[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C3B3S71433XRHJQS1539MQ":3,"skill-same:01M6C3B3S71433XRHJQS1539MQ":96},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6C3B3S71433XRHJQS1539MQ","speckit-converge",null,"Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.","IgorGanapolsky\u002FRandom-Timer","IgorGanapolsky","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F201209?v=4","01M6C2WB7720K13ERYVB3AJ0SQ","Igor Ganapolsky","01M6C2WBBF0NWVQV4A89FS00Q5",1,"MIT","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fspeckit-converge\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"speckit converge","directory","spec","github","implement","project structure","tasks","specify","templates","plan","work","append","2026-11-10 10:12:30",false,"---\nname: \"speckit-converge\"\ndescription: \"Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.\"\ncompatibility: \"Requires spec-kit project structure with .specify\u002F directory\"\nmetadata:\n  author: \"github-spec-kit\"\n  source: \"templates\u002Fcommands\u002Fconverge.md\"\n---\n\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou **MUST** consider the user input before proceeding (if not empty).\n\n## Pre-Execution Checks\n\n**Check for extension hooks (before convergence)**:\n\n- Check if `.specify\u002Fextensions.yml` exists in the project root.\n- If it exists, read it and look for entries under the `hooks.before_converge` key\n- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then continue normally\n- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.\n- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:\n  - If the hook has no `condition` field, or it is null\u002Fempty, treat the hook as executable\n  - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation\n- When constructing command invocations from hook command names, replace dots (`.`) with hyphens (`-`). For example, `speckit.git.commit` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Optional hook** (`optional: true`):\n\n    ```text\n    ## Extension Hooks\n\n    **Optional Pre-Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n\n  - **Mandatory hook** (`optional: false`):\n\n    ```text\n    ## Extension Hooks\n\n    **Automatic Pre-Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n\n    Wait for the result of the hook command before proceeding to the Goal.\n    ```\n    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n\n- If no hooks are registered or `.specify\u002Fextensions.yml` does not exist, skip silently\n\n## Goal\n\nClose the gap between what a feature's specification, plan, and tasks call for and what the\ncodebase currently implements. Read `spec.md`, `plan.md`, and `tasks.md` as the **sole\nsource of intent** (with the constitution as governing constraints), assess the current\nstate of the code, determine which requirements, acceptance criteria, plan decisions, and\nexisting tasks are unmet, incomplete, or only partially satisfied, and **append each piece\nof remaining work as a new, traceable task** at the bottom of `tasks.md` so that\n`\u002Fspeckit-implement` can complete it. This command MUST run only after\n`\u002Fspeckit-implement` has run on the current `tasks.md`, and after `\u002Fspeckit-tasks` has produced a complete `tasks.md`.\n\nThis is **not** a diff tool and does **not** track changes. It assesses the present state\nof the code relative to the feature's artifacts — no git, no branch comparison, no history.\n\n## Operating Constraints\n\n**APPEND-ONLY, NEVER REWRITE**: The command's **only** write is appending a new\n`## Phase N: Convergence` section to `tasks.md`. It MUST NOT:\n\n- modify `spec.md` or `plan.md` in any way;\n- rewrite, renumber, reorder, or delete any existing task (including tasks from a prior\n  Convergence phase);\n- modify, create, or delete any application code — completing the appended tasks is the\n  job of `\u002Fspeckit-implement`.\n\nWhen the codebase already satisfies everything, the command MUST leave `tasks.md`\n**byte-for-byte unchanged** (no empty Convergence header) and report a clean result.