Wp Performance Review
elvismdev/claude-wordpress-skills
WordPress performance code review and optimization analysis.
Evidence gathering for performance review cycles. An agent skill from techwolf-ai/ai-first-toolkit.
Install Performance Cycle
$ npx skills add techwolf-ai/ai-first-toolkit --skill performance-cycle -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install techwolf-ai/ai-first-toolkit performance-cycle --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/techwolf-ai/ai-first-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/people-management/skills/performance-cycle .claude/skills/performance-cycle && 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 "performance-cycle" agent skill from https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/performance-cycle into .claude/skills/performance-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-cycle", 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/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/performance-cycleType 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 techwolf-ai/ai-first-toolkit --skill performance-cycle -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install techwolf-ai/ai-first-toolkit performance-cycle --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/people-management/skills/performance-cycle .agents/skills/performance-cycle && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "performance-cycle" agent skill from https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/performance-cycle into .agents/skills/performance-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-cycle", 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 techwolf-ai/ai-first-toolkit --skill performance-cycle -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install techwolf-ai/ai-first-toolkit performance-cycle --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/people-management/skills/performance-cycle .cursor/skills/performance-cycle && 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 "performance-cycle" agent skill from https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/performance-cycle into .cursor/skills/performance-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-cycle", 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/techwolf-ai/ai-first-toolkit.git --path plugins/people-management/skills/performance-cycle--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 techwolf-ai/ai-first-toolkit --skill performance-cycle -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install techwolf-ai/ai-first-toolkit performance-cycle --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/people-management/skills/performance-cycle .gemini/skills/performance-cycle && 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 "performance-cycle" agent skill from https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/performance-cycle into .gemini/skills/performance-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-cycle", 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 techwolf-ai/ai-first-toolkit performance-cycleInstalls 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 techwolf-ai/ai-first-toolkit --skill performance-cycle -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/people-management/skills/performance-cycle .github/skills/performance-cycle && 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 "performance-cycle" agent skill from https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/performance-cycle into .github/skills/performance-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-cycle", 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 techwolf-ai/ai-first-toolkit --skill performance-cycle -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install techwolf-ai/ai-first-toolkit performance-cycle --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/techwolf-ai/ai-first-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/people-management/skills/performance-cycle .opencode/skills/performance-cycle && 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 "performance-cycle" agent skill from https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/people-management/skills/performance-cycle into .opencode/skills/performance-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "performance-cycle", 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.
Facts
- Skill name
performance-cycle- GitHub stars
- 132
- Token cost
- ~2.1k tokens
- SKILL.md length
- 961 words
- Files
- 6 (incl. references)
- Skills in repo
- 29
- Repo updated
- First seen
- Licence
- MIT
At a glance
Evidence gathering for performance review cycles. An agent skill from techwolf-ai/ai-first-toolkit.
- Works in 10 steps: Identify Scope → Load Context → Gather Evidence Along Each Dimension → …
- Tasks that involve Performance reviews
- SKILL.md covers When to Use, Context: Performance Framework, Instructions and Important Notes
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Performance Cycle is an agent skill from techwolf-ai/ai-first-toolkit. Evidence gathering for performance review cycles. Gathers goal completion evidence, peer feedback, development progress, scope changes, and values alignment, organised along the org's performance framework dimensions, with organizational values as the 'how' lens. Surfaces evidence gaps. Never suggests ratings, only organises evidence for the manager's judgment.
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/management-framework.md`, `references/operating-principles.md` and `references/output-template.md`).
It sits in Business, Finance & HR, covering Performance reviews. The repository describes itself as: Open-source Claude Code skills and Codex skills for AI-first work. Audit, re-engineer, and bootstrap projects with AI-first design principles. The licence is MIT.
When your agent uses it
- Tasks that involve Performance reviews
Example prompts
- “s performance framework dimensions, with organizational values as the”
- “/performance-cycle”
Workflow steps
10 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 2ee7841. 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
Performance Cycle loads about 2.1k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 95 tokens; SKILL.md has 961 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.
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 techwolf-ai/ai-first-toolkit at commit 2ee7841, republished under its MIT licence (© techwolf-ai). 961 words, ~2,115 tokens.
Download SKILL.mdSave it as
.claude/skills/performance-cycle/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- performance-cycle
- description
- Evidence gathering for performance review cycles. Gathers goal completion evidence, peer feedback, development progress, scope changes, and values alignment, organised along the org's performance framework dimensions, with organizational values as the 'how' lens. Surfaces evidence gaps. Never suggests ratings, only organises evidence for the manager's judgment.
Performance Cycle Assistant
Principle: "You are responsible." This skill gathers and organises evidence. Rating decisions and development assessments are the manager's alone.
Helps managers prepare evidence-based assessments for performance review cycles. The org's performance framework dimensions measure what was achieved and how the person developed. Organizational values measure how they showed up while doing it.
