[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M727JR57WYQ01FJQF07TCENJ":3,"skill-same:01M727JR57WYQ01FJQF07TCENJ":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M727JR57WYQ01FJQF07TCENJ","foundation-okr-writer",null,"Drafts, reviews, rewrites, and coaches outcome-based OKR sets across team, department, product, or company scopes. Supports five entry modes (Guided default, One-Shot via --oneshot, Sustained Coach, Audit Only, Rewrite). Diagnoses empowered-team context and adjusts framing; refuses to fabricate baselines or targets; refuses to use OKR scores for compensation; reframes feature-delivery KRs into outcome KRs. Use when planning quarterly OKRs, translating strategy into team outcomes, reviewing draft OKRs for quality, or converting roadmap-as-OKR drafts into proper OKR sets.","product-on-purpose\u002Fpm-skills","product-on-purpose","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F253892650?v=4","01M7230Q4442AHBADCVFJCS277","Product on Purpose","01M727ASMTF77MQ3AKT3GKRQWM",805,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-okr-writer\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: foundation-okr-writer\ndescription: Drafts, reviews, rewrites, and coaches outcome-based OKR sets across team, department, product, or company scopes. Supports five entry modes (Guided default, One-Shot via --oneshot, Sustained Coach, Audit Only, Rewrite). Diagnoses empowered-team context and adjusts framing; refuses to fabricate baselines or targets; refuses to use OKR scores for compensation; reframes feature-delivery KRs into outcome KRs. Use when planning quarterly OKRs, translating strategy into team outcomes, reviewing draft OKRs for quality, or converting roadmap-as-OKR drafts into proper OKR sets.\nlicense: Apache-2.0\nmetadata:\n  classification: foundation\n  version: \"1.1.0\"\n  updated: 2026-04-30\n  category: coordination\n  frameworks: [triple-diamond, okrs, lean-startup]\n  author: product-on-purpose\n---\n\u003C!-- PM-Skills | https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills | Apache 2.0 -->\n# OKR Writer\n\nAn OKR (Objectives and Key Results) set is a quarterly artifact that translates strategy into measurable outcomes a team commits to drive. OKRs are a focus and learning system, not a project plan, KPI dashboard, performance review device, or roadmap wrapper. Done well, they make priorities explicit, force tradeoffs, enable cross-team alignment, and create visible evidence of progress. Done poorly, they generate roadmap theater, compensation gaming, and false precision.\n\nThis skill is a coach, not a template filler. It drafts, reviews, rewrites, and audits OKR sets against the empirical consensus drawn from Doerr (`Measure What Matters`), Wodtke (`Radical Focus`), Cagan (SVPG team objectives), Castro (outcome-vs-output), Grove (`High Output Management`), Torres (continuous discovery), and Gothelf and Seiden (`Outcomes Over Output`).\n\n## Supported Modes\n\nFive entry modes support different engagement levels. Mode is detected from user phrasing; default to Guided when ambiguous. State the detected mode at the start of the response.\n\n- `Guided` (default, moderate engagement) - brief diagnostic, draft, score against rubric, surface issues, ask user to confirm. Selected by phrasing like \"help me write OKRs for X.\"\n- `One-Shot` (low engagement) - produces a complete OKR set in one pass with all assumptions labeled. Selected by `--oneshot` flag or phrasing like \"just draft OKRs from this context.\"\n- `Sustained Coach` (high engagement) - iterative loop, one component at a time, re-scored each turn until quality threshold met. Selected by \"coach me through OKRs for X.\"\n- `Audit Only` - user pastes existing OKRs, skill scores and critiques, no new drafts unless user asks. Selected by \"review these OKRs.\"\n- `Rewrite` - convert flawed OKRs, feature lists, or roadmap items into outcome-shaped OKRs. Selected by \"fix these OKRs\" or \"convert this roadmap to OKRs.