Wp Performance Review
elvismdev/claude-wordpress-skills
WordPress performance code review and optimization analysis.
Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports.
$ npx skills add manager-dot-dev/manager-skills --skill 1on1s -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install manager-dot-dev/manager-skills 1on1s --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/1on1s .claude/skills/1on1s && 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 "1on1s" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/1on1s into .claude/skills/1on1s/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1on1s", 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/1on1sType 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 1on1s -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install manager-dot-dev/manager-skills 1on1s --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/1on1s .agents/skills/1on1s && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "1on1s" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/1on1s into .agents/skills/1on1s/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1on1s", 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 1on1s -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install manager-dot-dev/manager-skills 1on1s --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/1on1s .cursor/skills/1on1s && 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 "1on1s" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/1on1s into .cursor/skills/1on1s/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1on1s", 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/1on1s--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 1on1s -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install manager-dot-dev/manager-skills 1on1s --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/1on1s .gemini/skills/1on1s && 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 "1on1s" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/1on1s into .gemini/skills/1on1s/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1on1s", 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 1on1sInstalls 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 1on1s -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/1on1s .github/skills/1on1s && 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 "1on1s" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/1on1s into .github/skills/1on1s/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1on1s", 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 1on1s -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 1on1s --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/1on1s .opencode/skills/1on1s && 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 "1on1s" agent skill from https://github.com/manager-dot-dev/manager-skills/tree/main/skills/1on1s into .opencode/skills/1on1s/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "1on1s", 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.
1on1sPrepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports.
1on1s is an agent skill from manager-dot-dev/manager-skills. Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports. Use when the user wants to prepare for, run, improve, or follow up on a 1:1, or says "1:1 agenda," "prepare for my 1:1," "1:1 notes," "what should I talk about with," "my direct report," "check in with my report," "make my 1:1s better," "1:1 template," or "my 1:1s feel like status updates." Do NOT use when the user needs to deliver specific feedback (use feedback) or discuss…
Its SKILL.md is about 3k 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 Business, Finance & HR, covering Performance reviews. The repository describes itself as: Skills for engineering managers. The licence is MIT.
3 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.
1on1s loads about 3k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 1,790 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). 1,790 words, ~3,023 tokens.
.claude/skills/1on1s/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:
.agents/em-context.md if it exists.agents/reports/[name].md and read itIf .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 before applying a framework:
If a specific person is mentioned, check .agents/reports/[name].md before responding — it may already contain context about their communication style, what they care about, and past conversations.
When helping with a 1:1, produce something the manager can use in the next conversation:
If the user only asks for a template, give the template first and keep explanation short.
Based on a survey of engineers: the most valued 1:1s share a few consistent traits.
Do them weekly. Research from Manager Tools (based on data from thousands of managers) shows: fortnightly 1:1s are 40% less effective than weekly. Monthly 1:1s perform worse than no 1:1s at all. Weekly 1:1s alone account for a significant portion of manager effectiveness. The data is unusually clear on this.
Be consistent. The biggest mistake is cancelling or rescheduling often. Engineers notice. It communicates that the 1:1 — and by extension, they — aren't a priority. Protect the slot.
Don't focus on day-to-day work. Status updates have other venues. 1:1s are not standups. Use them for: career development, growth, personal connection, things they won't bring up in a group setting, what's frustrating them, what they're excited about.
Use them for personal connection. Ask about life outside work — not in a prying way, just genuine interest. Remember what they tell you. Return to it. This is how trust builds.
Three things to know about the people you manage — and use by name:
It's never too late to ask. These details change 1:1s from professional check-ins into conversations with someone who actually knows you.
Be patient. Trust takes time. Some people open up in the first 1:1. Others take months. One story: a developer didn't really open up until 6+ months in — and the relationship became one of the manager's strongest. Show up consistently. The patience pays off.
Ask about cadence — don't assume. Weekly 1:1s work well for most people. Some prefer bi-weekly. Some feel they don't need a standing slot at all. Ask what cadence your reports actually want. The same applies to other defaults: not everyone wants to be involved in roadmap discussions, not everyone wants to present in team meetings. Ask first.
One question worth adding to your 1:1 rotation: "How did you feel this week?"
Not "how did it go" — that gets you status. "How did you feel" gets you signals.
Three patterns to watch for:
The over-responsive engineer — responds to every Slack message immediately, anxious when they miss something, apologizes for small things. The underlying signal: fear of letting people down. Left unaddressed, this leads to burnout. What they need: explicit permission to disconnect, reassurance that availability doesn't equal value.
The always-late engineer — consistently underestimates how long things take, commits to more than they can deliver, misses self-imposed deadlines. The underlying signal: they're planning for their ideal self, not their real self. Not a discipline problem — a calibration problem. Work on scoping together, not on accountability pressure.
The messy-PR engineer — submits PRs that feel rushed or incomplete, gets defensive in code review, doesn't ask for help until blocked. The underlying signal: they feel judged or exposed when work is imperfect. What they need: psychological safety to ship imperfect work-in-progress and get feedback earlier.
The pattern only becomes visible if you ask the question regularly and pay attention to the answer over time.
You are not a therapist. Care genuinely — but set limits on what you can hold.
When a 1:1 drifts into territory that's beyond your role: "I hear you, and I want to support this. Let me think about what I can actually do on my side." Then focus on what you can control: workload, team dynamics, scope, flexibility.
If someone's personal situation is affecting their work at a serious level, consult HR before acting. Know when to redirect to professional support — and how to do it without it feeling like a dismissal.