When to Use
- During full review cycles (per the org's review cadence)
- During lighter check-ins between full reviews
- When the manager says "help me prep [name]'s review", "gather evidence for [name]'s performance"
- Can be run for one team member or all reports in batch
Context: Performance Framework
Load the org's performance framework from manager-context/performance-framework.md (created during /setup). This defines:
- Framework dimensions and sub-dimensions
- Rating scale
- Promotion readiness labels (if tracked)
- Review cadence
If manager-context/performance-framework.md doesn't exist, ask the manager to run /setup first.
Instructions
If any MCP connector is unavailable, follow the connector unavailability protocol in references/operating-principles.md.
1. Identify Scope
Determine who to prepare for:
- Single team member: "prep [name]'s review"
- Whole team: "prep all reviews" (runs sequentially for each report)
Determine the review period:
- Default: last 6 months (for bi-annual review) or last 3 months (for check-in)
- Can be customised: "since [date]"
2. Load Context
For the target team member, read from manager-context/team/[name].md:
- Their goals (locations in Notion/Drive)
- Their development areas from last review
- Their role and level (from Job Architecture)
- Their projects and responsibilities
Also load:
manager-context/performance-framework.md: org-specific framework dimensions and rating descriptors (falls back toreferences/performance-framework.mddefaults)manager-context/management-framework.md: org-specific management dimensions (falls back toreferences/management-framework.mddefaults)references/values-guide.md: values definitions and signal guidancemanager-context/values.md: the organization's specific values
3. Gather Evidence Along Each Dimension
For each dimension and sub-dimension in the org's performance framework (from manager-context/performance-framework.md), gather evidence from connected sources.
For each sub-dimension:
- Notion: Pull goals, project pages, status updates, metrics relevant to this dimension
- Slack: Search for messages showing activity, feedback, recognition, or friction related to this dimension
- Google Drive: Look for deliverables, reports, documents tied to this dimension
- Calendar: Check for activities that signal growth or scope changes (new meetings, new stakeholders)
- Compile: what evidence was found, with links
Common evidence patterns by dimension type:
- Results/delivery dimensions: goal completion, shipped work, quality feedback, business outcomes
- Growth/development dimensions: learning activities, new skills applied, scope expansion, behavioural changes
- Collaboration/leadership dimensions: cross-team activity, mentoring, influence in discussions
For dimensions that are hardest to assess digitally (e.g., behavioural growth, leadership presence), explicitly flag that the manager's direct observations carry more weight.
4. Gather Values Evidence
Values are the "how": how this person delivered their results and showed up for the team. Search for evidence across the organization's values (from manager-context/values.md). See references/values-guide.md for guidance on finding value signals.
For each value defined in manager-context/values.md, search for evidence using the signal guidance stored there. Common evidence sources by value type:
Collaboration / teamwork values:
- Slack: cross-team collaboration, helping unblock others, participating in team decisions
- DMs (with manager): conversations about team dynamics, commitment to group decisions
Ambition / ownership values:
- Slack/Notion: volunteering for stretch work, proposing ideas, driving outcomes
- Evidence of taking things to completion without being pushed
Innovation / resourcefulness values:
- Slack: creative problem-solving, finding workarounds, learning from obstacles
- Evidence of unblocking themselves or the team under constraints
Transparency / communication values:
- Slack: sharing context proactively, raising issues early, giving and receiving feedback
- DMs (with manager): being open about challenges, asking for help
Care / wellbeing values:
- Slack: celebrating others, recognising teammates, showing empathy
- Calendar: sustainable work patterns or concerning overwork patterns
For each value, compile evidence as observations (not judgments):
- Strong signal: Multiple visible examples
- Some signal: 1-2 examples
- Gap: No evidence found (note: absence of evidence ≠ absence of the behaviour)
Show full SKILL.md (359 more words)Show less
5. Check Peer Recognition
Search Slack for recognition this person received during the review period:
- Direct shoutouts from teammates
- Recognition in team channels
- Reactions on their messages (high-reaction messages = valued contributions)
6. Identify Evidence Gaps
For each dimension, assess evidence strength:
- Strong evidence: Multiple sources corroborate
- Some evidence: 1-2 data points
- Gap: No evidence found, manager needs to gather this manually
7. Produce the Evidence Summary
Read references/output-template.md for the full output template structure (individual and batch mode).
8. For Batch Mode (All Reports)
If preparing for the whole team, produce individual evidence summaries for each team member plus a team-level comparison view. See the batch mode template in references/output-template.md.
9. Present
Here's the evidence I gathered for [name]'s review. I've flagged gaps where you'll want to add your own observations.
Remember: this is evidence gathering only. Rating decisions and promotion assessments are yours to make based on the full picture, including things I can't see.10. Sub-Agent Review
Spawn a sub-agent to review the evidence summary with fresh eyes. The reviewer should:
- Check for recency bias: is most evidence from the last few weeks, or spread across the review period?
- Check for dimension imbalance: are some dimensions well-evidenced while others are thin? Flag under-covered areas.
- Check for interpretive language: flag any phrasing that crosses from evidence ("shipped X on time") into interpretation ("demonstrated strong execution").