\"\n\n## When to Use\n\n- Planning OKRs at company, department, product, product-area, team, or initiative scope\n- Translating parent OKRs or strategy into team OKRs\n- Reviewing a draft OKR set for quality (Audit Only mode)\n- Reframing feature, roadmap, or initiative lists into outcome-based OKRs (Rewrite mode)\n- Preparing OKRs for stakeholder review\n- Identifying whether KRs are measurable and evidence-backed\n\n## When NOT to Use\n\n- You only need a dashboard spec - use `measure-dashboard-requirements`\n- You only need event tracking - use `measure-instrumentation-spec`\n- You only need an experiment - use `measure-experiment-design`\n- You only need a hypothesis - use `define-hypothesis`\n- The cycle has ended and you need formal scoring with evidence and learning synthesis - use `measure-okr-grader`\n- The team is purely business-as-usual and needs steady-state KPIs, not stretch outcomes - OKRs are the wrong artifact\n\n## Instructions\n\nWhen asked to write or review OKRs, follow these steps:\n\n1. **Detect mode**\n   Read the user's phrasing and classify into Guided, One-Shot, Sustained Coach, Audit Only, or Rewrite. Look for explicit signals (`--oneshot`, \"review these,\" \"fix these,\" \"coach me\"). Default to Guided when ambiguous. State the detected mode at the start of the response.\n\n2. **Run the empowered-team diagnostic** (skip in Audit Only when no new drafting is happening)\n   Ask briefly:\n   - Are features, projects, or dates already committed for this cycle?\n   - Can the team change initiatives mid-cycle if KRs are not moving?\n   - Who decides what gets built, this team or someone else?\n\n   Capture the answer as `empowerment_signal: empowered | feature-team | mixed | unknown`. This affects output framing in later steps. Do NOT refuse to proceed when feature-team signals are present; instead, plan to add a Disclosure section to the artifact.\n\n3. **Determine if OKRs are the right artifact**\n   If the request is really a project plan, KPI dashboard, launch checklist, hypothesis, experiment, or status update, redirect to the appropriate pm-skill or chain. Do not force OKR shape onto non-OKR work.\n\n4. **Classify operating context**\n   Capture scope (company | department | product | product-area | team | initiative), cycle (quarter | half | annual | launch window | custom), level, and OKR type (committed | aspirational | learning | operational_health | compliance_or_safety). Default cycle is quarterly when context is missing.\n\n5. **Extract or infer strategic intent**\n   Identify the parent objective, strategy pillar, customer problem, or business pressure that motivates this OKR set. If none is supplied, ask once before drafting.\n\n6. **Separate outcomes from work**\n   Move features, tasks, projects, launches, hiring counts, and activity counts into Initiatives. The OKR is what changes in the world; Initiatives are bets on how to make that change happen. Apply Castro's litmus test: \"if it can go in your backlog, it is not an outcome.\"\n\n7. **Draft or improve the Objective**\n   The Objective is qualitative, specific, directional, and cycle-appropriate. It describes a desired state change, not a project. It connects to strategy. It avoids embedded metrics (numbers belong in KRs). It avoids empty adjectives unless the artifact defines what they mean.\n\n8. **Draft or improve Key Results**\n   For each KR include: metric definition, baseline (or `recommended-to-measure` if missing), target, deadline, evidence source, owner where appropriate, indicator class (`leading | lagging | guardrail | health | evidence_generation`), and confidence (`high | medium | low | unknown`). Include a guardrail KR for any optimization that could harm a paired metric (engagement vs quality, growth vs retention, speed vs reliability).\n\n   Apply the constraint rules in the next section.\n\n9. **Map initiatives as bets**\n   Each initiative names which KR(s) it is expected to move and the assumption underlying that expectation. Initiatives are hypotheses, not commitments. Do not list initiatives as KRs.\n\n10. **Run the OKR Quality Audit**\n    Score the draft against the rubric below. Surface issues inline rather than burying them in an appendix. For each `risk` or `fail` rating, include a specific recommendation.\n\n11. **Apply the empowered-team Disclosure** (when needed)\n    If `empowerment_signal == feature-team` or `mixed`, add a Disclosure section: \"This OKR set frames pre-committed work as outcome bets. If the metrics do not move when the work ships, that is a learning, not a delivery failure. The team's lever this cycle is to keep shipping; the OKR's lever is to update next-cycle planning.\" Omit this section entirely when the signal is `empowered`.\n\n12. **Surface open questions**\n    Capture any decisions the user must make that the skill cannot resolve from context. Examples: KR measurement window extending past cycle close, initiative phasing decisions, cohort definition boundaries.\n\n13. **Note the source of truth**\n    The artifact is a planning input, not the canonical OKR system. Include a `source_of_truth` field pointing to the user's actual OKR tracker (company OKR doc, Confluence page, dashboard, dedicated platform, spreadsheet, or wherever the live status lives).