\n\n**Constitution Authority**: The project constitution (`.specify\u002Fmemory\u002Fconstitution.md`) is\n**non-negotiable**. Code that violates a MUST principle is the highest-severity finding and\nproduces a corresponding remediation task. If the constitution is an unfilled template,\nskip constitution checks gracefully rather than failing.\n\n## Execution Steps\n\n### 1. Initialize Convergence Context\n\nRun `.specify\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --require-spec --require-tasks --include-tasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:\n\n- SPEC = FEATURE_DIR\u002Fspec.md\n- PLAN = FEATURE_DIR\u002Fplan.md\n- TASKS = FEATURE_DIR\u002Ftasks.md\n- CONSTITUTION = `.specify\u002Fmemory\u002Fconstitution.md` (if present)\nIf `spec.md`, `plan.md`, or `tasks.md` is missing, STOP with a clear, actionable message naming the\nprerequisite command to run (`\u002Fspeckit-specify` for a missing spec, `\u002Fspeckit-plan` for a missing plan,\n`\u002Fspeckit-tasks` for missing tasks). Do not produce partial output.\nFor single quotes in args like \"I'm Groot\", use escape syntax: e.g 'I'\\''m Groot' (or double-quote if possible: \"I'm Groot\").\n\n### 2. Load Artifacts (Progressive Disclosure)\n\nLoad only the minimal necessary context from each artifact:\n\n**From spec.md:**\n\n- Functional Requirements (FR-###)\n- Success Criteria (SC-###) — include only items requiring buildable work; exclude\n  post-launch outcome metrics and business KPIs\n- User Stories and their Acceptance Scenarios\n- Edge Cases (if present)\n\n**From plan.md:**\n\n- Architecture\u002Fstack choices and technical decisions\n- Data Model references\n- Phases and named touch-points (files\u002Fcomponents the plan says will be created or edited)\n- Technical constraints\n\n**From tasks.md:**\n\n- Task IDs (to compute the next ID and next phase number)\n- Descriptions, phase grouping, and referenced file paths\n\n**From constitution (if not an unfilled template):**\n\n- Principle names and MUST\u002FSHOULD normative statements\n\n### 3. Build the Intent Inventory\n\nCreate an internal model (do not echo raw artifacts):\n\n- **Requirements inventory**: one stable key per FR-### \u002F SC-### \u002F user-story acceptance\n  scenario (e.g. `US1\u002FAC2`), plus the plan decisions and constitution principles that\n  impose buildable obligations.\n- **Code-scope map**: from the file paths named in `plan.md` and `tasks.md`, plus a keyword\n  search for the concepts each requirement describes, derive the set of source files and\n  components in scope for assessment. Bound the assessment to these — do **not** infer\n  scope beyond what the artifacts define.\n\n### 4. Assess the Codebase and Classify Findings\n\nFor each item in the intent inventory, inspect the current code in scope and produce a\n`Finding` only where there is a gap. Classify every finding by **gap type**:\n\n- **`missing`**: the required work is absent from the code entirely.\n- **`partial`**: the work exists but does not yet fully satisfy the requirement \u002F\n  acceptance criterion \u002F plan decision.\n- **`contradicts`**: the code does something that conflicts with stated intent or a\n  constitution MUST principle.\n- **`unrequested`**: the code contains work not called for by the spec, plan, or tasks\n  (surfaced for awareness — converge does **not** delete code, it only appends a task to\n  review\u002Fjustify or remove it).\n\nEach `Finding` records: a stable id, the `source-ref` it traces to, the `gap-type`, a\nseverity, and a short human-readable description with the evidence (the file\u002Farea observed).\n\n**Edge cases:**\n\n- **Little or no code yet**: treat the entire specified scope as `missing` remaining work\n  rather than failing.\n- **Nothing remains**: produce zero findings and follow the converged branch in Step 7.\n\n### 5. Assign Severity\n\n- **CRITICAL**: violates a constitution MUST principle, or a `missing`\u002F`contradicts` gap\n  that blocks baseline functionality of a P1 user story.\n- **HIGH**: a `missing` or `partial` gap on a core functional requirement or acceptance\n  criterion.\n- **MEDIUM**: a `partial` gap on a secondary requirement, or an `unrequested` addition with\n  unclear justification.