKILL.md.

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 JanDeDobbeleer/oh-my-posh at commit 1d6bd96, republished under its MIT licence (© JanDeDobbeleer). 302 words, ~748 tokens.

Download SKILL.mdSave it as .claude/skills/project-knowledge/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
project-knowledge
description
Accumulated project memory: verified gotchas and prior findings for oh-my-posh work. Consult BEFORE touching shell integration scripts (zsh, pwsh, fish, bash, cmd/Clink), terminal or pty behavior, WSL-based shell testing, or internals (cache, segments, streaming, serve daemon). Read only the topic files relevant to the task at hand.

Project Knowledge

A modular memory of hard-won, verified facts about this codebase and its runtime environments. Everything here was learned the expensive way - through debugging, benchmarking, or reproduction - and is not derivable from a quick read of the code.

How to use

  1. Identify which topics the task touches (a zsh script change touches zsh and probably testing; a segment bug touches codebase).
  2. Read those reference files before writing code or designing an experiment.
  3. Treat entries as point-in-time observations: they carry dates, and code moves. Verify a claim against the current code before building on it, and fix the entry when it drifted.

Topics

TopicRead when
codebaseTouching Go code: segments, cache, templates, streaming, serve daemon
zshTouching omp.zsh, zle widgets, coproc, or zsh plugin interop
pwshTouching omp.ps1, PSReadLine, runspaces, events, or pwsh perf
fishTouching omp.fish, fish jobs, fifos, or fish event handlers
bashTouching omp.bash, PROMPT_COMMAND, readline, or bash coprocs
cmd-clinkTouching omp.lua, Clink integration, or Windows pipe lifecycles
terminalReasoning about ptys, ConPTY, Windows Terminal, or terminal encoding
testingBuilding a harness to drive a shell end-to-end (WSL, zpty, script(1))

How to maintain

This is a living memory - extend it whenever a session ends with knowledge worth keeping:

  • Add durable, verified facts only: gotchas, platform quirks, measured numbers, failed approaches worth not retrying. No speculation, no session-specific state.
  • Date non-obvious claims (verified 2026-07-14) so future readers can judge staleness.
  • One topic per file. Append to the matching reference file; create a new file and index row when a fact fits no existing topic.
  • Prefer updating or deleting a stale entry over stacking corrections on top of it.
  • Keep entries self-contained: name the file, function, or command they apply to.
  • This skill is committed - include knowledge updates in the commit of the change they relate to.

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

Files

SKILL.md and 8 other files (references) in .agents/skills/project-knowledge of JanDeDobbeleer/oh-my-posh.

  • SKILL.md
  • references/bash.md
  • references/cmd-clink.md
  • references/codebase.md
  • references/fish.md
  • references/pwsh.md
  • references/terminal.md
  • references/testing.md
  • references/zsh.md

Open the folder on GitHubat commit 1d6bd96

Compare with similar skills

Project Knowledge 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.

Project Knowledge compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Project Knowledge this skillJanDeDobbeleer/oh-my-posh24k—~748Automated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Nano Memoryagentscope-ai/skills129—~1.2kAutomated safety check: PassApache-2.0
Agent Developmentmajiayu000/claude-skill-registry6661 repos~2.9kAutomated safety check: PassMIT
Shellm Architecture Referencelaude-institute/headlong1.2k—~2kAutomated safety check: NotesApache-2.0
Hf Cloud Sagemaker Iam Preflightwaybarrios/opencode-power-pack533—~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Nano Memory

    agentscope-ai/skills

    Guidelines and workflows for the agent to maintain persistent memory using native file tools (readfile, writefile, editfile) and standard OS commands for searching.

    129 GitHub stars~1.2k tokensUpdated 27 days ago
    Agent WorkflowsAuto-check passed
  • Agent Development

    majiayu000/claude-skill-registry

    Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.

    666 GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed
  • Shellm Architecture Reference

    laude-institute/headlong

    Explains how shellm's bash-based recursive LLM shell fits together - its core engine, identity system, memory, skills and trajectory log.

