[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M727QCDS2WFTJPHXASSE5W6X":3,"skill-same:01M727QCDS2WFTJPHXASSE5W6X":71},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M727QCDS2WFTJPHXASSE5W6X","utility-pm-skill-validate",null,"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.","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\u002Futility-pm-skill-validate\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: utility-pm-skill-validate\ndescription: 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.\nlicense: Apache-2.0\nmetadata:\n  classification: utility\n  version: \"1.2.0\"\n  updated: 2026-07-04\n  category: coordination\n  frameworks: [triple-diamond]\n  author: product-on-purpose\n---\n# PM Skill Validate\n\nThis skill audits an existing pm-skills skill against the repo's structural\nconventions and quality criteria. It produces a validation report that a\nhuman can scan and that `utility-pm-skill-iterate` can consume as input.\n\nThe validator checks two tiers:\n- **Tier 1 (Structural)** - deterministic checks that mirror CI: frontmatter,\n  naming, file presence, description word count.\n- **Tier 2 (Quality)** - LLM-assessed coherence checks: does the output\n  contract reference the template? Is the example complete? Are checklist\n  items testable?\n\n## When to Use\n\n- After creating a skill with `utility-pm-skill-builder`, before shipping\n- After manually editing a skill, to confirm it still passes conventions\n- Before running `utility-pm-skill-iterate`, to identify what needs improvement\n- When a convention changes, to audit which skills need updating (batch mode)\n- When reviewing a contributed skill for quality and completeness\n\n## When NOT to Use\n\n- To create a new skill from scratch -> use `utility-pm-skill-builder`\n- To fix or improve a skill -> use `utility-pm-skill-iterate` (feed it this report)\n- To run CI checks in a pipeline -> use `scripts\u002Flint-skills-frontmatter.sh`\n  (this skill is for interactive, deeper-than-CI validation)\n- To audit the whole catalog rather than one skill -> use `utility-pm-skill-auditor`. This skill goes deep on a single skill; the auditor goes wide across the repo and aggregates cross-cutting findings.\n\n## Instructions\n\nWhen asked to validate a skill, follow these steps:\n\n### Step 1: Identify the Target\n\nAccept the skill name in any form:\n- Directory name: `deliver-prd`\n- Full path: `skills\u002Fdeliver-prd\u002FSKILL.md`\n- Slash command: `deliver-prd`\n\nResolve to the canonical directory path: `skills\u002F{name}\u002F`.\n\nIf the skill directory does not exist, report immediately:\n\n```\n# Validation Report: {input}\nResult: FAIL\nSkill directory `skills\u002F{input}\u002F` does not exist.\n```\n\n**Batch mode:** If the input is `--all`, run Tier 1 structural checks\nacross all skills and produce a summary table (see Step 5). Do not run\nTier 2 in batch mode.\n\n### Step 2: Read Skill Files\n\nRead all files in the skill directory:\n\n| File | Required | Purpose |\n|------|----------|---------|\n| `SKILL.md` | yes | Frontmatter + instructions |\n| `references\u002FTEMPLATE.md` | yes | Output template |\n| `references\u002FEXAMPLE.md` | yes | Worked example |\n| `HISTORY.md` | no | Version history (if present) |\n| `evals\u002Ftrigger-fixtures.json` | no | Routing-eval fixtures (B-4); present for roster skills |\n| `evals\u002Foutput-scenarios\u002F*.md` | no | Output-quality scenarios (B-7); present for evaled skills |\n\nAlso read:\n- The corresponding command file: `commands\u002F{command-name}.md`\n- The AGENTS.md entry for this skill\n\nIf reading files is not possible (MCP\u002Fembedded environment), ask the user\nto paste the content of each file before proceeding (see Degraded Mode).