[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72YC5HTSYVJB5QT1XNZERG5":3,"skill-same:01M72YC5HTSYVJB5QT1XNZERG5":93},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M72YC5HTSYVJB5QT1XNZERG5","implement-tasks",null,"Use to implement a feature from its tasks.json with test-driven development — writes a failing test first, makes it pass, refactors, gates, and commits per task. Triggers on \"\u002Fsdlc:implement-tasks {slug}\", \"implement {slug}\", \"build {slug}\", \"TDD {slug}\", \"code up the tasks for {slug}\", \"імплементуй {slug}\", \"реалізуй фічу {slug}\", \"напиши код за задачами {slug}\". Reads docs\u002Ffeatures\u002F{slug}\u002Ftasks\u002Ftasks.json + the upstream artifacts, detects the repo's test\u002Flint\u002Fvet commands stack-agnostically, builds a dependency DAG, and runs one of three modes — sequential single-agent TDD, an agent team (TeamCreate), or a dynamic Workflow — chosen from settings + DAG shape with graceful fallback. Output: committed, tested code + updated tasks\u002Ftracker.md. Hard-refuses if docs\u002Ffeatures\u002F{slug}\u002Ftasks\u002Ftasks.json is missing (the legacy docs\u002Ffeatures\u002F{slug}\u002Ftasks.json is accepted as a fallback) → run `\u002Fsdlc:break-tasks {slug}` first.","genkovich\u002Fagentic-engineering-course-public","genkovich","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14920737?v=4","01M72Y5BWEEZ8VT4DFW6AGGE8X","Kirill Sulimovsky","01M72Y5BXYRGV5PKCVCHEX81WY",15,"MIT","https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: implement-tasks\nmodel: inherit\neffort: medium\nagents: [test-author, implementer, refactor, reviewer]\ndescription: >\n  Use to implement a feature from its tasks.json with test-driven development — writes a failing\n  test first, makes it pass, refactors, gates, and commits per task. Triggers on\n  \"\u002Fsdlc:implement-tasks {slug}\", \"implement {slug}\", \"build {slug}\", \"TDD {slug}\",\n  \"code up the tasks for {slug}\", \"імплементуй {slug}\", \"реалізуй фічу {slug}\",\n  \"напиши код за задачами {slug}\". Reads docs\u002Ffeatures\u002F{slug}\u002Ftasks\u002Ftasks.json + the upstream\n  artifacts, detects the repo's test\u002Flint\u002Fvet commands stack-agnostically, builds a dependency\n  DAG, and runs one of three modes — sequential single-agent TDD, an agent team (TeamCreate), or\n  a dynamic Workflow — chosen from settings + DAG shape with graceful fallback. Output: committed,\n  tested code + updated tasks\u002Ftracker.md. Hard-refuses if docs\u002Ffeatures\u002F{slug}\u002Ftasks\u002Ftasks.json is\n  missing (the legacy docs\u002Ffeatures\u002F{slug}\u002Ftasks.json is accepted as a fallback) → run\n  `\u002Fsdlc:break-tasks {slug}` first.\ntriggers:\n  - \u002Fsdlc:implement-tasks\nstage: \"17\"\n---\n\n# Skill: implement-tasks (SDLC stage 17 — Code)\n\nThe implementation engine — the keystone that closes the cycle. It turns `tasks.json` into committed, tested code through a strict TDD cycle per task — `SELECT → RED → GREEN → REFACTOR → GATE → COMMIT` — and orchestrates that cycle in one of three modes (sequential \u002F agent-team \u002F dynamic-workflow) picked by an unambiguous decision tree. Everything is stack-agnostic: the test, lint, and vet commands are **detected**, never hard-coded.\n\nThis file is the spine. Each step delegates to a file in `references\u002F`.\n\n## Owner\n\nTech Lead drives; the engine runs the cycle. Four subagents ship with the plugin: [`test-author`](..\u002F..\u002Fagents\u002Ftest-author.md) (`sdlc:test-author`, RED), [`implementer`](..\u002F..\u002Fagents\u002Fimplementer.md) (`sdlc:implementer`, GREEN), [`refactor`](..\u002F..\u002Fagents\u002Frefactor.md) (`sdlc:refactor`, REFACTOR — isolated, tidies while green), [`reviewer`](..\u002F..\u002Fagents\u002Freviewer.md) (`sdlc:reviewer`, read-only review). GATE + COMMIT stay on the engine, which owns the settings and the `require_integration` policy.\n\n## Inputs\n\n- `\u003Cslug>` — feature slug.\n- **Gate (hard refuse):** `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks\u002Ftasks.json` (legacy fallback: `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks.json`, used only when the first is absent). Both missing → «run `\u002Fsdlc:break-tasks \u003Cslug>` first». Greenfield skeleton: `\u003Cslug>` = `_scaffold` (written by `map-architecture`).