    1.2k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check: notes
  • Hf Cloud Sagemaker Iam Preflight

    waybarrios/opencode-power-pack

    Verify or select a SageMaker execution role before creating models, endpoints, or training jobs.

    533 GitHub stars~1.6k tokensUpdated yesterday
    SecurityAuto-check passed
  • Rtk Skill

    sopaco/deepwiki-rs

    A skill your agent uses when running shell commands that produce verbose output (git, test, build, lint, package managers, docker).

    3.1k GitHub stars~1.4k tokensUpdated 23 days ago
    DevOps & CloudAuto-check passed

More from JanDeDobbeleer/oh-my-posh

All 11 skills in this repo
  • Segment Docs

    JanDeDobbeleer/oh-my-posh

    Reference mapping between Oh My Posh Go segment source code and MDX documentation.

    24k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Segment Create

    JanDeDobbeleer/oh-my-posh

    Full scaffolding workflow for creating a new Oh My Posh segment.

    24k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Architecture

    JanDeDobbeleer/oh-my-posh

    Cross-language architecture and clean-code principles for this project: Clean Code, Object Calisthenics, SOLID, guard clauses, hot-path cost, and the code review checklist.

    24k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Conventional Commit

    JanDeDobbeleer/oh-my-posh

    Workflow for generating conventional commit messages following the Conventional Commits specification.

    24k GitHub stars~1.2k tokensUpdated today
    Auto-check: notes
  • Golang

    JanDeDobbeleer/oh-my-posh

    Go coding standards and conventions for this project. An agent skill from JanDeDobbeleer/oh-my-posh.

    24k GitHub stars~4.3k tokensUpdated today
    Auto-check passed
  • Markdown

    JanDeDobbeleer/oh-my-posh

    Markdown formatting rules for this project. An agent skill from JanDeDobbeleer/oh-my-posh.

    24k GitHub stars~754 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Project Knowledge

What does Project Knowledge do?

Accumulated project memory: verified gotchas and prior findings for oh-my-posh work. Project Knowledge is an agent skill from JanDeDobbeleer/oh-my-posh. Accumulated project memory: verified gotchas and prior findings for oh-my-posh work.

When should I use Project Knowledge?

Project Knowledge fits situations like: tasks that involve Agent memory.

How do I install Project Knowledge in Claude Code?

Run `npx skills add JanDeDobbeleer/oh-my-posh --skill project-knowledge -a claude-code`. Or copy the skill folder (.agents/skills/project-knowledge in JanDeDobbeleer/oh-my-posh) into .claude/skills/project-knowledge in your project. Claude Code loads it when a task matches its description.

How do I install Project Knowledge in Codex?

Run `npx skills add JanDeDobbeleer/oh-my-posh --skill project-knowledge -a codex`. Or copy the skill folder (.agents/skills/project-knowledge in JanDeDobbeleer/oh-my-posh) into .agents/skills/project-knowledge in your project. Codex loads it when a task matches its description.

Can I use Project Knowledge 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 JanDeDobbeleer/oh-my-posh --skill project-knowledge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/project-knowledge, .gemini/skills/project-knowledge, .github/skills/project-knowledge and .opencode/skills/project-knowledge in your project.

What does Project Knowledge need to run?

SKILL.md names no scripts, command-line tools or credentials: Project Knowledge is instructions for the agent only.

Does Project Knowledge 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 Project Knowledge safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Project Knowledge use?

Project Knowledge 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 Project Knowledge use?

About 748 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.9k tokens, read only when the agent opens those files.

What are the alternatives to Project Knowledge?

Skills that share tags, products or a category with Project Knowledge: Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars), Nano Memory (agentscope-ai/skills, 129 stars), Agent Development (majiayu000/claude-skill-registry, 666 stars) and Shellm Architecture Reference (laude-institute/headlong, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Project Knowledge?

JanDeDobbeleer (a GitHub user) maintains it in JanDeDobbeleer/oh-my-posh, which has 23,555 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

Source: JanDeDobbeleer/oh-my-posh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.