\n- **LOW**: minor partial gaps, polish, or low-risk `unrequested` additions.\n\n### 6. Present the In-Session Findings Summary\n\nBefore appending anything, output a compact, severity-graded summary (no file writes yet):\n\n## Convergence Findings\n\n| ID | Gap Type | Severity | Source | Evidence | Remaining Work |\n|----|----------|----------|--------|----------|----------------|\n| F1 | missing  | HIGH     | FR-008 | Example: no append-only guard detected in path\u002Fto\u002Fmodule.py when writing tasks.md | Add append-only enforcement |\n\n**Summary metrics:**\n\n- Requirements \u002F acceptance criteria checked\n- Plan decisions checked\n- Constitution principles checked (or \"skipped — template\")\n- Findings by gap type (missing \u002F partial \u002F contradicts \u002F unrequested)\n- Findings by severity\n\n### 7. Append Convergence Tasks (or report converged)\n\n**If there are one or more actionable findings** (`tasks_appended` outcome):\n\nAppend to the **end** of `tasks.md`, per the append contract:\n\n1. Scan all existing task IDs; let `M` be the maximum. Determine the next phase number `N`\n   (highest existing phase + 1).\n2. Write a single new section header `## Phase N: Convergence`.\n3. Emit one checklist item per actionable finding, ordered CRITICAL\u002FHIGH first, assigning\n   zero-padded IDs `T{M+1:03d}, T{M+2:03d}, …`:\n\n   ```markdown\n   - [ ] T042 \u003Cimperative description> per \u003Csource-ref> (\u003Cgap-type>)\n   ```\n\n   `\u003Csource-ref>` traces the task to its origin: e.g. `FR-003`, `SC-002`,\n   `US1\u002FAC2`, `plan: storage decision`, `Constitution II`.\n\n   `\u003Cgap-type>` is one of `missing`, `partial`, `contradicts`, `unrequested`.\n\n   Constitution-violation tasks MUST be emitted first and described as\n   `CRITICAL`.\n4. Never reuse or renumber existing IDs. If a prior Convergence phase exists, add a new,\n   separately-numbered one below it — do not touch the old one.\n\n**If there are no actionable findings** (`converged` outcome):\n\n- Do **not** modify `tasks.md` at all — no empty phase header.\n- Report: **\"✅ Converged — the implementation satisfies the spec, plan, and tasks.\"**\n- Include the summary counts of what was checked.\n\n### 8. Provide Next Actions (Handoff)\n\n- On `tasks_appended`: state how many tasks were appended under which phase, and recommend\n  running `\u002Fspeckit-implement` to complete them; note that a follow-up converge\n  run will find fewer or no remaining items.\n- On `converged`: recommend proceeding to review \u002F opening a PR. No further implement pass\n  is needed for this feature's specified scope.\n\n### 9. Check for extension hooks\n\nAfter producing the result, check if `.specify\u002Fextensions.yml` exists in the project root.\n\n- If it exists, read it and look for entries under the `hooks.after_converge` key\n- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then continue normally\n- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.\n- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:\n  - If the hook has no `condition` field, or it is null\u002Fempty, treat the hook as executable\n  - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation\n- Report the convergence outcome (`converged` or `tasks_appended`) in-session before listing\n  any hooks, so users can decide whether to run optional follow-up commands.\n- When constructing command invocations from hook command names, replace dots (`.`) with hyphens (`-`). For example, `speckit.git.commit` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Optional hook** (`optional: true`):\n\n    ```text\n    ## Extension Hooks\n\n    **Optional Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n\n  - **Mandatory hook** (`optional: false`):\n\n    ```text\n    ## Extension Hooks\n\n    **Automatic Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n    ```\n    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n\n- If no hooks are registered or `.specify\u002Fextensions.yml` does not exist, skip silently\n","## User Input\n\n```text\n$ARGUMENTS\n```\n\nYou **MUST** consider the user input before proceeding (if not empty).