\n- Read for context (the agents read these directly, not via paraphrase): `PRD.md` (AC), `data-model.md` + the **staged** migrations under `docs\u002Ffeatures\u002F\u003Cslug>\u002Fmigrations\u002F` (a `layer: migration` task **promotes** these into the live migrations tree — see [`.\u002Freferences\u002Finputs.md`](.\u002Freferences\u002Finputs.md)), `contracts\u002Fopenapi.yaml`, `test-plan.md`, `sad.md`, Accepted `adr\u002F`.\n- Settings: `.claude\u002Fsdlc.local.md` (auto-created with documented defaults if absent — normally by `write-prd` at the backbone start; `implement-tasks` creates it too if you jump straight here) → [`.\u002Freferences\u002Fsettings.md`](.\u002Freferences\u002Fsettings.md).\n\n## Protocol\n\n1. **Preconditions.** Resolve the plan path — `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks\u002Ftasks.json`, else the legacy `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks.json` (warn that it's legacy) — verify it parses; load the upstream artifacts list. Detail → [`.\u002Freferences\u002Finputs.md`](.\u002Freferences\u002Finputs.md).\n2. **Settings.** Read `.claude\u002Fsdlc.local.md`; if absent, auto-create it with the documented defaults (frontmatter + the «What each key does» body, self-documenting) and patch `.gitignore` (`.claude\u002F*.local.md`, `.worktrees\u002F`) — the same template `write-prd` writes. → [`.\u002Freferences\u002Fsettings.md`](.\u002Freferences\u002Fsettings.md).\n3. **Detect commands.** Run the stack-agnostic cascade (settings override → Makefile → package scripts → language manifests → Docker probe for the integration tier) to resolve unit \u002F integration \u002F lint \u002F vet commands. Print what was detected. → [`.\u002Freferences\u002Fcommand-detection.md`](.\u002Freferences\u002Fcommand-detection.md).\n4. **Build the DAG.** Parse `tasks.json`, validate `deps` is acyclic, topologically sort into phases (Kahn). Compute `task_count`, `longest_chain`, `parallel_width`. Mark serialization lanes (`layer: migration`; tasks with overlapping `files_hint`). `layer: ui` is **not** auto-serialized — UI tasks parallelize unless their `files_hint` overlaps.\n5. **Pick the mode.** Run the decision tree (below; full form → [`.\u002Freferences\u002Fdecision-tree.md`](.\u002Freferences\u002Fdecision-tree.md)). Apply the guards.\n6. **Generate the run-plan.** Sequential → an ordered task list. Team → a shared TaskList with the full task text in each body. Workflow → a generated `Workflow` script (DAG → Kahn phases → fan-out pipeline). → [`.\u002Freferences\u002Fteam-exec.md`](.\u002Freferences\u002Fteam-exec.md) \u002F [`.\u002Freferences\u002Fworkflow-exec.md`](.\u002Freferences\u002Fworkflow-exec.md).\n7. **Banner.** Print the active mode and the settings that drove it: `mode=\u003C…> tdd=\u003C…> isolation=\u003C…> parallel=\u003Cn> integration=\u003C…>`. The user sees exactly how the engine will behave before it acts.\n8. **Execute** in the chosen mode. Every task runs the TDD cycle → [`.\u002Freferences\u002Ftdd-loop.md`](.\u002Freferences\u002Ftdd-loop.md). A `layer: migration` task first **promotes** its staged migration(s) (`docs\u002Ffeatures\u002F\u003Cslug>\u002Fmigrations\u002F\u003CNN>_*`) into the live migrations tree — assigning the real sequence number \u002F timestamp per the repo's convention, in ordinal order — *then* applies + reverts them; detail → [`.\u002Freferences\u002Finputs.md`](.\u002Freferences\u002Finputs.md).\n9. **Per-task gate + commit.** RED runs in `sdlc:test-author`, GREEN in `sdlc:implementer`, REFACTOR in the isolated `sdlc:refactor` agent. After GREEN+REFACTOR the **engine** runs the gate — unit + (integration if available) + lint + vet must be clean — then commits task-scoped with trailers `SDLC-Task: \u003Cid>` and `SDLC-AC: \u003Cid>` (one per satisfied AC). GATE + COMMIT are the engine's, not any agent's. Update `tasks\u002Ftracker.md` → `done`.\n10. **Summary + hand off.** Report covered AC, commits made (with `SDLC-Task` trailers), any task dropped\u002Fblocked, and the per-task gate results. Then **emit the stage-handoff block** per [`..