\n\n### Step 3: Run Tier 1 - Structural Checks\n\nRun these deterministic checks. Each produces a `PASS` or `FAIL` line.\n\n| Check ID | What to check | Pass condition |\n|----------|--------------|----------------|\n| `frontmatter-at-byte-zero` | First line of SKILL.md, references\u002FTEMPLATE.md, references\u002FEXAMPLE.md is exactly `---` | Line 1 is the opening `---` fence with no preceding HTML comment, BOM, or whitespace. Severity: FAIL. Reference: `library\u002Fskill-output-samples\u002FSAMPLE_CREATION.md` Section 5. |\n| `name-match` | Frontmatter `name` matches directory name | Exact string match |\n| `description-present` | Frontmatter `description` exists | Non-empty value |\n| `description-length` | Description word count | 20-100 words |\n| `version-present` | Frontmatter `version` exists | Non-empty, valid SemVer |\n| `updated-present` | Frontmatter `updated` exists | Non-empty, ISO date |\n| `license-present` | Frontmatter `license` exists | Non-empty value |\n| `phase-classification` | Phase\u002Fclassification consistency | Domain has `phase:`, foundation\u002Futility has `classification:`, not both |\n| `template-exists` | `references\u002FTEMPLATE.md` exists | File present |\n| `template-sections` | TEMPLATE.md has sufficient structure | ≥3 `##` level-2 headers |\n| `example-exists` | `references\u002FEXAMPLE.md` exists | File present |\n| `command-exists` | Command file exists in `commands\u002F` | File present and references correct skill path |\n| `agents-entry` | AGENTS.md has an entry for this skill | Entry exists with matching `**Path:**` |\n| `eval-trigger-fixtures` | Routing fixtures present + well-formed (B-4) | If `evals\u002Ftrigger-fixtures.json` exists: `schema:1`, `skill` matches dir, >=16 queries, >=8 per class (trigger \u002F no-trigger), >=2 near-misses. If absent: INFO (not in the trigger-eval roster, or fixtures not yet authored). Authoritative gate: `scripts\u002Fcheck-trigger-fixtures.mjs`. |\n| `eval-output-scenarios` | Output scenarios present + well-formed (B-7) | If `evals\u002Foutput-scenarios\u002F*.md` exist: each has `scenario`\u002F`skill`\u002F`family` frontmatter, `skill` matches dir, `family` maps to an existing `docs\u002Finternal\u002Feval-rubrics\u002F{family}.md`, body >=100 chars. If absent: INFO (not yet output-evaled). Authoritative gate: `scripts\u002Fcheck-output-eval-assets.mjs`. |\n| `reciprocal-boundary-pointers` | Declared collision pairs cross-point (C-5) | If the skill appears in `COLLISION_PAIRS` (`scripts\u002Fcheck-trigger-fixtures.mjs`): its `When NOT to Use` names each partner AND each partner's `When NOT to Use` names it back. FAIL if a declared pair is one-directional. If not in any pair: PASS. Authoritative gate: `scripts\u002Fcheck-reciprocal-boundary-pointers.mjs`. |\n\n### Step 4: Run Tier 2 - Quality Checks\n\nRun these LLM-assessed checks. Each produces a `PASS`, `WARN`, or `INFO`\nline. Tier 2 findings are capped at `WARN` unless objectively grounded\n(placeholder leakage is the exception - it can `FAIL`).\n\n| Check ID | What to assess | How to assess | Max severity |\n|----------|---------------|---------------|-------------|\n| `output-contract-coverage` | SKILL.md references the template | Check for explicit reference to `references\u002FTEMPLATE.md` or \"use the template\" in an Output section. Accept either pattern as valid. WARN only if template is not referenced at all. | WARN |\n| `checklist-verifiability` | Quality checklist items are testable | Read each checklist item. Flag items that are vague (\"is good quality\") vs. specific (\"metrics are measurable\"). WARN if ≥2 items are vague. | WARN |\n| `example-completeness` | EXAMPLE.md fills all template sections | Compare `##` headers in TEMPLATE.md against `##` headers in EXAMPLE.md. WARN if EXAMPLE.md is missing sections that appear in the template. Also check for unresolved placeholders. Line count is informational only - report it but do not gate on it. | WARN |\n| `template-example-alignment` | EXAMPLE.md follows TEMPLATE.md structure | Compare section header ordering. WARN if EXAMPLE.md has sections in a different order or uses different header names than TEMPLATE.md. | WARN |\n| `description-actionability` | Description tells *when* to use the skill | Check for a trigger phrase like \"Use when...