[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MP81MKJG763NGPQ9M0FX5W":3,"skill-same:01M6MP81MKJG763NGPQ9M0FX5W":59},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6MP81MKJG763NGPQ9M0FX5W","brainstorming",null,"Use before any feature work — explores intent, requirements, and design. Produces HOTL contracts (intent, verification, governance) before implementation.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fbrainstorming\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29],"design","governance","verification","work","use","implementation","intent","contracts","requirements","feature","hotl","2026-11-10 10:12:30",false,"---\nname: brainstorming\ndescription: \"Use before any feature work — explores intent, requirements, and design. Produces HOTL contracts (intent, verification, governance) before implementation.\"\n---\n\n# HOTL Brainstorming\n\n## Overview\n\nTurn ideas into designs with explicit HOTL contracts. Ask questions one at a time. Present design for approval before any implementation.\n\n\u003CHARD-GATE>\nDo NOT write any implementation code until the design is approved and writing-plans has generated the executable workflow.\n\u003C\u002FHARD-GATE>\n\n## Process\n\n1. **Explore context (cheap preflight first)**\n\n   **Phase 1 — Cheap preflight** (Glob only, current project directory):\n   - If user's message references a doc path → read it\n   - Check for canonical design docs in `docs\u002Fdesigns\u002F*.md`\n   - Check for legacy design docs in `docs\u002Fplans\u002F*.md`\n   - Check for source code, config manifests, or project-specific config files\n   - **\"Relevant context\" means:** design docs, source code, configuration manifests, or project-specific config. Files like `README.md`, `.gitignore`, `LICENSE`, and scaffolding boilerplate do **not** count.\n\n   **Phase 2 — Branch on result:**\n   - **Relevant local context found:** Read the most recent 1-2 design docs from canonical or legacy locations, inspect only relevant in-project files, and optionally review recent commits (only if the directory is a git repo).\n   - **No relevant local context found:** State: \"This appears to be a greenfield or effectively empty project, so I'm skipping deep context scanning and moving to clarifying questions.\" Proceed directly to step 2.\n\n   **Hard rule:** Never scan parent directories, sibling folders, or workspace-wide paths unless the user explicitly provides a path.\n2. **Determine scope** — decide between `feature`, `phase`, or `initiative` before the clarifying-questions loop. Scope shapes every downstream step: output path, contract structure, depth of inquiry.\n\n   **Scope choices:**\n\n   - **`feature`** — one feature, one bug fix, one refactor. Output: `docs\u002Fdesigns\u002FYYYY-MM-DD-\u003Cslug>-design.md` (dated, tactical).\n   - **`phase`** — one slice of a multi-phase initiative. Same output family as feature: `docs\u002Fdesigns\u002FYYYY-MM-DD-phase-N-\u003Cslug>-design.md`.\n   - **`initiative`** — a multi-phase project (v1\u002Fv2, platform migration, enterprise rebuild). Output: `docs\u002Fdesigns\u002F\u003Ctopic>.md` (undated, durable, strategic).\n\n   **Default: feature.** If the user's initial message clearly describes a feature, proceed with `feature` scope without blocking for input. Optionally acknowledge in one line (\"Treating as feature scope; say so if this should be a phase or initiative\"). Do not pause the flow.\n\n   **Ask the scope question explicitly when the request is ambiguous or multi-phase** (e.g., \"migrate v1 to v2\", \"platform rebuild\", \"rework across services\"). Present the three choices with `feature` as the pre-filled default and wait for the user's answer before continuing.\n\n   **For initiative scope, load the strategic-design template once at session start.