LLM Wiki
lewislulu/llm-wiki-skill
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…
Helps EMs build a reliable relationship with their manager, navigate disagreements with leadership, and communicate upward effectively.
$ npx skills add manager-dot-dev/manager-skills --skill managing-up -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install manager-dot-dev/manager-skills managing-up --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/managing-up .claude/skills/managing-up && rm -rf skills-srcUse ~/.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/
Install the "managing-up" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/managing-up into .claude/skills/managing-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "managing-up", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/manager-dot-dev/manager-skills/tree/main/skills/managing-upType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add manager-dot-dev/manager-skills --skill managing-up -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install manager-dot-dev/manager-skills managing-up --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/managing-up .agents/skills/managing-up && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "managing-up" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/managing-up into .agents/skills/managing-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "managing-up", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add manager-dot-dev/manager-skills --skill managing-up -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install manager-dot-dev/manager-skills managing-up --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/managing-up .cursor/skills/managing-up && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "managing-up" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/managing-up into .cursor/skills/managing-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "managing-up", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/manager-dot-dev/manager-skills.git --path skills/managing-up--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add manager-dot-dev/manager-skills --skill managing-up -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install manager-dot-dev/manager-skills managing-up --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/managing-up .gemini/skills/managing-up && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "managing-up" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/managing-up into .gemini/skills/managing-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "managing-up", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install manager-dot-dev/manager-skills managing-upInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add manager-dot-dev/manager-skills --skill managing-up -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/managing-up .github/skills/managing-up && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "managing-up" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/managing-up into .github/skills/managing-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "managing-up", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add manager-dot-dev/manager-skills --skill managing-up -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install manager-dot-dev/manager-skills managing-up --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/manager-dot-dev/manager-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/managing-up .opencode/skills/managing-up && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "managing-up" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/managing-up into .opencode/skills/managing-up/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "managing-up", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
managing-upHelps EMs build a reliable relationship with their manager, navigate disagreements with leadership, and communicate upward effectively.
Managing Up is an agent skill from manager-dot-dev/manager-skills. Helps EMs build a reliable relationship with their manager, navigate disagreements with leadership, and communicate upward effectively. Use when the user says "managing up," "my manager," "I disagree with a decision," "I need to push back," "my skip level," "communicating with leadership," "my manager committed my team without asking," "how do I tell my boss," or "senior leadership." Do NOT use for influencing peers or cross-functional stakeholders (use influence) or for general EM self-reflection (use…
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/sources.md`).
It sits in Knowledge Management, covering Journaling and reflection. The repository describes itself as: Skills for engineering managers. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c47ebc7. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Managing Up loads about 2.4k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 135 tokens; SKILL.md has 1,371 words of instructions outside code blocks.
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.
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.
The full file from manager-dot-dev/manager-skills at commit c47ebc7, republished under its MIT licence (© manager-dot-dev). 1,371 words, ~2,387 tokens.
.claude/skills/managing-up/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Check for EM context first. If .agents/em-context.md exists, read it.
If .agents/em-context.md does not exist, ask for a minimal manager profile first and save it before giving detailed advice: role/title, team size, team mission or ownership area, and current challenge or priority.
If a specific person is central to the conversation and .agents/reports/[name].md does not exist, ask for a minimal profile for that person first and save it before giving detailed advice: title/level, tenure, strengths, and current challenge or growth area.
.agents/em-context.md or .agents/reports/[name].md automatically. Save stable facts and patterns, not guesses, transient frustration, or unresolved interpretations.Keep the first answer concise and useful. Do not dump the whole framework unless the user asks for depth.
Default to:
Identify the situation first:
When helping someone manage up, focus on reliability and leverage:
For disagreements, separate "I need to be heard" from "I need the decision changed."
"Managing up" is often described as a political skill. It isn't. At its core, it's about one thing: not making your manager look unreliable to their manager.
Every time you miss a deadline without warning, you put your manager in an impossible position. They committed that deadline upward. Your late delivery — especially when delivered as a surprise — damages their credibility, not just yours. Managers talk to each other. Repeated surprises end careers.
The rule: warn early, not late. As soon as you know you can't hit a commitment, say so. "Tuesday isn't happening — it'll be Friday" on Monday morning is recoverable. "Oops, it'll be next week" on Tuesday afternoon is not.
This applies upward at every level. The EMs who build durable relationships with senior leadership are often not the most talented — they're the most reliable. They follow through. They don't make promises they can't keep. They surface problems before they become surprises.
Manage your manager intentionally. Your manager often knows less than you about what the right decision is. When you bring a problem, also bring the decision you want them to make. "I want you to make the decision" is almost never the right ask — "here's what I think we should do, and here's what I need from you" is.
Respond promptly to anything that might be blocking your manager. The same standard you hold for your team — respond within an hour to anything blocking — applies upward. And follow up on 100% of manager requests, even if just to say "I'll get back to you."
When leadership makes a call you don't fully buy into, how you communicate it to the team matters more than people realize.
First: engage properly with the decision before communicating it. Distinguish between types:
The key principle: you're almost never as certain as you think you are. Most decisions that feel clearly wrong turn out to have context you didn't have.
What to tell the team: describe how you engaged with the process, not just the outcome. "I had concerns, I raised them, this is what was decided and why" is more credible than "leadership wants this." The first version maintains your integrity. The second erodes it every time.
A few behaviors that undermine how senior leadership perceives you:
Finesse matters. How you communicate has as much impact as what you communicate. Saying "everything we presented in the last 2 months was a lie" in a Slack channel — even if technically accurate — demoralizes people and signals lack of judgment. HOW you present difficult information matters.