\" or \"Use for...\" in the frontmatter description. WARN if the description only says *what* the skill does without indicating *when* to use it. | WARN |\n| `instruction-clarity` | Instructions are numbered and imperative | Check for `### Step` headings or a numbered list pattern in the Instructions section. WARN if instructions are prose paragraphs without clear step structure. | WARN |\n| `placeholder-leakage` | No leftover scaffolding in any shipped file | Scan SKILL.md, TEMPLATE.md, and EXAMPLE.md for: `[Placeholder]` or `[Feature Name]` patterns, `\u003C!-- ... -->` HTML comments (except the license header), template guidance blockquotes that should have been removed, and authoring notes like \"TODO\" or \"FIXME\". FAIL if any are found - this is objectively grounded. | FAIL |\n| `when-not-to-use` | \"When NOT to Use\" section present and names neighbors | Check for a `When NOT to Use` section that names the skill's nearest neighbors (when to use them instead). WARN if the section is absent, or present but generic (no neighbor named). This became a convention in the v2.26.0 rewrites and underpins the reciprocity gate; `reciprocal-boundary-pointers` (Tier 1) is the deterministic backstop for declared collision pairs. | WARN |\n\n**Quality standard framing:** These checks validate against current library\nconventions - what the shipped library actually does today. Findings graded\nWARN or INFO represent the v2.8 quality standard that newer skills (built\nwith `utility-pm-skill-builder`) meet. Older skills may legitimately receive these\nfindings until iterated through the lifecycle.\n\n**Heading and dialect conventions:** for the authoritative section skeleton per\ndialect (classic, contract-shaped, tool-family) and the exact canon heading\nspellings, see [Skeleton Canon: The Three Sanctioned\nDialects](..\u002F..\u002Fsite\u002Fsrc\u002Fcontent\u002Fdocs\u002Fguides\u002Fcreating-pm-skills.md#skeleton-canon-the-three-sanctioned-dialects)\nin the skill-authoring guide. A skill whose headings or section set drift from\nits dialect's canon should be flagged in Recommendations even where no Tier 1\ncheck above already covers it; `scripts\u002Fcheck-heading-canon.mjs` is the eventual\ndeterministic backstop, shipping advisory until the full catalog is normalized.\n\n### Step 5: Produce the Validation Report\n\nAssemble the report using this exact structure. F-11 (`utility-pm-skill-iterate`)\nparses this report by section headings and pipe-delimited fields.\n\n```\n# Validation Report: {skill-name}\nDate: {YYYY-MM-DD}\nSkill version: {version from frontmatter}\nValidator version: 1.0.0\nReport schema: v1\nResult: {PASS | WARN | FAIL}\n\n## Summary\n{1-2 sentence overall assessment.}\nErrors: {n} | Warnings: {n} | Info: {n}\n\n> Tier 2 findings are heuristic quality assessments and may require human review.\n\n## Structural Checks\n- {STATUS} | structural | {check-id} | {message}\n- {STATUS} | structural | {check-id} | {message}\n...\n\n## Quality Checks\n- {STATUS} | quality | {check-id} | {message}\n- {STATUS} | quality | {check-id} | {message}\n...\n\n## Recommendations\n1. {STATUS} | {check-id} | Target: {file-path}\n   Action: {what to do}\n2. {STATUS} | {check-id} | Target: {file-path}\n   Action: {what to do}\n...\n```\n\n**Report rules:**\n\n- **Result** = worst severity found: any FAIL → `FAIL`, else any WARN → `WARN`, else `PASS`.