跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

performance-cycle

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.

techwolf-ai · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add techwolf-ai/ai-first-toolkit --skill performance-cycle

技能说明


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 to references/performance-framework.md defaults)
  • manager-context/management-framework.md: org-specific management dimensions (falls back to references/management-framework.md defaults)
  • references/values-guide.md: values definitions and signal guidance
  • manager-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)

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 manua
阅读完整来源 ↗