\n\n## Pre-Execution Checks\n\n**Check for extension hooks (before convergence)**:\n\n- Check if `.specify\u002Fextensions.yml` exists in the project root.\n- If it exists, read it and look for entries under the `hooks.before_converge` key\n- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then continue normally\n- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.\n- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:\n  - If the hook has no `condition` field, or it is null\u002Fempty, treat the hook as executable\n  - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation\n- When constructing command invocations from hook command names, replace dots (`.`) with hyphens (`-`). For example, `speckit.git.commit` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Optional hook** (`optional: true`):\n\n    ```text\n    ## Extension Hooks\n\n    **Optional Pre-Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n\n  - **Mandatory hook** (`optional: false`):\n\n    ```text\n    ## Extension Hooks\n\n    **Automatic Pre-Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n\n    Wait for the result of the hook command before proceeding to the Goal.\n    ```\n    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n\n- If no hooks are registered or `.specify\u002Fextensions.yml` does not exist, skip silently\n\n## Goal\n\nClose the gap between what a feature's specification, plan, and tasks call for and what the\ncodebase currently implements. Read `spec.md`, `plan.md`, and `tasks.md` as the **sole\nsource of intent** (with the constitution as governing constraints), assess the current\nstate of the code, determine which requirements, acceptance criteria, plan decisions, and\nexisting tasks are unmet, incomplete, or only partially satisfied, and **append each piece\nof remaining work as a new, traceable task** at the bottom of `tasks.md` so that\n`\u002Fspeckit-implement` can complete it. This command MUST run only after\n`\u002Fspeckit-implement` has run on the current `tasks.md`, and after `\u002Fspeckit-tasks` has produced a complete `tasks.md`.\n\nThis is **not** a diff tool and does **not** track changes. It assesses the present state\nof the code relative to the feature's artifacts — no git, no branch comparison, no history.\n\n## Operating Constraints\n\n**APPEND-ONLY, NEVER REWRITE**: The command's **only** write is appending a new\n`## Phase N: Convergence` section to `tasks.md`. It MUST NOT:\n\n- modify `spec.md` or `plan.md` in any way;\n- rewrite, renumber, reorder, or delete any existing task (including tasks from a prior\n  Convergence phase);\n- modify, create, or delete any application code — completing the appended tasks is the\n  job of `\u002Fspeckit-implement`.\n\nWhen the codebase already satisfies everything, the command MUST leave `tasks.md`\n**byte-for-byte unchanged** (no empty Convergence header) and report a clean result.\n\n**Constitution Authority**: The project constitution (`.specify\u002Fmemory\u002Fconstitution.md`) is\n**non-negotiable**. Code that violates a MUST principle is the highest-severity finding and\nproduces a corresponding remediation task. If the constitution is an unfilled template,\nskip constitution checks gracefully rather than failing.\n\n## Execution Steps\n\n### 1. Initialize Convergence Context\n\nRun `.specify\u002Fscripts\u002Fbash\u002Fcheck-prerequisites.sh --json --require-spec --require-tasks --include-tasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:\n\n- SPEC = FEATURE_DIR\u002Fspec.md\n- PLAN = FEATURE_DIR\u002Fplan.md\n- TASKS = FEATURE_DIR\u002Ftasks.md\n- CONSTITUTION = `.specify\u002Fmemory\u002Fconstitution.md` (if present)\nIf `spec.md`, `plan.md`, or `tasks.md` is missing, STOP with a clear, actionable message naming the\nprerequisite command to run (`\u002Fspeckit-specify` for a missing spec, `\u002Fspeckit-plan` for a missing plan,\n`\u002Fspeckit-tasks` for missing tasks). Do not produce partial output.\nFor single quotes in args like \"I'm Groot\", use escape syntax: e.g 'I'\\''m Groot' (or double-quote if possible: \"I'm Groot\").