\n\n14. **Finalize for direct use**\n    Remove all skill instruction commentary from the final artifact. The final output should be reader-facing.\n\n## Project Memory Contract\n\nActive only when `.claude\u002Fpm-skills.local.md` exists. With no file, ignore this section entirely\nand behave exactly as described above.\n\n- **Reads:** `phase`, `active_initiative`, and any prior `decision` artifacts, so objectives align to what has already been committed rather than restating it.\n- **Writes:** the OKR set as a `decision` artifact.\n- **Posture:** propose the entry and wait for confirmation before writing, unless\n  `memory_auto_append: true` is set, in which case append and echo what was written.\n- **Write discipline:** re-read the file immediately before writing, never from the copy that\n  produced the proposal. If it changed in between, merge your entry into the current state and\n  re-propose rather than overwriting; add only your own entry and leave every other field and\n  section byte-identical. Nothing enforces this at runtime and the file is gitignored, so a\n  careless whole-file write loses another session's work with no way to recover it.\n\nMemory never supplies a baseline or a target. The refusal to fabricate those stands regardless of what is recorded.\n## Constraint Rules (MUST \u002F MUST NOT)\n\nThese rules are non-negotiable. The skill enforces them in every mode.\n\n- **MUST** measure outcomes (customer behavior change, business KPI delta, operational health change), not features, tasks, milestones, or activity counts.\n- **MUST NOT** silently fabricate baselines, targets, current values, or benchmarks. Mark missing values explicitly as `assumption`, `placeholder`, `recommended-to-measure`, or `not-enough-evidence`.\n- **MUST NOT** use OKR scores as individual performance ratings or compensation inputs. If the user requests this, refuse and explain.\n- **MUST** include at least one guardrail or counter-metric KR for any KR that incentivizes growth, speed, or volume.\n- **MUST** treat the 0.6 to 0.7 sweet spot as applying ONLY to aspirational OKRs. Committed, compliance, safety, reliability, and contractual KRs target 1.0.\n- **MUST** default to team-level OKRs. Warn when individual OKRs are requested; explain the sandbagging and false-precision risks.\n- **MUST NOT** become the canonical source of truth. Always include a `source_of_truth` pointer to the user's actual OKR tracker.\n- **MUST** apply the empowered-team Disclosure when feature-team signals are present. Do NOT refuse the user; adjust the framing.\n\n## Quality Audit Rubric\n\nThe skill applies this rubric to every OKR set it drafts or reviews. Each criterion gets `pass`, `risk`, or `fail` with a one-line rationale.\n\n- Strategic fit: clear link to strategy, parent OKR, or customer problem\n- Objective quality: specific, qualitative, tradeoff-guiding (not a slogan, task, metric bundle, or project name)\n- KR outcome quality: measures outcome or behavior change (not tasks, features, or milestones)\n- Measurement quality: baseline, target, deadline, evidence source present (or marked placeholder)\n- Product influence: team can plausibly influence the outcome\n- Focus: 1 to 3 objectives, 2 to 4 KRs each\n- Guardrails: quality, reliability, or risk considered for any optimization KR\n- Alignment: parent, peer, dependency relationships clear\n- Operating rhythm: cycle, check-ins, review points explicit\n- Integrity: no compensation coupling, no fabricated data\n- Empowered-team Disclosure: included when feature-team signal present, omitted when empowered\n\n## Anti-Patterns the Skill Detects\n\nThe skill scans for these and either refuses, reframes, or surfaces them with a `fail` audit rating:\n\n- Feature-delivery KR (\"Launch X\" instead of \"Increase Y from A to B\") - reframe into outcome KR; move feature to Initiatives\n- Task-count KR (\"Complete 10 interviews\" without a learning outcome) - reframe or move to evidence-generation type\n- Vanity metric KR (metric improves without customer or business value) - flag and propose alternative\n- Activity objective (objective describes work, not change) - reframe\n- Metric-stuffed objective (objective is just KPIs glued together) - reframe\n- Too many OKRs (more than 3 objectives, more than 4 KRs per objective) - force ranking\n- Cascading theater (parent KR copied locally without ownership logic) - rewrite as networked alignment\n- Roadmap wrapper (OKRs reformat the