\n- **Structural Checks**: one line per Tier 1 check. STATUS is `PASS` or `FAIL`.\n- **Quality Checks**: one line per Tier 2 check. STATUS is `PASS`, `WARN`, or `INFO`.\n- **Recommendations**: only include checks that did NOT pass. Each recommendation\n  includes the check ID, the target file path, and a specific action.\n- If all checks pass, the Recommendations section should say: \"No issues found.\"\n- Omit passing checks from Recommendations - only list findings that need action.\n\n**Batch mode output** (when input is `--all`):\n\nRun Tier 1 structural checks only across all skills. Produce a summary table:\n\n```\n# Batch Validation Summary\nDate: {YYYY-MM-DD}\nValidator version: 1.0.0\nReport schema: v1\nSkills checked: {n}\n\n| Skill | Result | Errors | Warnings |\n|-------|--------|--------|----------|\n| deliver-prd | PASS | 0 | 0 |\n| define-hypothesis | WARN | 0 | 1 |\n| foundation-persona | FAIL | 1 | 0 |\n...\n\nSkills passing: {n}\u002F{total}\nRun `utility-pm-skill-validate {skill}` for a detailed report.\n```\n\n## Degraded Mode\n\nIf you cannot read skill files directly (e.g., running via MCP or in an\nembedded environment without file system access):\n\n1. Ask the user to provide the content of each required file:\n   - `skills\u002F{name}\u002FSKILL.md`\n   - `skills\u002F{name}\u002Freferences\u002FTEMPLATE.md`\n   - `skills\u002F{name}\u002Freferences\u002FEXAMPLE.md`\n2. Run all checks against the provided content.\n3. Note in the report: \"Validated from user-provided content (file system not available).\"\n4. Batch mode is not available in degraded mode - single skill only.\n\n## Output Contract\n\nThe validator MUST produce a validation report following the format in Step 5.\n\nThe report:\n- Uses the exact section headings: `## Summary`, `## Structural Checks`,\n  `## Quality Checks`, `## Recommendations`\n- Uses pipe-delimited check lines: `STATUS | TIER | CHECK-ID | message`\n- Uses pipe-delimited recommendations: `STATUS | CHECK-ID | Target: path`\n  followed by `Action: description` on the next line\n- Includes `Report schema: v1` in the header for F-11 compatibility\n- Includes the Tier 2 caveat line in the Summary section\n\n## Quality Checklist\n\nBefore delivering the report, verify:\n\n- [ ] All Tier 1 structural checks were run (not skipped), including the eval-asset checks (`eval-trigger-fixtures`, `eval-output-scenarios`, `reciprocal-boundary-pointers`); absent eval assets are INFO, not FAIL, except a one-directional declared collision pair which FAILs\n- [ ] All Tier 2 quality checks were run (not skipped) - single skill mode only\n- [ ] Report follows the exact section and line format from Step 5\n- [ ] Every non-passing check appears in Recommendations with a target file path\n- [ ] Result field reflects the worst severity found\n- [ ] Tier 2 findings are capped at WARN (except placeholder-leakage which can FAIL)\n- [ ] No Tier 2 check was marked FAIL unless objectively grounded\n\n## Examples\n\nSee `references\u002FEXAMPLE.md` for a completed validation report demonstrating\nboth Tier 1 and Tier 2 checks against a real shipped skill.\n","# PM Skill Validate\n\nThis skill audits an existing pm-skills skill against the repo's structural\nconventions and quality criteria. It produces a validation report that a\nhuman can scan and that `utility-pm-skill-iterate` can consume as input.\n\nThe validator checks two tiers:\n- **Tier 1 (Structural)** - deterministic checks that mirror CI: frontmatter,\n  naming, file presence, description word count.\n- **Tier 2 (Quality)** - LLM-assessed coherence checks: does the output\n  contract reference the template? Is the example complete? Are checklist\n  items testable?