** Resolve `adapters\u002Fstrategic-design.template.md` in this order (same pattern used for `document-lint.sh` and `hotl-config.sh` — see `skills\u002Fdocument-review\u002FSKILL.md`):\n\n   1. If you are working in the `hotl-plugin` repo itself, use `adapters\u002Fstrategic-design.template.md`\n   2. Codex native-skills install: `~\u002F.codex\u002Fhotl\u002Fadapters\u002Fstrategic-design.template.md`\n   3. Codex plugin install: `~\u002F.codex\u002Fplugins\u002Fhotl-source\u002Fadapters\u002Fstrategic-design.template.md`\n   4. Codex plugin cache fallback: `~\u002F.codex\u002Fplugins\u002Fcache\u002Fcodex-plugins\u002Fhotl\u002F*\u002Fadapters\u002Fstrategic-design.template.md`\n   5. Cline install fallback: `~\u002F.cline\u002Fhotl\u002Fadapters\u002Fstrategic-design.template.md`\n   6. Claude Code plugin fallback: `~\u002F.claude\u002Fplugins\u002Fhotl\u002Fadapters\u002Fstrategic-design.template.md`\n\n   Read the resolved template once at session start — its section structure (problem, vision, non-goals, stakeholders, architecture, phase breakdown, risks) becomes the skeleton of the design doc you produce. Do not assume `adapters\u002Fstrategic-design.template.md` exists in the repo being worked on.\n\n   **For initiative scope, resolve the output directory via `hotl-config-resolve.sh`:**\n\n   ```bash\n   bash \u003Cresolved-hotl-config-resolve.sh> get designs_dir --default=docs\u002Fdesigns\n   ```\n\n   Resolve `hotl-config-resolve.sh` via the same six-location order. The default is `docs\u002Fdesigns` when no `.hotl\u002Fconfig.yml` is present; opted-in projects may override via that config.\n\n3. **Ask clarifying questions** — one at a time, understand purpose\u002Fconstraints\u002Fsuccess criteria. Prefer multiple-choice when the likely answer space is known (e.g., \"Which constraints apply? (a) Must not break existing API (b) Backward-compatible (c) Performance-sensitive (d) Other\"). Fall back to open-ended only when the problem is unusual or exploratory.\n4. **Propose 2-3 approaches** — with trade-offs and recommendation\n5. **Present design in sections** — get approval after each section\n6. **Define HOTL contracts** — always include all three:\n\n### Intent Contract\n```\nintent: [one sentence goal]\nconstraints: [what must not change\u002Fbreak]\nsuccess_criteria: [how we know it's done]\nrisk_level: low | medium | high\n```\n\n### Verification Contract\n```\nverify_steps:\n  - run tests: [test command]\n  - check: [what to inspect]\n  - confirm: [success signal]\n```\n\n### Governance Contract\n```\napproval_gates: [list of steps requiring human review]\nrollback: [how to undo if something goes wrong]\nownership: [who is accountable]\n```\n\n7. **Write design doc** — path depends on scope:\n   - `feature` scope: save to `docs\u002Fdesigns\u002FYYYY-MM-DD-\u003Cslug>-design.md` (dated, tactical).\n   - `phase` scope: save to `docs\u002Fdesigns\u002FYYYY-MM-DD-phase-N-\u003Cslug>-design.md` (dated, tactical).\n   - `initiative` scope: save to `\u003Cdesigns_dir>\u002F\u003Ctopic>.md` (undated, durable). `\u003Cdesigns_dir>` is the value returned by the step-2 resolver (default `docs\u002Fdesigns`). Follow the section structure of the strategic template loaded in step 2.\n\n   **Always write YAML frontmatter with the HOTL marker.** Every saved design doc MUST start with frontmatter declaring at minimum:\n\n   ```yaml\n   ---\n   design_type: \u003Cfeature|phase|initiative>   # match the scope chosen in step 2\n   created_at: YYYY-MM-DD\n   ---\n   ```\n\n   The `design_type` field is the deterministic signal that opts the doc into HOTL strict lint (`document-lint.sh` SKIPs unmarked docs). Without it, the doc is treated as non-HOTL and routes through generic AI review only.\n8. **Self-check the design doc** — before presenting for human approval, review the saved design doc for: missing constraints, vague success criteria, contract mismatches (do verification steps actually test the intent?), risk_level appropriateness, and scope creep. Fix any issues found. Lightweight: 1-2 passes by default, max 3 only if real issues are found. Do not ask the user to review — this is an internal quality pass.\n\n   **Run document-lint on the saved design doc** as part of this self-check. Resolve `scripts\u002Fdocument-lint.sh` via the standard six-location order, then:\n\n   ```bash\n   bash \u003Cresolved-document-lint.sh> \u003Csaved-design-path>\n   ```\n\n   The lint emits two stable warning shapes for feature\u002Fphase docs:\n\n   ```\n   category=structure severity=warning design_type=\u003Cresolved>\n   message=\"missing required section: ## \u003Cname>\"\n\n   category=implementation-leakage severity=warning design_type=\u003Cresolved> line=\u003Cn>\n   message=\"\u003Cshort description>\"\n   ```\n\n   Apply the **5-step self-check behavior** to surfaced warnings:\n\n   1. Run `document-lint.sh` on the saved design doc.