roadmap) - full Rewrite mode\n- Missing baseline (target uninterpretable) - mark `recommended-to-measure`\n- Missing evidence source (no one knows where the score will come from) - mark `not-enough-evidence`\n- Lag-only product OKR (team owns revenue without product outcome) - add a leading product-outcome KR\n- No guardrail (optimization may damage quality, trust, retention) - add guardrail KR\n- Compensation coupling (people will sandbag or hide learning) - refuse and explain\n- Individual OKR default - default to team OKRs; warn if individual OKRs are requested\n- Unsupported benchmark (universal target without evidence) - flag and ask for source\n- Pre-PMF over-metricization (false quantitative precision when learning is the real objective) - reframe as learning OKR\n\n## Output Contract (v1.0.0)\n\n- All required sections present in canonical order: Context, Objective, Key Results, Initiatives as Bets, Guardrails and Health Checks, Alignment Notes, Quality Audit, Open Questions, Suggested Next Step\n- Disclosure section is present when `empowerment_signal == feature-team | mixed`, omitted when `empowered`\n- Every KR includes metric definition, baseline (or marked placeholder), target, deadline, evidence source, indicator class, and confidence\n- Initiatives are listed separately from KRs and explicitly tied to which KR(s) they aim to move\n- At least one guardrail KR exists for any optimization-style primary KR\n- Source-of-truth note is present and points to a non-skill location\n- Quality Audit covers all rubric criteria with explicit pass \u002F risk \u002F fail ratings\n- Markdown only output. No JSON.\n- Foundation classification: no `phase:` field in frontmatter; uses `classification: foundation`\n\n## Quality Checklist\n\nBefore finalizing, verify:\n\n- [ ] Mode detected and stated at the start of the response\n- [ ] Empowered-team diagnostic run when drafting; signal captured\n- [ ] All required sections present in canonical order\n- [ ] Disclosure section included when feature-team signal present\n- [ ] Every KR has metric, baseline (or placeholder), target, deadline, evidence source, indicator class, confidence\n- [ ] At least one guardrail KR for any optimization primary KR\n- [ ] Source-of-truth note present\n- [ ] No fabricated baselines or targets - missing values explicitly marked\n- [ ] No compensation-coupled framing\n- [ ] Quality Audit applied with explicit pass \u002F risk \u002F fail ratings\n- [ ] Anti-pattern catalog scanned - detected anti-patterns flagged or reframed\n- [ ] OKR type classified (committed | aspirational | learning | operational_health | compliance_or_safety)\n- [ ] Skill instruction commentary removed from final artifact\n- [ ] Markdown only - no JSON output\n\n## Examples\n\nSee `references\u002FEXAMPLE.md` for a completed OKR set in the storevine sample thread (Campaigns team, Q3 2026), demonstrating Guided mode on an empowered-team product context with a real cross-team alignment dependency. The companion `measure-okr-grader` skill handles end-of-cycle scoring; together they cover the full quarterly arc.\n","\u003C!-- PM-Skills | https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills | Apache 2.0 -->\n# OKR Writer\n\nAn OKR (Objectives and Key Results) set is a quarterly artifact that translates strategy into measurable outcomes a team commits to drive. OKRs are a focus and learning system, not a project plan, KPI dashboard, performance review device, or roadmap wrapper. Done well, they make priorities explicit, force tradeoffs, enable cross-team alignment, and create visible evidence of progress. Done poorly, they generate roadmap theater, compensation gaming, and false precision.\n\nThis skill is a coach, not a template filler. It drafts, reviews, rewrites, and audits OKR sets against the empirical consensus drawn from Doerr (`Measure What Matters`), Wodtke (`Radical Focus`), Cagan (SVPG team objectives), Castro (outcome-vs-output), Grove (`High Output Management`), Torres (continuous discovery), and Gothelf and Seiden (`Outcomes Over Output`).\n\n## Supported Modes\n\nFive entry modes support different engagement levels. Mode is detected from user phrasing; default to Guided when ambiguous. State the detected mode at the start of the response.\n\n- `Guided` (default, moderate engagement) - brief diagnostic, draft, score against rubric, surface issues, ask user to confirm. Selected by phrasing like \"help me write OKRs for X.\"\n- `One-Shot` (low engagement) - produces a complete OKR set in one pass with all assumptions labeled. Selected by `--oneshot` flag or phrasing like \"just draft OKRs from this context.