\n\n## When to Use\n\n- After creating a skill with `utility-pm-skill-builder`, before shipping\n- After manually editing a skill, to confirm it still passes conventions\n- Before running `utility-pm-skill-iterate`, to identify what needs improvement\n- When a convention changes, to audit which skills need updating (batch mode)\n- When reviewing a contributed skill for quality and completeness\n\n## When NOT to Use\n\n- To create a new skill from scratch -> use `utility-pm-skill-builder`\n- To fix or improve a skill -> use `utility-pm-skill-iterate` (feed it this report)\n- To run CI checks in a pipeline -> use `scripts\u002Flint-skills-frontmatter.sh`\n  (this skill is for interactive, deeper-than-CI validation)\n- To audit the whole catalog rather than one skill -> use `utility-pm-skill-auditor`. This skill goes deep on a single skill; the auditor goes wide across the repo and aggregates cross-cutting findings.\n\n## Instructions\n\nWhen asked to validate a skill, follow these steps:\n\n### Step 1: Identify the Target\n\nAccept the skill name in any form:\n- Directory name: `deliver-prd`\n- Full path: `skills\u002Fdeliver-prd\u002FSKILL.md`\n- Slash command: `deliver-prd`\n\nResolve to the canonical directory path: `skills\u002F{name}\u002F`.\n\nIf the skill directory does not exist, report immediately:\n\n```\n# Validation Report: {input}\nResult: FAIL\nSkill directory `skills\u002F{input}\u002F` does not exist.\n```\n\n**Batch mode:** If the input is `--all`, run Tier 1 structural checks\nacross all skills and produce a summary table (see Step 5). Do not run\nTier 2 in batch mode.\n\n### Step 2: Read Skill Files\n\nRead all files in the skill directory:\n\n| File | Required | Purpose |\n|------|----------|---------|\n| `SKILL.md` | yes | Frontmatter + instructions |\n| `references\u002FTEMPLATE.md` | yes | Output template |\n| `references\u002FEXAMPLE.md` | yes | Worked example |\n| `HISTORY.md` | no | Version history (if present) |\n| `evals\u002Ftrigger-fixtures.json` | no | Routing-eval fixtures (B-4); present for roster skills |\n| `evals\u002Foutput-scenarios\u002F*.md` | no | Output-quality scenarios (B-7); present for evaled skills |\n\nAlso read:\n- The corresponding command file: `commands\u002F{command-name}.md`\n- The AGENTS.md entry for this skill\n\nIf reading files is not possible (MCP\u002Fembedded environment), ask the user\nto paste the content of each file before proceeding (see Degraded Mode).\n\n### Step 3: Run Tier 1 - Structural Checks\n\nRun these deterministic checks. Each produces a `PASS` or `FAIL` line.\n\n| Check ID | What to check | Pass condition |\n|----------|--------------|----------------|\n| `frontmatter-at-byte-zero` | First line of SKILL.md, references\u002FTEMPLATE.md, references\u002FEXAMPLE.md is exactly `---` | Line 1 is the opening `---` fence with no preceding HTML comment, BOM, or whitespace. Severity: FAIL. Reference: `library\u002Fskill-output-samples\u002FSAMPLE_CREATION.md` Section 5. |\n| `name-match` | Frontmatter `name` matches directory name | Exact string match |\n| `description-present` | Frontmatter `description` exists | Non-empty value |\n| `description-length` | Description word count | 20-100 words |\n| `version-present` | Frontmatter `version` exists | Non-empty, valid SemVer |\n| `updated-present` | Frontmatter `updated` exists | Non-empty, ISO date |\n| `license-present` | Frontmatter `license` exists | Non-empty value |\n| `phase-classification` | Phase\u002Fclassification consistency | Domain has `phase:`, foundation\u002Futility has `classification:`, not both |\n| `template-exists` | `references\u002FTEMPLATE.md` exists | File present |\n| `template-sections` | TEMPLATE.md has sufficient structure | ≥3 `##` level-2 headers |\n| `example-exists` | `references\u002FEXAMPLE.md` exists | File present |\n| `command-exists` | Command file