The goal isn't to make someone feel heard at the expense of making them feel abandoned. Both are possible. The frame: "What can we adjust at work to help you succeed?"
Sometimes the connection in a 1:1 just doesn't click — age gap, cultural difference, personality mismatch, opposite communication styles. The wrong response is to give up and keep 1:1s purely transactional.
When connection doesn't flow naturally: try harder, not less.
"There is no stronger way to build relationships than taking a genuine interest in other human beings." (Danny Meyer)
One question worth adding to your 1:1 rotation: "What's the one thing you'd change about our team if you were in my shoes?"
This gets different answers than "what do you think about X?" because it starts from scratch — the engineer has to generate the problem, not just react to yours. It also bypasses the social filter of "is it okay to criticize my manager's decisions."
Note: most managers either don't ask this, or ask about a direction they've already decided on. The value is in asking it genuinely, before you've committed.
Things many managers assume are universal preferences — but aren't. Ask before assuming:
Even if you think you know — just ask. You'll be right sometimes and wrong in ways that matter.
Most 1:1s fall into one of three types. Knowing which you're in changes how you respond.
The Update — the engineer shares status. What's going on with their work, projects, blockers. This is the most common type, and often the least valuable. If your 1:1s are mostly Updates, you're running a standup, not a 1:1. The goal should be to create enough safety that they move past the Update.
The Vent — they need to process something. Frustration with the team, a decision they disagree with, a relationship that's difficult. Your job here is not to fix it immediately. It's to listen, ask questions, help them feel heard. "Have you talked to them directly?" is often the right next question — but only after they've been heard, not as a shortcut past the listening.
The Disaster — something is genuinely wrong: a relationship has broken, they're thinking about leaving, something serious happened. You'll know because the conversation has a different weight. Here, you need to shift into action mode: understand what happened, figure out what they need, and commit to follow-through.
The cardinal rule on 1:1s from Rands: you work for them, not the other way around. Each 1:1 they don't attend costs them an hour. Each one you cancel tells them: "You don't matter." The cancellation sticks longer than the meeting would have.
A practical format: give 60% of the time (roughly 18 of 30 minutes) to the report, and use the remaining 40% for topics you need to cover.
The trap with this format: managers use "their" 40% first and then run out of time for the report. Reverse it — start with them. Let their topics drive the conversation. Your agenda items will nearly always fit at the end; theirs won't if they're deprioritized.
Share the format with your reports. When they understand that 1:1s are primarily their time, they come more prepared and use it better.
If the user asks where a framework came from, wants to read the original article, or wants more context on any topic in this skill — read references/sources.md for the full list of source articles (with links) and books.
feedback — For preparing or delivering specific feedback in a 1:1performance-reviews — For end-of-cycle review discussionsteam-health — For patterns across your team's 1:1s© 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/1on1s of manager-dot-dev/manager-skills.
Open the folder on GitHubat commit c47ebc7
1on1s 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 |
|---|---|---|---|---|---|---|
| 1on1s this skillmanager-dot-dev/manager-skills | 114 | — | ~3k | Automated safety check: Pass | MIT | |
| Wp Performance Reviewelvismdev/claude-wordpress-skills | 235 | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Align Humanagentscope-ai/OpenJudge | 868 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Performance ReportAffitor/affiliate-skills | 699 | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Run Mv Hoi Reconstructionnvidia-isaac/video_to_data | 850 | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| Company Analysiszhu1090093659/dsh-trading | 231 | — | ~4.2k | Automated safety check: Pass | Custom licence |
elvismdev/claude-wordpress-skills
WordPress performance code review and optimization analysis.
agentscope-ai/OpenJudge
A skill your agent uses when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic…
Affitor/affiliate-skills
Generate affiliate performance reports with KPIs and recommendations.
nvidia-isaac/video_to_data
Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.
zhu1090093659/dsh-trading
A skill your agent uses when the user wants to analyze a listed company, stock, business, or investment target; challenge or revise an existing company report; compare A/H or primary-listing/ADR…
microsoft/win-dev-skills
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation.
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
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.
manager-dot-dev/manager-skills
Helps engineering managers measure and improve team delivery — produces a history of why common metrics fail, the DORA four-key-metrics framework (deployment frequency, lead time, change failure…
Categories
Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports. 1on1s is an agent skill from manager-dot-dev/manager-skills. Prepares agendas, diagnoses struggling 1:1 relationships, and gives frameworks for running effective 1:1 meetings with direct reports.
1on1s fits situations like: the user wants to prepare for; follow up on a 1:1; says 1:1 agenda; prepare for my 1:1.
Run `npx skills add manager-dot-dev/manager-skills --skill 1on1s -a claude-code`. Or copy the skill folder (skills/1on1s in manager-dot-dev/manager-skills) into .claude/skills/1on1s in your project. Claude Code loads it when a task matches its description.
Run `npx skills add manager-dot-dev/manager-skills --skill 1on1s -a codex`. Or copy the skill folder (skills/1on1s in manager-dot-dev/manager-skills) into .agents/skills/1on1s 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 1on1s -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/1on1s, .gemini/skills/1on1s, .github/skills/1on1s and .opencode/skills/1on1s in your project.
SKILL.md names no scripts, command-line tools or credentials: 1on1s 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.
1on1s is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k 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 245 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with 1on1s: Wp Performance Review (elvismdev/claude-wordpress-skills, 235 stars), Align Human (agentscope-ai/OpenJudge, 868 stars), Performance Report (Affitor/affiliate-skills, 699 stars) and Run Mv Hoi Reconstruction (nvidia-isaac/video_to_data, 850 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.