\n   2. Surface warnings to the user before asking for approval.\n   3. Fix warnings that clearly violate the design\u002Fplan boundary.\n   4. Justify a warning only when the flagged content sits inside a clearly delimited example block — a Markdown blockquote (`> Example: ...`) or a section whose heading includes the word `Example`. All other findings must be fixed.\n   5. Do not block approval unless the user decides the warnings are blocking.\n\n   **Loop bound:** This 5-step procedure runs at most once per self-check pass; the parent self-check (step 8) caps the total at 3 passes before stopping.\n\n   Lint exits 0 even when these warnings are emitted (warning-only contract this pass). Initiative \u002F architecture \u002F contract \u002F reference docs receive neither check; the lint emits no `category=structure` or `category=implementation-leakage` lines for them.\n9. **Invoke writing-plans** — transition to implementation planning (feature\u002Fphase scope only; initiative designs decompose into child phase plans that each go through their own brainstorming → writing-plans cycle).\n\n## Doc-discipline rules\n\nFor `design_type ∈ {feature, phase}` docs, write the body using these **seven required sections in fixed order**. Phase 1 lint enforces presence only; out-of-order or extra sections are not flagged this pass but the prose order below is the canonical convention:\n\n1. `## Intent Contract`\n2. `## Verification Contract`\n3. `## Governance Contract`\n4. `## Scope` (in \u002F out, table form preferred)\n5. `## Decisions` (# \u002F decision \u002F choice \u002F rejected alternatives, table form preferred)\n6. `## Surface` (APIs \u002F storage \u002F components \u002F files-touched, paragraph each)\n7. `## Risks & Open Questions`\n\nInitiative \u002F architecture \u002F contract \u002F reference docs are durable references; they may legitimately include deeper technical shape. The lint defers any rules for them this pass.\n\n### Implementation-leakage anti-patterns\n\nA design doc says **shape**; the workflow file and the code say **exact bytes**. The following patterns belong in `writing-plans` output (or in code itself), not in the design — the lint warns when they appear in feature\u002Fphase design bodies:\n\n| Pattern | Example | Why it doesn't belong in design |\n|---|---|---|\n| File:line references | `cli.py:16`, `auth.ts:204` | Line numbers rot the moment code moves; pin to workflow steps instead. |\n| Long fenced code blocks (>10 content lines) | a 30-line Python snippet | Design shows shape; full implementation goes in workflow tasks or code. |\n| Dense flag lines (≥6 `--` tokens) | `docker run --network=none --cap-drop=ALL --read-only --tmpfs \u002Ftmp ...` | Argv assertions go in workflow steps and tests, not design surface. |\n\nWhen a design doc must reference one of these (e.g., as an illustrative example), the warning is acceptable and the agent should justify it during the self-check (step 8) rather than rewrite the design.\n\n### Doc-type detection\n\n1. **Frontmatter is the deterministic signal.** A doc is HOTL-managed only when its frontmatter declares `design_type:` (one of `feature | phase | initiative | architecture | contract | reference`) or `hotl_managed: true`. The brainstorming skill always writes the marker; ad-hoc docs in `docs\u002Fdesigns\u002F` are treated as non-HOTL by default.\n2. **Filename pattern is a hint, not a classifier.** Dated `YYYY-MM-DD-*-design.md` is the conventional pattern for HOTL-authored docs, but the lint still requires a frontmatter marker before applying HOTL rules. Without a marker, `document-lint.sh` SKIPs cleanly with a clear message and exits 0.\n3. **Unmarked design-folder docs route to AI review.** `hotl:document-review` runs a generic-rubric AI review on them; `document-lint.sh` skips them. To opt a hand-authored doc into HOTL strict review, add `design_type: \u003Crecognized-value>` or `hotl_managed: true` to its frontmatter.\n\n## Key Principles\n\n- One question at a time — prefer multiple-choice when practical\n- YAGNI ruthlessly — remove unnecessary features\n- Always propose alternatives before settling\n- `risk_level: high` = security, auth, privacy, billing (always human-gated)\n","# HOTL Brainstorming\n\n## Overview\n\nTurn ideas into designs with explicit HOTL contracts. Ask questions one at a time. Present design for approval before any implementation.