exists in `commands\u002F` | File present and references correct skill path |\n| `agents-entry` | AGENTS.md has an entry for this skill | Entry exists with matching `**Path:**` |\n| `eval-trigger-fixtures` | Routing fixtures present + well-formed (B-4) | If `evals\u002Ftrigger-fixtures.json` exists: `schema:1`, `skill` matches dir, >=16 queries, >=8 per class (trigger \u002F no-trigger), >=2 near-misses. If absent: INFO (not in the trigger-eval roster, or fixtures not yet authored). Authoritative gate: `scripts\u002Fcheck-trigger-fixtures.mjs`. |\n| `eval-output-scenarios` | Output scenarios present + well-formed (B-7) | If `evals\u002Foutput-scenarios\u002F*.md` exist: each has `scenario`\u002F`skill`\u002F`family` frontmatter, `skill` matches dir, `family` maps to an existing `docs\u002Finternal\u002Feval-rubrics\u002F{family}.md`, body >=100 chars. If absent: INFO (not yet output-evaled). Authoritative gate: `scripts\u002Fcheck-output-eval-assets.mjs`. |\n| `reciprocal-boundary-pointers` | Declared collision pairs cross-point (C-5) | If the skill appears in `COLLISION_PAIRS` (`scripts\u002Fcheck-trigger-fixtures.mjs`): its `When NOT to Use` names each partner AND each partner's `When NOT to Use` names it back. FAIL if a declared pair is one-directional. If not in any pair: PASS. Authoritative gate: `scripts\u002Fcheck-reciprocal-boundary-pointers.mjs`. |\n\n### Step 4: Run Tier 2 - Quality Checks\n\nRun these LLM-assessed checks. Each produces a `PASS`, `WARN`, or `INFO`\nline. Tier 2 findings are capped at `WARN` unless objectively grounded\n(placeholder leakage is the exception - it can `FAIL`).\n\n| Check ID | What to assess | How to assess | Max severity |\n|----------|---------------|---------------|-------------|\n| `output-contract-coverage` | SKILL.md references the template | Check for explicit reference to `references\u002FTEMPLATE.md` or \"use the template\" in an Output section. Accept either pattern as valid. WARN only if template is not referenced at all. | WARN |\n| `checklist-verifiability` | Quality checklist items are testable | Read each checklist item. Flag items that are vague (\"is good quality\") vs. specific (\"metrics are measurable\"). WARN if ≥2 items are vague. | WARN |\n| `example-completeness` | EXAMPLE.md fills all template sections | Compare `##` headers in TEMPLATE.md against `##` headers in EXAMPLE.md. WARN if EXAMPLE.md is missing sections that appear in the template. Also check for unresolved placeholders. Line count is informational only - report it but do not gate on it. | WARN |\n| `template-example-alignment` | EXAMPLE.md follows TEMPLATE.md structure | Compare section header ordering. WARN if EXAMPLE.md has sections in a different order or uses different header names than TEMPLATE.md. | WARN |\n| `description-actionability` | Description tells *when* to use the skill | Check for a trigger phrase like \"Use when...\" or \"Use for...\" in the frontmatter description. WARN if the description only says *what* the skill does without indicating *when* to use it. | WARN |\n| `instruction-clarity` | Instructions are numbered and imperative | Check for `### Step` headings or a numbered list pattern in the Instructions section. WARN if instructions are prose paragraphs without clear step structure. | WARN |\n| `placeholder-leakage` | No leftover scaffolding in any shipped file | Scan SKILL.md, TEMPLATE.md, and EXAMPLE.md for: `[Placeholder]` or `[Feature Name]` patterns, `\u003C!