How do I install the Practice Setup skill?

Run npx skillmds@latest add daddia/practice-setup in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Practice Setup safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Practice Setup?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Practice Setup free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Practice Setup?

daddia (@daddia) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Practice Setup by daddia — Agent Skill

Name: Practice Setup
Rating: 4.5 (4 reviews)
Author: daddia

Practice Setup

This skill should be used when the user runs "/okr:practice-setup" (with optional --quick, --full, --redo, --check-integrations, or --resume), asks to "set up the okr plugin," "teach Claude our OKR process," or wants to redo that setup after the cadence, scoring approach, or cascade structure changes materially. Writes the shared org profile and the okr practice profile.

daddia Updated Sep 22, 2026

File contents

Practice Setup — okr

When to use

OKR cycle owners configuring philosophy, scoring, cadence, and cascade — explicit invocation only. Philosophy question matters more here than most plugins.

What this skill does not do

Does not draft OKRs — writes profiles only.
Does not auto-write without confirmation.
Does not modify other plugins' profiles.

Preconditions

Per ../../references/practice-setup-framework.md — detect setup, offer quick/full.

Provisional mode

Quick mode: philosophy and scoring must be explicit choices, not silent defaults; gaps flagged for set-targets and score-and-retro.

Trust spine

Structured-aggregation bands; explicit confirmation before write; commit vs aspirational philosophy recorded.

Shared framework

Read and follow ../../references/practice-setup-framework.md with okr as the plugin name.

Org profile: ~/.claude/plugins/config/claude-for-strategy/org-profile.md
Plugin profile: ~/.claude/plugins/config/claude-for-strategy/okr/CLAUDE.md

Plugin-specific interview

After the org layer is satisfied (planning cadence may already be in org profile):

Full mode: include a prior cycle's OKR set — objectives, KRs, targets, scores.
Philosophy — commit-only vs mixed; sandbagging/overreach history.
Scoring — scale and formula (default linear interpolation baseline→target).
Cadence — cycle length, check-in frequency, retro timing (check-in-nudge agent).
Cascade structure — levels and ceilings on objectives/KRs per level.
Cross-plugin: whether performance is installed (metric handoff to instrument-metrics).
Write profiles — Philosophy and Scoring must not be silent defaults.
Confirm and summarize.

Living profile

Profile paths: org org-profile.md; plugin okr/CLAUDE.md under ~/.claude/plugins/config/claude-for-strategy/.

Auto-apply: this skill only, after user confirms the summary.
Propose profile update: all other skills — org facts to org profile; OKR facts to plugin profile.

Output format

Summary of org + plugin changes; defaults used; files written on confirmation.

Worked example

Input: --quick, quarterly cycle, mixed commit/aspirational, linear scoring, 3 objectives max, performance plugin installed.

Summary excerpt: Philosophy mixed; aspirational band 0.6–0.7; check-in biweekly; cascade company→team; performance handoff enabled for instrument-metrics.

Quality checks before delivering

Philosophy and scoring explicitly recorded (not silent defaults)
Cascade levels and ceilings captured
Confirmation before write
Framework startup rules followed

Outputs

Follows plugin CLAUDE.md § Outputs. Next: draft-objectives or cascade.

---name: practice-setupdescription: This skill should be used when the user runs "/okr:practice-setup" (with optional --quick, --full, --redo, --check-integrations, or --resume), asks to "set up the okr plugin," "teach Claude our OKR process," or wants to redo that setup after the cadence, scoring approach, or cascade structure changes materially. Writes the shared org profile and the okr practice profile.---# Practice Setup — okr## When to useOKR cycle owners configuring philosophy, scoring, cadence, and cascade — explicit invocation only. Philosophy question matters more here than most plugins.## What this skill does not do- **Does not draft OKRs** — writes profiles only.- **Does not auto-write without confirmation.**- **Does not modify other plugins' profiles.**## PreconditionsPer `../../references/practice-setup-framework.md` — detect setup, offer quick/full.## Provisional modeQuick mode: philosophy and scoring must be explicit choices, not silent defaults; gaps flagged for `set-targets` and `score-and-retro`.## Trust spineStructured-aggregation bands; explicit confirmation before write; commit vs aspirational philosophy recorded.## Shared frameworkRead and follow `../../references/practice-setup-framework.md` with `okr` as the plugin name.**Org profile:** `~/.claude/plugins/config/claude-for-strategy/org-profile.md` **Plugin profile:** `~/.claude/plugins/config/claude-for-strategy/okr/CLAUDE.md`## Plugin-specific interviewAfter the org layer is satisfied (planning cadence may already be in org profile):1. **Full mode:** include a prior cycle's OKR set — objectives, KRs, targets, scores.2. **Philosophy** — commit-only vs mixed; sandbagging/overreach history.3. **Scoring** — scale and formula (default linear interpolation baseline→target).4. **Cadence** — cycle length, check-in frequency, retro timing (`check-in-nudge` agent).5. **Cascade structure** — levels and ceilings on objectives/KRs per level.6. **Cross-plugin:** whether `performance` is installed (metric handoff to `instrument-metrics`).7. **Write profiles** — Philosophy and Scoring must not be silent defaults.8. **Confirm and summarize.**## Living profile**Profile paths:** org `org-profile.md`; plugin `okr/CLAUDE.md` under `~/.claude/plugins/config/claude-for-strategy/`.- **Auto-apply:** this skill only, after user confirms the summary.- **Propose profile update:** all other skills — org facts to org profile; OKR facts to plugin profile.## Output formatSummary of org + plugin changes; defaults used; files written on confirmation.## Worked example**Input:** `--quick`, quarterly cycle, mixed commit/aspirational, linear scoring, 3 objectives max, performance plugin installed.**Summary excerpt:** Philosophy mixed; aspirational band 0.6–0.7; check-in biweekly; cascade company→team; performance handoff enabled for `instrument-metrics`.## Quality checks before delivering- [ ] Philosophy and scoring explicitly recorded (not silent defaults)- [ ] Cascade levels and ceilings captured- [ ] Confirmation before write- [ ] Framework startup rules followed## OutputsFollows plugin `CLAUDE.md` § Outputs. Next: `draft-objectives` or `cascade`.

Frequently asked questions