\n\n### 2. Load Artifacts (Progressive Disclosure)\n\nLoad only the minimal necessary context from each artifact:\n\n**From spec.md:**\n\n- Functional Requirements (FR-###)\n- Success Criteria (SC-###) — include only items requiring buildable work; exclude\n  post-launch outcome metrics and business KPIs\n- User Stories and their Acceptance Scenarios\n- Edge Cases (if present)\n\n**From plan.md:**\n\n- Architecture\u002Fstack choices and technical decisions\n- Data Model references\n- Phases and named touch-points (files\u002Fcomponents the plan says will be created or edited)\n- Technical constraints\n\n**From tasks.md:**\n\n- Task IDs (to compute the next ID and next phase number)\n- Descriptions, phase grouping, and referenced file paths\n\n**From constitution (if not an unfilled template):**\n\n- Principle names and MUST\u002FSHOULD normative statements\n\n### 3. Build the Intent Inventory\n\nCreate an internal model (do not echo raw artifacts):\n\n- **Requirements inventory**: one stable key per FR-### \u002F SC-### \u002F user-story acceptance\n  scenario (e.g. `US1\u002FAC2`), plus the plan decisions and constitution principles that\n  impose buildable obligations.\n- **Code-scope map**: from the file paths named in `plan.md` and `tasks.md`, plus a keyword\n  search for the concepts each requirement describes, derive the set of source files and\n  components in scope for assessment. Bound the assessment to these — do **not** infer\n  scope beyond what the artifacts define.\n\n### 4. Assess the Codebase and Classify Findings\n\nFor each item in the intent inventory, inspect the current code in scope and produce a\n`Finding` only where there is a gap. Classify every finding by **gap type**:\n\n- **`missing`**: the required work is absent from the code entirely.\n- **`partial`**: the work exists but does not yet fully satisfy the requirement \u002F\n  acceptance criterion \u002F plan decision.\n- **`contradicts`**: the code does something that conflicts with stated intent or a\n  constitution MUST principle.\n- **`unrequested`**: the code contains work not called for by the spec, plan, or tasks\n  (surfaced for awareness — converge does **not** delete code, it only appends a task to\n  review\u002Fjustify or remove it).\n\nEach `Finding` records: a stable id, the `source-ref` it traces to, the `gap-type`, a\nseverity, and a short human-readable description with the evidence (the file\u002Farea observed).\n\n**Edge cases:**\n\n- **Little or no code yet**: treat the entire specified scope as `missing` remaining work\n  rather than failing.\n- **Nothing remains**: produce zero findings and follow the converged branch in Step 7.\n\n### 5. Assign Severity\n\n- **CRITICAL**: violates a constitution MUST principle, or a `missing`\u002F`contradicts` gap\n  that blocks baseline functionality of a P1 user story.\n- **HIGH**: a `missing` or `partial` gap on a core functional requirement or acceptance\n  criterion.\n- **MEDIUM**: a `partial` gap on a secondary requirement, or an `unrequested` addition with\n  unclear justification.\n- **LOW**: minor partial gaps, polish, or low-risk `unrequested` additions.\n\n### 6. Present the In-Session Findings Summary\n\nBefore appending anything, output a compact, severity-graded summary (no file writes yet):\n\n## Convergence Findings\n\n| ID | Gap Type | Severity | Source | Evidence | Remaining Work |\n|----|----------|----------|--------|----------|----------------|\n| F1 | missing  | HIGH     | FR-008 | Example: no append-only guard detected in path\u002Fto\u002Fmodule.py when writing tasks.md | Add append-only enforcement |\n\n**Summary metrics:**\n\n- Requirements \u002F acceptance criteria checked\n- Plan decisions checked\n- Constitution principles checked (or \"skipped — template\")\n- Findings by gap type (missing \u002F partial \u002F contradicts \u002F unrequested)\n- Findings by severity\n\n### 7. Append Convergence Tasks (or report converged)\n\n**If there are one or more actionable findings** (`tasks_appended` outcome):\n\nAppend to the **end** of `tasks.md`, per the append contract:\n\n1. Scan all existing task IDs; let `M` be the maximum. Determine the next phase number `N`\n   (highest existing phase + 1).\n2. Write a single new section header `## Phase N: Convergence`.