\"\n- `Sustained Coach` (high engagement) - iterative loop, one component at a time, re-scored each turn until quality threshold met. Selected by \"coach me through OKRs for X.\"\n- `Audit Only` - user pastes existing OKRs, skill scores and critiques, no new drafts unless user asks. Selected by \"review these OKRs.\"\n- `Rewrite` - convert flawed OKRs, feature lists, or roadmap items into outcome-shaped OKRs. Selected by \"fix these OKRs\" or \"convert this roadmap to OKRs.\"\n\n## When to Use\n\n- Planning OKRs at company, department, product, product-area, team, or initiative scope\n- Translating parent OKRs or strategy into team OKRs\n- Reviewing a draft OKR set for quality (Audit Only mode)\n- Reframing feature, roadmap, or initiative lists into outcome-based OKRs (Rewrite mode)\n- Preparing OKRs for stakeholder review\n- Identifying whether KRs are measurable and evidence-backed\n\n## When NOT to Use\n\n- You only need a dashboard spec - use `measure-dashboard-requirements`\n- You only need event tracking - use `measure-instrumentation-spec`\n- You only need an experiment - use `measure-experiment-design`\n- You only need a hypothesis - use `define-hypothesis`\n- The cycle has ended and you need formal scoring with evidence and learning synthesis - use `measure-okr-grader`\n- The team is purely business-as-usual and needs steady-state KPIs, not stretch outcomes - OKRs are the wrong artifact\n\n## Instructions\n\nWhen asked to write or review OKRs, follow these steps:\n\n1. **Detect mode**\n   Read the user's phrasing and classify into Guided, One-Shot, Sustained Coach, Audit Only, or Rewrite. Look for explicit signals (`--oneshot`, \"review these,\" \"fix these,\" \"coach me\"). Default to Guided when ambiguous. State the detected mode at the start of the response.\n\n2. **Run the empowered-team diagnostic** (skip in Audit Only when no new drafting is happening)\n   Ask briefly:\n   - Are features, projects, or dates already committed for this cycle?\n   - Can the team change initiatives mid-cycle if KRs are not moving?\n   - Who decides what gets built, this team or someone else?\n\n   Capture the answer as `empowerment_signal: empowered | feature-team | mixed | unknown`. This affects output framing in later steps. Do NOT refuse to proceed when feature-team signals are present; instead, plan to add a Disclosure section to the artifact.\n\n3. **Determine if OKRs are the right artifact**\n   If the request is really a project plan, KPI dashboard, launch checklist, hypothesis, experiment, or status update, redirect to the appropriate pm-skill or chain. Do not force OKR shape onto non-OKR work.\n\n4. **Classify operating context**\n   Capture scope (company | department | product | product-area | team | initiative), cycle (quarter | half | annual | launch window | custom), level, and OKR type (committed | aspirational | learning | operational_health | compliance_or_safety). Default cycle is quarterly when context is missing.\n\n5. **Extract or infer strategic intent**\n   Identify the parent objective, strategy pillar, customer problem, or business pressure that motivates this OKR set. If none is supplied, ask once before drafting.\n\n6. **Separate outcomes from work**\n   Move features, tasks, projects, launches, hiring counts, and activity counts into Initiatives. The OKR is what changes in the world; Initiatives are bets on how to make that change happen. Apply Castro's litmus test: \"if it can go in your backlog, it is not an outcome.\"\n\n7. **Draft or improve the Objective**\n   The Objective is qualitative, specific, directional, and cycle-appropriate. It describes a desired state change, not a project. It connects to strategy. It avoids embedded metrics (numbers belong in KRs). It avoids empty adjectives unless the artifact defines what they mean.\n\n8. **Draft or improve Key Results**\n   For each KR include: metric definition, baseline (or `recommended-to-measure` if missing), target, deadline, evidence source, owner where appropriate, indicator class (`leading | lagging | guardrail | health | evidence_generation`), and confidence (`high | medium | low | unknown`). Include a guardrail KR for any optimization that could harm a paired metric (engagement vs quality, growth vs retention, speed vs reliability).\n\n   Apply the constraint rules in the next section.\n\n9. **Map initiatives as bets**\n   Each initiative names which KR(s) it is expected to move and the assumption underlying that expectation. Initiatives are hypotheses, not commitments. Do not list initiatives as KRs.