- Verify evidence gaps are honestly flagged, not papered over with weak data.
- Check that values evidence is presented as "examples I found", not "the full picture."
Incorporate the reviewer's feedback before presenting the final summary to the manager.
Important Notes
Read references/operating-principles.md for shared operating principles (data scope, DM flagging, signals vs diagnoses, connector unavailability).
Additional notes specific to this skill:
- NEVER suggest a rating. Not even hints. The manager decides ratings. Period.
- NEVER compare team members to each other. Evidence is per-person. Calibration is the manager's job.
- Evidence, not interpretation. "Shipped feature X on time" is evidence. "Demonstrated strong execution" is interpretation. Stick to evidence.
- Flag gaps honestly. "I found no evidence for behavioral growth" is more useful than padding with weak data.
- Recency bias warning. Note if most evidence is from the last month vs. spread across the review period.
- Values evidence is hardest to gather digitally. Many values are lived in person, not in Slack. The manager's direct observations are more authoritative.
- This supplements, not replaces. The manager has 6 months of direct observation.
© techwolf-ai, 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 5 other files (references) in plugins/people-management/skills/performance-cycle of techwolf-ai/ai-first-toolkit.
- SKILL.md
- references/management-framework.md
- references/operating-principles.md
- references/output-template.md
- references/performance-framework.md
- references/values-guide.md
Open the folder on GitHubat commit 2ee7841
Compare with similar skills
Performance Cycle 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 |
|---|---|---|---|---|---|---|
| Performance Cycle this skilltechwolf-ai/ai-first-toolkit | 132 | — | ~2.1k | 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 |
Similar skills
Align Human
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…
Performance Report
Affitor/affiliate-skills
Generate affiliate performance reports with KPIs and recommendations.
Run Mv Hoi Reconstruction
nvidia-isaac/video_to_data
Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.
Company Analysis
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…
- Official
Windbg Diagnostic Method
microsoft/win-dev-skills
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation.
More from techwolf-ai/ai-first-toolkit
All 29 skills in this repoTask Profile
techwolf-ai/ai-first-toolkit
Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often, how successfully where friction lives, then propose atomic skills that would…
Session Search
techwolf-ai/ai-first-toolkit
Find context from past Claude Code (CLI) and Claude Cowork (desktop) sessions on this Mac.
Token Doctor
techwolf-ai/ai-first-toolkit
Personal diagnosis of where your Claude Code + Cowork spend goes.
Write Blog Post
techwolf-ai/ai-first-toolkit
Write or develop a blog post. An agent skill from techwolf-ai/ai-first-toolkit.
Write Opinion
techwolf-ai/ai-first-toolkit
Write or develop an opinion piece (opiniestuk/op-ed). An agent skill from techwolf-ai/ai-first-toolkit.
AI Firstify
techwolf-ai/ai-first-toolkit
Analyze, re-engineer, or bootstrap projects to align with AI-first design principles.
Related
Categories
Questions about Performance Cycle
What does Performance Cycle do?
Evidence gathering for performance review cycles. An agent skill from techwolf-ai/ai-first-toolkit. Performance Cycle is an agent skill from techwolf-ai/ai-first-toolkit. Evidence gathering for performance review cycles.
When should I use Performance Cycle?
Performance Cycle fits situations like: tasks that involve Performance reviews.
How do I install Performance Cycle in Claude Code?
Run `npx skills add techwolf-ai/ai-first-toolkit --skill performance-cycle -a claude-code`. Or copy the skill folder (plugins/people-management/skills/performance-cycle in techwolf-ai/ai-first-toolkit) into .claude/skills/performance-cycle in your project. Claude Code loads it when a task matches its description.
How do I install Performance Cycle in Codex?
Run `npx skills add techwolf-ai/ai-first-toolkit --skill performance-cycle -a codex`. Or copy the skill folder (plugins/people-management/skills/performance-cycle in techwolf-ai/ai-first-toolkit) into .agents/skills/performance-cycle in your project. Codex loads it when a task matches its description.
Can I use Performance Cycle 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 techwolf-ai/ai-first-toolkit --skill performance-cycle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/performance-cycle, .gemini/skills/performance-cycle, .github/skills/performance-cycle and .opencode/skills/performance-cycle in your project.
What does Performance Cycle need to run?
SKILL.md names no scripts, command-line tools or credentials: Performance Cycle is instructions for the agent only.
Does Performance Cycle 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 Performance Cycle 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 Performance Cycle use?
Performance Cycle 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 Performance Cycle use?
About 2.1k tokens (SKILL.md is roughly 8.5k 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 2.8k tokens, read only when the agent opens those files.
What are the alternatives to Performance Cycle?
Skills that share tags, products or a category with Performance Cycle: 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.
Who maintains Performance Cycle?
techwolf-ai (a GitHub organization) maintains it in techwolf-ai/ai-first-toolkit, which has 132 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on September 29, 2026.
Source: techwolf-ai/ai-first-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.