\n3. Emit one checklist item per actionable finding, ordered CRITICAL\u002FHIGH first, assigning\n   zero-padded IDs `T{M+1:03d}, T{M+2:03d}, …`:\n\n   ```markdown\n   - [ ] T042 \u003Cimperative description> per \u003Csource-ref> (\u003Cgap-type>)\n   ```\n\n   `\u003Csource-ref>` traces the task to its origin: e.g. `FR-003`, `SC-002`,\n   `US1\u002FAC2`, `plan: storage decision`, `Constitution II`.\n\n   `\u003Cgap-type>` is one of `missing`, `partial`, `contradicts`, `unrequested`.\n\n   Constitution-violation tasks MUST be emitted first and described as\n   `CRITICAL`.\n4. Never reuse or renumber existing IDs. If a prior Convergence phase exists, add a new,\n   separately-numbered one below it — do not touch the old one.\n\n**If there are no actionable findings** (`converged` outcome):\n\n- Do **not** modify `tasks.md` at all — no empty phase header.\n- Report: **\"✅ Converged — the implementation satisfies the spec, plan, and tasks.\"**\n- Include the summary counts of what was checked.\n\n### 8. Provide Next Actions (Handoff)\n\n- On `tasks_appended`: state how many tasks were appended under which phase, and recommend\n  running `\u002Fspeckit-implement` to complete them; note that a follow-up converge\n  run will find fewer or no remaining items.\n- On `converged`: recommend proceeding to review \u002F opening a PR. No further implement pass\n  is needed for this feature's specified scope.\n\n### 9. Check for extension hooks\n\nAfter producing the result, check if `.specify\u002Fextensions.yml` exists in the project root.\n\n- If it exists, read it and look for entries under the `hooks.after_converge` key\n- If the YAML cannot be parsed or is invalid, do not skip silently: tell the user that `.specify\u002Fextensions.yml` could not be read (include the parser error) and that no hooks were checked, including any mandatory (`optional: false`) hooks registered there, then continue normally\n- Filter out hooks where `enabled` is explicitly `false`. Treat hooks without an `enabled` field as enabled by default.\n- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:\n  - If the hook has no `condition` field, or it is null\u002Fempty, treat the hook as executable\n  - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation\n- Report the convergence outcome (`converged` or `tasks_appended`) in-session before listing\n  any hooks, so users can decide whether to run optional follow-up commands.\n- When constructing command invocations from hook command names, replace dots (`.`) with hyphens (`-`). For example, `speckit.git.commit` → `\u002Fspeckit-git-commit`.\n- For each executable hook, output the following based on its `optional` flag:\n  - **Optional hook** (`optional: true`):\n\n    ```text\n    ## Extension Hooks\n\n    **Optional Hook**: {extension}\n    Command: `\u002F{command}`\n    Description: {description}\n\n    Prompt: {prompt}\n    To execute: `\u002F{command}`\n    ```\n\n  - **Mandatory hook** (`optional: false`):\n\n    ```text\n    ## Extension Hooks\n\n    **Automatic Hook**: {extension}\n    Executing: `\u002F{command}`\n    EXECUTE_COMMAND: {command}\n    ```\n    After emitting the block above you MUST actually invoke the hook and wait for it to finish before continuing. Run it the same way you would run the command yourself in this agent\u002Fsession (the invocation may differ from the literal `{command}` id shown above, e.g. a skills-mode agent runs it as `\u002Fskill:speckit-...` or `$speckit-...`). Emitting the block alone does not run the hook.\n\n- If no hooks are registered or `.specify\u002Fextensions.yml` does not exist, skip silently\n",{"name":5,"metadata":36,"description":7,"compatibility":39},{"author":37,"source":38},"github-spec-kit","templates\u002Fcommands\u002Fconverge.md","Requires spec-kit project structure with .specify\u002F directory","develop","4af946ac9a2b3cfbbe9b2e8696cc436f1d16e2e2",".cursor\u002Fskills\u002Fspeckit-converge",0,"https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer","https:\u002F\u002Fapps.apple.com\u002Fus\u002Fapp\u002Frandom-tactical-timer\u002Fid6758355312","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky","https:\u002F\u002Fwww.igorganapolsky.com","Forward Deploy AI Engineer. Automation specialist.