Language accuracy. If you're not 100% sure about something, signal it. "I believe..." or "as far as I know..." prevents the frustration of confident-sounding statements that turn out to be wrong.
Delivering bad news. Don't associate yourself with the news. Avoid: a long preface about importance, multiple negative words, excessive detail. State the situation clearly, own what's yours, move to next steps.
Giving feedback to senior leaders. It's an inversion of norms — and feeling nervous about it is healthy. Techniques that work: use the "even more" framing ("I think you could have even more impact if..."), use yourself as an example rather than criticizing them directly, lead with curiosity rather than judgment, bring specific data and examples.
Most managers want their reports to manage up — but rarely say it explicitly. What this looks like in practice:
The EMs who have the most influence with their managers aren't the ones who make the fewest mistakes — they're the ones their manager trusts to carry things without dropping them.
When your manager gives you a difficult performance review, the first instinct is to blame the manager. Sometimes that's right. But half the blame is usually yours.
Don't expect your manager to guess your motivations. Don't expect 1:1s to automatically solve communication problems. Don't expect appreciation for work that was never made visible. The same principle works in reverse: if your team never tells you what's working or what's frustrating, part of that is on you for not creating the space.
If the user asks where a framework came from, wants to read the original article, or wants more context on any topic — read references/sources.md for the full list of source articles (with links) and books.
managing-yourself — The 10 ways EMs get stuck includes traps #8–10 on managing up and downinfluence — For persuading peers, cross-functional stakeholders, and getting headcountfeedback — Giving feedback to your manager is a specific case of the feedback skill© manager-dot-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in skills/managing-up of manager-dot-dev/manager-skills.
Open the folder on GitHubat commit c47ebc7
Managing Up 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Managing Up this skillmanager-dot-dev/manager-skills | 114 | — | ~2.4k | Automated safety check: Pass | MIT | |
| LLM Wikilewislulu/llm-wiki-skill | 655 | — | ~3.7k | Automated safety check: Pass | None | |
| Munger Perspectivealchaincyf/munger-skill | 377 | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Daily Journalhuytieu/COG-second-brain | 1.3k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Letterboxd Diaryjoe-bell/skills | 211 | — | ~4.2k | Automated safety check: Pass | MIT | |
| Digital Brainforyourhealth111-pixel/Vibe-Skills | 3.6k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 |
lewislulu/llm-wiki-skill
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…
alchaincyf/munger-skill
查理·芒格的思维框架与表达方式。基于《穷查理宝典》、伯克希尔/Daily Journal股东会、 USC/哈佛演讲、访谈记录、外部批评等50+来源的深度调研, 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。
huytieu/COG-second-brain
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself.
joe-bell/skills
Fetch recently watched films from a Letterboxd member's diary RSS feed and render them as a compact markdown list, with first-run setup for the username.
foryourhealth111-pixel/Vibe-Skills
This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content…
SCStelz/security-investigator
Weekly review of an investigation tenant-context memory file against the most recent SOC scan reports (e.g.
manager-dot-dev/manager-skills
Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack.
manager-dot-dev/manager-skills
Foundation skill for engineering managers. An agent skill from manager-dot-dev/manager-skills.
manager-dot-dev/manager-skills
Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports.
manager-dot-dev/manager-skills
Explains business financial terms and frameworks for engineering managers — produces term definitions (ARR, COGS, CAC, LTV, gross margin, burn rate, EBITDA, AARRR), translation formulas for making…
manager-dot-dev/manager-skills
Helps engineering managers support direct report growth — produces a stage-by-stage model of engineering impact (Circles of Influence), a framework for non-linear career planning (Tarzan Method)…
manager-dot-dev/manager-skills
Guides managers out of the bottleneck role — provides the Team Rep pattern, Epic Ownership model, Task-Relevant Maturity framework, kingdom ownership, and three-layer assignment strategy.
Categories
Helps EMs build a reliable relationship with their manager, navigate disagreements with leadership, and communicate upward effectively. Managing Up is an agent skill from manager-dot-dev/manager-skills. Helps EMs build a reliable relationship with their manager, navigate disagreements with leadership, and communicate upward effectively.
Managing Up fits situations like: the user says managing up; I disagree with a decision; I need to push back; communicating with leadership.
Run `npx skills add manager-dot-dev/manager-skills --skill managing-up -a claude-code`. Or copy the skill folder (skills/managing-up in manager-dot-dev/manager-skills) into .claude/skills/managing-up in your project. Claude Code loads it when a task matches its description.
Run `npx skills add manager-dot-dev/manager-skills --skill managing-up -a codex`. Or copy the skill folder (skills/managing-up in manager-dot-dev/manager-skills) into .agents/skills/managing-up in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add manager-dot-dev/manager-skills --skill managing-up -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/managing-up, .gemini/skills/managing-up, .github/skills/managing-up and .opencode/skills/managing-up in your project.
SKILL.md names no scripts, command-line tools or credentials: Managing Up is instructions for the agent only.
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.
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.
Managing Up is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.4k tokens (SKILL.md is roughly 9.5k 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 198 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Managing Up: LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), Munger Perspective (alchaincyf/munger-skill, 377 stars), Daily Journal (huytieu/COG-second-brain, 1.3k stars) and Letterboxd Diary (joe-bell/skills, 211 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
manager-dot-dev (a GitHub organization) maintains it in manager-dot-dev/manager-skills, which has 114 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on May 9, 2026.
Source: manager-dot-dev/manager-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.