\n\n10. **Run the OKR Quality Audit**\n    Score the draft against the rubric below. Surface issues inline rather than burying them in an appendix. For each `risk` or `fail` rating, include a specific recommendation.\n\n11. **Apply the empowered-team Disclosure** (when needed)\n    If `empowerment_signal == feature-team` or `mixed`, add a Disclosure section: \"This OKR set frames pre-committed work as outcome bets. If the metrics do not move when the work ships, that is a learning, not a delivery failure. The team's lever this cycle is to keep shipping; the OKR's lever is to update next-cycle planning.\" Omit this section entirely when the signal is `empowered`.\n\n12. **Surface open questions**\n    Capture any decisions the user must make that the skill cannot resolve from context. Examples: KR measurement window extending past cycle close, initiative phasing decisions, cohort definition boundaries.\n\n13. **Note the source of truth**\n    The artifact is a planning input, not the canonical OKR system. Include a `source_of_truth` field pointing to the user's actual OKR tracker (company OKR doc, Confluence page, dashboard, dedicated platform, spreadsheet, or wherever the live status lives).\n\n14. **Finalize for direct use**\n    Remove all skill instruction commentary from the final artifact. The final output should be reader-facing.\n\n## Project Memory Contract\n\nActive only when `.claude\u002Fpm-skills.local.md` exists. With no file, ignore this section entirely\nand behave exactly as described above.\n\n- **Reads:** `phase`, `active_initiative`, and any prior `decision` artifacts, so objectives align to what has already been committed rather than restating it.\n- **Writes:** the OKR set as a `decision` artifact.\n- **Posture:** propose the entry and wait for confirmation before writing, unless\n  `memory_auto_append: true` is set, in which case append and echo what was written.\n- **Write discipline:** re-read the file immediately before writing, never from the copy that\n  produced the proposal. If it changed in between, merge your entry into the current state and\n  re-propose rather than overwriting; add only your own entry and leave every other field and\n  section byte-identical. Nothing enforces this at runtime and the file is gitignored, so a\n  careless whole-file write loses another session's work with no way to recover it.\n\nMemory never supplies a baseline or a target. The refusal to fabricate those stands regardless of what is recorded.\n## Constraint Rules (MUST \u002F MUST NOT)\n\nThese rules are non-negotiable. The skill enforces them in every mode.\n\n- **MUST** measure outcomes (customer behavior change, business KPI delta, operational health change), not features, tasks, milestones, or activity counts.\n- **MUST NOT** silently fabricate baselines, targets, current values, or benchmarks. Mark missing values explicitly as `assumption`, `placeholder`, `recommended-to-measure`, or `not-enough-evidence`.\n- **MUST NOT** use OKR scores as individual performance ratings or compensation inputs. If the user requests this, refuse and explain.\n- **MUST** include at least one guardrail or counter-metric KR for any KR that incentivizes growth, speed, or volume.\n- **MUST** treat the 0.6 to 0.7 sweet spot as applying ONLY to aspirational OKRs. Committed, compliance, safety, reliability, and contractual KRs target 1.0.\n- **MUST** default to team-level OKRs. Warn when individual OKRs are requested; explain the sandbagging and false-precision risks.\n- **MUST NOT** become the canonical source of truth. Always include a `source_of_truth` pointer to the user's actual OKR tracker.\n- **MUST** apply the empowered-team Disclosure when feature-team signals are present. Do NOT refuse the user; adjust the framing.\n\n## Quality Audit Rubric\n\nThe skill applies this rubric to every OKR set it drafts or reviews. Each criterion gets `pass`, `risk`, or `fail` with a one-line rationale.