\n\n\u003CHARD-GATE>\nDo NOT write any implementation code until the design is approved and writing-plans has generated the executable workflow.\n\u003C\u002FHARD-GATE>\n\n## Process\n\n1. **Explore context (cheap preflight first)**\n\n   **Phase 1 — Cheap preflight** (Glob only, current project directory):\n   - If user's message references a doc path → read it\n   - Check for canonical design docs in `docs\u002Fdesigns\u002F*.md`\n   - Check for legacy design docs in `docs\u002Fplans\u002F*.md`\n   - Check for source code, config manifests, or project-specific config files\n   - **\"Relevant context\" means:** design docs, source code, configuration manifests, or project-specific config. Files like `README.md`, `.gitignore`, `LICENSE`, and scaffolding boilerplate do **not** count.\n\n   **Phase 2 — Branch on result:**\n   - **Relevant local context found:** Read the most recent 1-2 design docs from canonical or legacy locations, inspect only relevant in-project files, and optionally review recent commits (only if the directory is a git repo).\n   - **No relevant local context found:** State: \"This appears to be a greenfield or effectively empty project, so I'm skipping deep context scanning and moving to clarifying questions.\" Proceed directly to step 2.\n\n   **Hard rule:** Never scan parent directories, sibling folders, or workspace-wide paths unless the user explicitly provides a path.\n2. **Determine scope** — decide between `feature`, `phase`, or `initiative` before the clarifying-questions loop. Scope shapes every downstream step: output path, contract structure, depth of inquiry.\n\n   **Scope choices:**\n\n   - **`feature`** — one feature, one bug fix, one refactor. Output: `docs\u002Fdesigns\u002FYYYY-MM-DD-\u003Cslug>-design.md` (dated, tactical).\n   - **`phase`** — one slice of a multi-phase initiative. Same output family as feature: `docs\u002Fdesigns\u002FYYYY-MM-DD-phase-N-\u003Cslug>-design.md`.\n   - **`initiative`** — a multi-phase project (v1\u002Fv2, platform migration, enterprise rebuild). Output: `docs\u002Fdesigns\u002F\u003Ctopic>.md` (undated, durable, strategic).\n\n   **Default: feature.** If the user's initial message clearly describes a feature, proceed with `feature` scope without blocking for input. Optionally acknowledge in one line (\"Treating as feature scope; say so if this should be a phase or initiative\"). Do not pause the flow.\n\n   **Ask the scope question explicitly when the request is ambiguous or multi-phase** (e.g., \"migrate v1 to v2\", \"platform rebuild\", \"rework across services\"). Present the three choices with `feature` as the pre-filled default and wait for the user's answer before continuing.\n\n   **For initiative scope, load the strategic-design template once at session start.** Resolve `adapters\u002Fstrategic-design.template.md` in this order (same pattern used for `document-lint.sh` and `hotl-config.sh` — see `skills\u002Fdocument-review\u002FSKILL.md`):\n\n   1. If you are working in the `hotl-plugin` repo itself, use `adapters\u002Fstrategic-design.template.md`\n   2. Codex native-skills install: `~\u002F.codex\u002Fhotl\u002Fadapters\u002Fstrategic-design.template.md`\n   3. Codex plugin install: `~\u002F.codex\u002Fplugins\u002Fhotl-source\u002Fadapters\u002Fstrategic-design.template.md`\n   4. Codex plugin cache fallback: `~\u002F.codex\u002Fplugins\u002Fcache\u002Fcodex-plugins\u002Fhotl\u002F*\u002Fadapters\u002Fstrategic-design.template.md`\n   5. Cline install fallback: `~\u002F.cline\u002Fhotl\u002Fadapters\u002Fstrategic-design.template.md`\n   6. Claude Code plugin fallback: `~\u002F.claude\u002Fplugins\u002Fhotl\u002Fadapters\u002Fstrategic-design.template.md`\n\n   Read the resolved template once at session start — its section structure (problem, vision, non-goals, stakeholders, architecture, phase breakdown, risks) becomes the skeleton of the design doc you produce. Do not assume `adapters\u002Fstrategic-design.template.md` exists in the repo being worked on.\n\n   **For initiative scope, resolve the output directory via `hotl-config-resolve.sh`:**\n\n   ```bash\n   bash \u003Cresolved-hotl-config-resolve.sh> get designs_dir --default=docs\u002Fdesigns\n   ```\n\n   Resolve `hotl-config-resolve.sh` via the same six-location order. The default is `docs\u002Fdesigns` when no `.hotl\u002Fconfig.yml` is present; opted-in projects may override via that config.