-- ... -->` HTML comments (except the license header), template guidance blockquotes that should have been removed, and authoring notes like \"TODO\" or \"FIXME\". FAIL if any are found - this is objectively grounded. | FAIL |\n| `when-not-to-use` | \"When NOT to Use\" section present and names neighbors | Check for a `When NOT to Use` section that names the skill's nearest neighbors (when to use them instead). WARN if the section is absent, or present but generic (no neighbor named). This became a convention in the v2.26.0 rewrites and underpins the reciprocity gate; `reciprocal-boundary-pointers` (Tier 1) is the deterministic backstop for declared collision pairs. | WARN |\n\n**Quality standard framing:** These checks validate against current library\nconventions - what the shipped library actually does today. Findings graded\nWARN or INFO represent the v2.8 quality standard that newer skills (built\nwith `utility-pm-skill-builder`) meet. Older skills may legitimately receive these\nfindings until iterated through the lifecycle.\n\n**Heading and dialect conventions:** for the authoritative section skeleton per\ndialect (classic, contract-shaped, tool-family) and the exact canon heading\nspellings, see [Skeleton Canon: The Three Sanctioned\nDialects](..\u002F..\u002Fsite\u002Fsrc\u002Fcontent\u002Fdocs\u002Fguides\u002Fcreating-pm-skills.md#skeleton-canon-the-three-sanctioned-dialects)\nin the skill-authoring guide. A skill whose headings or section set drift from\nits dialect's canon should be flagged in Recommendations even where no Tier 1\ncheck above already covers it; `scripts\u002Fcheck-heading-canon.mjs` is the eventual\ndeterministic backstop, shipping advisory until the full catalog is normalized.\n\n### Step 5: Produce the Validation Report\n\nAssemble the report using this exact structure. F-11 (`utility-pm-skill-iterate`)\nparses this report by section headings and pipe-delimited fields.\n\n```\n# Validation Report: {skill-name}\nDate: {YYYY-MM-DD}\nSkill version: {version from frontmatter}\nValidator version: 1.0.0\nReport schema: v1\nResult: {PASS | WARN | FAIL}\n\n## Summary\n{1-2 sentence overall assessment.}\nErrors: {n} | Warnings: {n} | Info: {n}\n\n> Tier 2 findings are heuristic quality assessments and may require human review.\n\n## Structural Checks\n- {STATUS} | structural | {check-id} | {message}\n- {STATUS} | structural | {check-id} | {message}\n...\n\n## Quality Checks\n- {STATUS} | quality | {check-id} | {message}\n- {STATUS} | quality | {check-id} | {message}\n...\n\n## Recommendations\n1. {STATUS} | {check-id} | Target: {file-path}\n   Action: {what to do}\n2. {STATUS} | {check-id} | Target: {file-path}\n   Action: {what to do}\n...\n```\n\n**Report rules:**\n\n- **Result** = worst severity found: any FAIL → `FAIL`, else any WARN → `WARN`, else `PASS`.\n- **Structural Checks**: one line per Tier 1 check. STATUS is `PASS` or `FAIL`.\n- **Quality Checks**: one line per Tier 2 check. STATUS is `PASS`, `WARN`, or `INFO`.\n- **Recommendations**: only include checks that did NOT pass. Each recommendation\n  includes the check ID, the target file path, and a specific action.\n- If all checks pass, the Recommendations section should say: \"No issues found.\"\n- Omit passing checks from Recommendations - only list findings that need action.\n\n**Batch mode output** (when input is `--all`):\n\nRun Tier 1 structural checks only across all skills. Produce a summary table:\n\n```\n# Batch Validation Summary\nDate: {YYYY-MM-DD}\nValidator version: 1.0.0\nReport schema: v1\nSkills checked: {n}\n\n| Skill | Result | Errors | Warnings |\n|-------|--------|--------|----------|\n| deliver-prd | PASS | 0 | 0 |\n| define-hypothesis | WARN | 0 | 1 |\n| foundation-persona | FAIL | 1 | 0 |\n...\n\nSkills passing: {n}\u002F{total}\nRun `utility-pm-skill-validate {skill}` for a detailed report.\n```\n\n## Degraded Mode\n\nIf you cannot read skill files directly (e.g., running via MCP or in an\nembedded environment without file system access):\n\n1. Ask the user to provide the content of each required file:\n   - `skills\u002F{name}\u002FSKILL.md`\n   - `skills\u002F{name}\u002Freferences\u002FTEMPLATE.md`\n   - `skills\u002F{name}\u002Freferences\u002FEXAMPLE.md`\n2. Run all checks against the provided content.