\n\n- Strategic fit: clear link to strategy, parent OKR, or customer problem\n- Objective quality: specific, qualitative, tradeoff-guiding (not a slogan, task, metric bundle, or project name)\n- KR outcome quality: measures outcome or behavior change (not tasks, features, or milestones)\n- Measurement quality: baseline, target, deadline, evidence source present (or marked placeholder)\n- Product influence: team can plausibly influence the outcome\n- Focus: 1 to 3 objectives, 2 to 4 KRs each\n- Guardrails: quality, reliability, or risk considered for any optimization KR\n- Alignment: parent, peer, dependency relationships clear\n- Operating rhythm: cycle, check-ins, review points explicit\n- Integrity: no compensation coupling, no fabricated data\n- Empowered-team Disclosure: included when feature-team signal present, omitted when empowered\n\n## Anti-Patterns the Skill Detects\n\nThe skill scans for these and either refuses, reframes, or surfaces them with a `fail` audit rating:\n\n- Feature-delivery KR (\"Launch X\" instead of \"Increase Y from A to B\") - reframe into outcome KR; move feature to Initiatives\n- Task-count KR (\"Complete 10 interviews\" without a learning outcome) - reframe or move to evidence-generation type\n- Vanity metric KR (metric improves without customer or business value) - flag and propose alternative\n- Activity objective (objective describes work, not change) - reframe\n- Metric-stuffed objective (objective is just KPIs glued together) - reframe\n- Too many OKRs (more than 3 objectives, more than 4 KRs per objective) - force ranking\n- Cascading theater (parent KR copied locally without ownership logic) - rewrite as networked alignment\n- Roadmap wrapper (OKRs reformat the roadmap) - full Rewrite mode\n- Missing baseline (target uninterpretable) - mark `recommended-to-measure`\n- Missing evidence source (no one knows where the score will come from) - mark `not-enough-evidence`\n- Lag-only product OKR (team owns revenue without product outcome) - add a leading product-outcome KR\n- No guardrail (optimization may damage quality, trust, retention) - add guardrail KR\n- Compensation coupling (people will sandbag or hide learning) - refuse and explain\n- Individual OKR default - default to team OKRs; warn if individual OKRs are requested\n- Unsupported benchmark (universal target without evidence) - flag and ask for source\n- Pre-PMF over-metricization (false quantitative precision when learning is the real objective) - reframe as learning OKR\n\n## Output Contract (v1.0.0)\n\n- All required sections present in canonical order: Context, Objective, Key Results, Initiatives as Bets, Guardrails and Health Checks, Alignment Notes, Quality Audit, Open Questions, Suggested Next Step\n- Disclosure section is present when `empowerment_signal == feature-team | mixed`, omitted when `empowered`\n- Every KR includes metric definition, baseline (or marked placeholder), target, deadline, evidence source, indicator class, and confidence\n- Initiatives are listed separately from KRs and explicitly tied to which KR(s) they aim to move\n- At least one guardrail KR exists for any optimization-style primary KR\n- Source-of-truth note is present and points to a non-skill location\n- Quality Audit covers all rubric criteria with explicit pass \u002F risk \u002F fail ratings\n- Markdown only output. No JSON.\n- Foundation classification: no `phase:` field in frontmatter; uses `classification: foundation`\n\n## Quality Checklist\n\nBefore finalizing, verify:\n\n- [ ] Mode detected and stated at the start of the response\n- [ ] Empowered-team diagnostic run when drafting; signal captured\n- [ ] All required sections present in canonical order\n- [ ] Disclosure section included when feature-team signal present\n- [ ] Every KR has metric, baseline (or placeholder), target, deadline, evidence source, indicator class, confidence\n- [ ] At least one guardrail KR for any optimization primary KR\n- [ ] Source-of-truth note present\n- [ ] No fabricated baselines or targets - missing values explicitly marked\n- [ ] No compensation-coupled framing\n- [ ] Quality Audit applied with explicit pass \u002F risk \u002F fail ratings\n- [ ] Anti-pattern catalog scanned - detected anti-patterns flagged or reframed\n- [ ] OKR type classified (committed | aspirational | learning | operational_health | compliance_or_safety)\n- [ ] Skill instruction commentary removed from final artifact\n- [ ] Markdown only - no JSON output\n\n## Examples\n\nSee `references\u002FEXAMPLE.md` for a completed OKR set in the storevine sample thread (Campaigns team, Q3 2026), demonstrating Guided mode on an empowered-team product context with a real cross-team alignment dependency. The companion `measure-okr-grader` skill handles end-of-cycle scoring; together they cover the full quarterly arc.