\n\n3. **Ask clarifying questions** — one at a time, understand purpose\u002Fconstraints\u002Fsuccess criteria. Prefer multiple-choice when the likely answer space is known (e.g., \"Which constraints apply? (a) Must not break existing API (b) Backward-compatible (c) Performance-sensitive (d) Other\"). Fall back to open-ended only when the problem is unusual or exploratory.\n4. **Propose 2-3 approaches** — with trade-offs and recommendation\n5. **Present design in sections** — get approval after each section\n6. **Define HOTL contracts** — always include all three:\n\n### Intent Contract\n```\nintent: [one sentence goal]\nconstraints: [what must not change\u002Fbreak]\nsuccess_criteria: [how we know it's done]\nrisk_level: low | medium | high\n```\n\n### Verification Contract\n```\nverify_steps:\n  - run tests: [test command]\n  - check: [what to inspect]\n  - confirm: [success signal]\n```\n\n### Governance Contract\n```\napproval_gates: [list of steps requiring human review]\nrollback: [how to undo if something goes wrong]\nownership: [who is accountable]\n```\n\n7. **Write design doc** — path depends on scope:\n   - `feature` scope: save to `docs\u002Fdesigns\u002FYYYY-MM-DD-\u003Cslug>-design.md` (dated, tactical).\n   - `phase` scope: save to `docs\u002Fdesigns\u002FYYYY-MM-DD-phase-N-\u003Cslug>-design.md` (dated, tactical).\n   - `initiative` scope: save to `\u003Cdesigns_dir>\u002F\u003Ctopic>.md` (undated, durable). `\u003Cdesigns_dir>` is the value returned by the step-2 resolver (default `docs\u002Fdesigns`). Follow the section structure of the strategic template loaded in step 2.\n\n   **Always write YAML frontmatter with the HOTL marker.** Every saved design doc MUST start with frontmatter declaring at minimum:\n\n   ```yaml\n   ---\n   design_type: \u003Cfeature|phase|initiative>   # match the scope chosen in step 2\n   created_at: YYYY-MM-DD\n   ---\n   ```\n\n   The `design_type` field is the deterministic signal that opts the doc into HOTL strict lint (`document-lint.sh` SKIPs unmarked docs). Without it, the doc is treated as non-HOTL and routes through generic AI review only.\n8. **Self-check the design doc** — before presenting for human approval, review the saved design doc for: missing constraints, vague success criteria, contract mismatches (do verification steps actually test the intent?), risk_level appropriateness, and scope creep. Fix any issues found. Lightweight: 1-2 passes by default, max 3 only if real issues are found. Do not ask the user to review — this is an internal quality pass.\n\n   **Run document-lint on the saved design doc** as part of this self-check. Resolve `scripts\u002Fdocument-lint.sh` via the standard six-location order, then:\n\n   ```bash\n   bash \u003Cresolved-document-lint.sh> \u003Csaved-design-path>\n   ```\n\n   The lint emits two stable warning shapes for feature\u002Fphase docs:\n\n   ```\n   category=structure severity=warning design_type=\u003Cresolved>\n   message=\"missing required section: ## \u003Cname>\"\n\n   category=implementation-leakage severity=warning design_type=\u003Cresolved> line=\u003Cn>\n   message=\"\u003Cshort description>\"\n   ```\n\n   Apply the **5-step self-check behavior** to surfaced warnings:\n\n   1. Run `document-lint.sh` on the saved design doc.\n   2. Surface warnings to the user before asking for approval.\n   3. Fix warnings that clearly violate the design\u002Fplan boundary.\n   4. Justify a warning only when the flagged content sits inside a clearly delimited example block — a Markdown blockquote (`> Example: ...`) or a section whose heading includes the word `Example`. All other findings must be fixed.\n   5. Do not block approval unless the user decides the warnings are blocking.\n\n   **Loop bound:** This 5-step procedure runs at most once per self-check pass; the parent self-check (step 8) caps the total at 3 passes before stopping.\n\n   Lint exits 0 even when these warnings are emitted (warning-only contract this pass). Initiative \u002F architecture \u002F contract \u002F reference docs receive neither check; the lint emits no `category=structure` or `category=implementation-leakage` lines for them.\n9. **Invoke writing-plans** — transition to implementation planning (feature\u002Fphase scope only; initiative designs decompose into child phase plans that each go through their own brainstorming → writing-plans cycle).