\n3. Note in the report: \"Validated from user-provided content (file system not available).\"\n4. Batch mode is not available in degraded mode - single skill only.\n\n## Output Contract\n\nThe validator MUST produce a validation report following the format in Step 5.\n\nThe report:\n- Uses the exact section headings: `## Summary`, `## Structural Checks`,\n  `## Quality Checks`, `## Recommendations`\n- Uses pipe-delimited check lines: `STATUS | TIER | CHECK-ID | message`\n- Uses pipe-delimited recommendations: `STATUS | CHECK-ID | Target: path`\n  followed by `Action: description` on the next line\n- Includes `Report schema: v1` in the header for F-11 compatibility\n- Includes the Tier 2 caveat line in the Summary section\n\n## Quality Checklist\n\nBefore delivering the report, verify:\n\n- [ ] All Tier 1 structural checks were run (not skipped), including the eval-asset checks (`eval-trigger-fixtures`, `eval-output-scenarios`, `reciprocal-boundary-pointers`); absent eval assets are INFO, not FAIL, except a one-directional declared collision pair which FAILs\n- [ ] All Tier 2 quality checks were run (not skipped) - single skill mode only\n- [ ] Report follows the exact section and line format from Step 5\n- [ ] Every non-passing check appears in Recommendations with a target file path\n- [ ] Result field reflects the worst severity found\n- [ ] Tier 2 findings are capped at WARN (except placeholder-leakage which can FAIL)\n- [ ] No Tier 2 check was marked FAIL unless objectively grounded\n\n## Examples\n\nSee `references\u002FEXAMPLE.md` for a completed validation report demonstrating\nboth Tier 1 and Tier 2 checks against a real shipped skill.\n",{"name":5,"license":15,"metadata":24,"description":7},{"author":9,"updated":25,"version":26,"category":27,"frameworks":28,"classification":30},1783123200000,"1.2.0","coordination",[29],"triple-diamond","utility","main","9b920db418c5bf641edea9afb4915a286e1d42ea","skills\u002Futility-pm-skill-validate",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":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add product-on-purpose\u002Fpm-skills --skill utility-pm-skill-validate",{"tool":45,"command":46},"bunx","bunx skills add product-on-purpose\u002Fpm-skills --skill utility-pm-skill-validate",{"tool":48,"command":49},"pnpm","pnpm dlx skills add product-on-purpose\u002Fpm-skills --skill utility-pm-skill-validate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-validate\u002FSKILL.md",true,[53,59,63,67],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"evals\u002Ftrigger-fixtures.json","REFERENCE","参考文档",5944,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-validate\u002Fevals\u002Ftrigger-fixtures.json",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"HISTORY.md",3470,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-validate\u002FHISTORY.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002FEXAMPLE.md",3984,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-validate\u002Freferences\u002FEXAMPLE.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002FTEMPLATE.md",1231,"https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-validate\u002Freferences\u002FTEMPLATE.md",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M727Q49TZERFYHQJTT8DCRK0","utility-pm-skill-builder","Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions. Runs gap analysis, validates through a Why Gate, classifies by type and phase, generates draft files, and writes to a staging area for review before promotion.","https:\u002F\u002Fgithub.com\u002Fproduct-on-purpose\u002Fpm-skills\u002Fblob\u002Fmain\u002Fskills\u002Futility-pm-skill-builder\u002FSKILL.md",[],[]]