\n",{"name":5,"license":15,"metadata":24,"description":7},{"author":9,"updated":25,"version":26,"category":27,"frameworks":28,"classification":32},1777507200000,"1.1.0","coordination",[29,30,31],"triple-diamond","okrs","lean-startup","foundation","main","9b920db418c5bf641edea9afb4915a286e1d42ea","skills\u002Ffoundation-okr-writer",102,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills","https:\u002F\u002Fproduct-on-purpose.github.io\u002Fpm-skills\u002F","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose","2026-11-14 16:57:35",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add product-on-purpose\u002Fpm-skills --skill foundation-okr-writer",{"tool":47,"command":48},"bunx","bunx skills add product-on-purpose\u002Fpm-skills --skill foundation-okr-writer",{"tool":50,"command":51},"pnpm","pnpm dlx skills add product-on-purpose\u002Fpm-skills --skill foundation-okr-writer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-okr-writer\u002FSKILL.md",true,[55,61,65,69,73],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"evals\u002Foutput-scenarios\u002Factivation-quarter.md","REFERENCE","参考文档",2060,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-okr-writer\u002Fevals\u002Foutput-scenarios\u002Factivation-quarter.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Ftrigger-fixtures.json",4331,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-okr-writer\u002Fevals\u002Ftrigger-fixtures.json",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"HISTORY.md",1207,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-okr-writer\u002FHISTORY.md",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002FEXAMPLE.md",11788,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-okr-writer\u002Freferences\u002FEXAMPLE.md",{"path":74,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002FTEMPLATE.md",4647,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Ffoundation-okr-writer\u002Freferences\u002FTEMPLATE.md",[78,85,92,99,106,113],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M727QTD4J5TPP3EEYPXMGZE4","utility-update-pm-skills","Checks for newer pm-skills releases, compares local vs. latest version, previews what would change, and updates local files after user confirmation. Generates a structured update report documenting changed files, new capabilities, and the value delta between versions. Use when you want to bring a local pm-skills installation up to date.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-update-pm-skills\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M727QQSXYBZK7D29C80WMQ8M","utility-slideshow-creator","Generates professional presentations from a JSON deck specification using 18 slide types with dark\u002Flight variants, content-to-layout decision logic, and calibrated character limits. Ships with a default professional theme.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-slideshow-creator\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M727QKYD45K0PCJ591046TK2","utility-pm-workflow-orchestrator","Run an ordered sequence of pm-skills against one input, pausing for go\u002Fno-go and stopping on a failed or empty step. Accepts a saved prioritized action plan (Mode A) or an ad-hoc named chain (Mode B; the chain command routes here). Explicit invocation only; run --dry-run first while the native path is EXPERIMENTAL. To author a durable workflow instead, use utility-pm-workflow-builder.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-workflow-orchestrator\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M727QFN6W9M8JGVXNQMT5642","utility-pm-workflow-builder","Guides a contributor from a workflow idea to a complete Workflow Implementation Packet (draft workflow file, draft workflow command, cross-cutting update checklist) in a staging area for review. Runs overlap analysis against the existing workflows with a Why Gate, then helps select and sequence skills with authored handoffs. Use when creating a new multi-skill workflow or promoting a repeated ad-hoc chain into a durable one. To build a single skill instead, use utility-pm-skill-builder; to run a sequence without authoring anything, use the chain command or utility-pm-workflow-orchestrator.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-workflow-builder\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M727QCDS2WFTJPHXASSE5W6X","utility-pm-skill-validate","Audits an existing pm-skills skill against structural conventions and quality criteria. Produces a structured validation report with pass\u002Ffail checks, severity-graded findings, and actionable recommendations. Use when checking whether a skill meets repo standards before shipping or after making changes.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-validate\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M727Q8GW1AZWPNWXYH7WHG9F","utility-pm-skill-iterate","Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-iterate\u002FSKILL.md",[],[]]