\r\n","2026-11-09 23:14:20",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add IgorGanapolsky\u002FRandom-Timer --skill speckit-converge",{"tool":56,"command":57},"bunx","bunx skills add IgorGanapolsky\u002FRandom-Timer --skill speckit-converge",{"tool":59,"command":60},"pnpm","pnpm dlx skills add IgorGanapolsky\u002FRandom-Timer --skill speckit-converge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fspeckit-converge\u002FSKILL.md",true,[64,70,74,78,82,86,92],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fauri-analysis.md","REFERENCE","参考文档",7694,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-matematico-tao\u002Freferences\u002Fauri-analysis.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcomplexity-patterns.md",9082,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-matematico-tao\u002Freferences\u002Fcomplexity-patterns.md",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fconcurrency-models.md",8908,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-matematico-tao\u002Freferences\u002Fconcurrency-models.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fdetailed-guide.md",7910,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-matematico-tao\u002Freferences\u002Fdetailed-guide.md",{"path":83,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Finformation-theory.md",3376,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-matematico-tao\u002Freferences\u002Finformation-theory.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fcomplexity_analyzer.py","SCRIPT","脚本",22340,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-matematico-tao\u002Fscripts\u002Fcomplexity_analyzer.py",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fdependency_graph.py",22317,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-matematico-tao\u002Fscripts\u002Fdependency_graph.py",[97,118,137,147,159,170],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":113,"publishedAt":31},"01M6C3CEGAENG02BPG636N9WG6","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[103,108],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[114,115,21,116,117],"writing plans","writing","code","use",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":127,"publishedAt":31},"01M6C3CC40GJBTJQHQ5BF7CQN9","workflow-economics-lite","Escape AI pilot purgatory: require completion-loop workflows with one owner, baseline, economic metric, system-of-record integration, and audit trail. Block orphan chatbots and interest-as-ROI claims.","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fworkflow-economics-lite\u002FSKILL.md",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000023","Skill与智能体开发",[128,129,130,131,132,133,134,135,136],"workflow economics lite","workflow","loop","roi","workflows","audit","integration","baseline","system",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":31},"01M6C3C9ESBW612NMMMBQDWSWR","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[144,145,117,146,29],"verification before completion","verification","evidence",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":31},"01M6C3C71DNQHJ6PGV0TN1R99N","value-center-lite","Apply InfoQ Rohrer value-center \u002F VSM five questions (agency + coherence). Use when planning work, shipping releases, or auditing agent autonomy claims. Fail closed on product-only slogans without WQTU\u002Fpaywall value.","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fvalue-center-lite\u002FSKILL.md",[],[154,155,117,29,156,157,158],"value center lite","only","product","shipping","planning",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":31},"01M6C3C41Q0R2J49F3Q4CQ004J","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[166,167,117,168,169],"superpowers","using superpowers","find","how",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":31},"01M6C3C1EBYXRVMNHZZE9N49PN","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002FIgorGanapolsky\u002FRandom-Timer\u002Fblob\u002Fdevelop\u002F.cursor\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[177,178,179,180,181,182,183,29,117],"git","using git worktrees","git worktrees","git worktree","Tools","worktree","workspace"]