\n\n## Doc-discipline rules\n\nFor `design_type ∈ {feature, phase}` docs, write the body using these **seven required sections in fixed order**. Phase 1 lint enforces presence only; out-of-order or extra sections are not flagged this pass but the prose order below is the canonical convention:\n\n1. `## Intent Contract`\n2. `## Verification Contract`\n3. `## Governance Contract`\n4. `## Scope` (in \u002F out, table form preferred)\n5. `## Decisions` (# \u002F decision \u002F choice \u002F rejected alternatives, table form preferred)\n6. `## Surface` (APIs \u002F storage \u002F components \u002F files-touched, paragraph each)\n7. `## Risks & Open Questions`\n\nInitiative \u002F architecture \u002F contract \u002F reference docs are durable references; they may legitimately include deeper technical shape. The lint defers any rules for them this pass.\n\n### Implementation-leakage anti-patterns\n\nA design doc says **shape**; the workflow file and the code say **exact bytes**. The following patterns belong in `writing-plans` output (or in code itself), not in the design — the lint warns when they appear in feature\u002Fphase design bodies:\n\n| Pattern | Example | Why it doesn't belong in design |\n|---|---|---|\n| File:line references | `cli.py:16`, `auth.ts:204` | Line numbers rot the moment code moves; pin to workflow steps instead. |\n| Long fenced code blocks (>10 content lines) | a 30-line Python snippet | Design shows shape; full implementation goes in workflow tasks or code. |\n| Dense flag lines (≥6 `--` tokens) | `docker run --network=none --cap-drop=ALL --read-only --tmpfs \u002Ftmp ...` | Argv assertions go in workflow steps and tests, not design surface. |\n\nWhen a design doc must reference one of these (e.g., as an illustrative example), the warning is acceptable and the agent should justify it during the self-check (step 8) rather than rewrite the design.\n\n### Doc-type detection\n\n1. **Frontmatter is the deterministic signal.** A doc is HOTL-managed only when its frontmatter declares `design_type:` (one of `feature | phase | initiative | architecture | contract | reference`) or `hotl_managed: true`. The brainstorming skill always writes the marker; ad-hoc docs in `docs\u002Fdesigns\u002F` are treated as non-HOTL by default.\n2. **Filename pattern is a hint, not a classifier.** Dated `YYYY-MM-DD-*-design.md` is the conventional pattern for HOTL-authored docs, but the lint still requires a frontmatter marker before applying HOTL rules. Without a marker, `document-lint.sh` SKIPs cleanly with a clear message and exits 0.\n3. **Unmarked design-folder docs route to AI review.** `hotl:document-review` runs a generic-rubric AI review on them; `document-lint.sh` skips them. To opt a hand-authored doc into HOTL strict review, add `design_type: \u003Crecognized-value>` or `hotl_managed: true` to its frontmatter.\n\n## Key Principles\n\n- One question at a time — prefer multiple-choice when practical\n- YAGNI ruthlessly — remove unnecessary features\n- Always propose alternatives before settling\n- `risk_level: high` = security, auth, privacy, billing (always human-gated)\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fbrainstorming",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill brainstorming",{"tool":51,"command":52},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill brainstorming",{"tool":54,"command":55},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill brainstorming","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyimwoo\u002Fhotl-plugin\u002Fskills\u002Fbrainstorming\u002FSKILL.md",true,[],[60,70,78,86,94,102],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":65,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":69},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":69},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"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":64,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":69},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\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":64,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":69},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":69},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":69},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]