\u002F_shared\u002Fhandoff.md`](..\u002F_shared\u002Fhandoff.md) — *What I did* (covered AC, commits with `SDLC-Task` trailers, gate results) + *Review* (the committed diff + `tasks\u002Ftracker.md`) + *Run next* (`\u002Fclear`, then `\u002Fsdlc:review-feature \u003Cslug>` — a clean-context pass over the whole diff), then `\u002Fsdlc:ship-feature \u003Cslug>`. In team mode the [`reviewer`](..\u002F..\u002Fagents\u002Freviewer.md) may also run per-task, but the authoritative independent review of the whole change lives in the `review-feature` skill — `implement-tasks` does not self-certify.\n\n## Decision tree (compact)\n\n```\nparallel_eligible := isolation==worktree AND max_parallel>1 AND parallel_width>=2\n                     AND (size in {M,L,XL} OR task_count>=4)\n\nif team_mode AND parallel_eligible:                          → AGENT TEAM (TeamCreate) over the DAG\nelif workflow_mode==\"auto\" AND parallel_eligible AND Workflow-available: → DYNAMIC WORKFLOW\nelse:                                                        → SEQUENTIAL single-agent TDD (topo order)\n```\n\n**Guards (apply before dispatch):** `team_mode` but not eligible → warn + downgrade to the next mode. `max_parallel>1` with `isolation: inplace` → clamp parallel to 1 (no two agents edit one tree). `workflow_mode: off` → never generate a Workflow. `tdd: false` → skip RED (warn loudly — you lose the safety net). `require_integration: always` but Docker absent → **BLOCK** before dispatch; `auto` → run unit-only and mark integration NON-red; `never` → skip the integration tier. Full table → [`.\u002Freferences\u002Fdecision-tree.md`](.\u002Freferences\u002Fdecision-tree.md). Graceful degrade: if `Workflow`\u002F`TeamCreate` is unavailable at runtime, fall through to sequential.\n\n## TDD cycle (per task)\n\n`SELECT → RED → GREEN → REFACTOR → GATE → COMMIT` — RED in `sdlc:test-author`, GREEN in `sdlc:implementer`, REFACTOR in the isolated `sdlc:refactor`, GATE + COMMIT on the engine. The RED step is load-bearing: write the test first, run it, and **classify the first run** — GOOD red (assertion fails \u002F unimplemented) vs BAD red (the test itself won't compile → fix the test) vs false-pass (green immediately → the test is too weak, strengthen it) vs NON-red (skipped because Docker is absent → governed by `require_integration`, counts as neither red nor green). Quote the failing line before writing any production code. Escalation on persistent red → [`.\u002Freferences\u002Fescalation.md`](.\u002Freferences\u002Fescalation.md): more-capable model → retry → split the task → if the test encodes a wrong AC, **ask a human** (never weaken the test) → rollback to the last green. `stop_on_red` decides halt vs drop-and-continue (dependents auto-block).\n\n## Definition of Done\n\n- Every task in `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks\u002Ftasks.json` is either committed (test-first, gate-clean, `SDLC-Task`\u002F`SDLC-AC` trailers) or explicitly reported as dropped\u002Fblocked with the reason.\n- Unit gate green; integration green where available (or NON-red recorded with the policy reason); lint + vet clean per the detected commands.\n- The active mode + settings were printed in the banner before execution.\n- `tasks\u002Ftracker.md` reflects final status; the summary reports the gate results and hands off to `review-feature` (the independent review gate) — `implement-tasks` does not self-certify the whole change.\n\n## Anti-patterns\n\n- **Code before the test.** RED first, always (unless `tdd: false`, which warns).\n- **Weakening a test to make it pass.** If the AC is wrong, ask a human and fix the AC; never edit the test to be less strict.\n- **Skipping the RED classification.** A false-pass that looks green hides a useless test.\n- **Parallel agents editing one working tree.** Parallelism requires worktree isolation — the guard clamps it.\n- **Committing with a red or skipped gate** and calling it done. A NON-red integration tier must be labelled, not hidden.\n- **Spawning a team for \u003C4 tasks** — coordination overhead exceeds the gain; the eligibility check forbids it.\n- **Claiming integration passed when Docker was absent.** Report NON-red honestly.\n\n## References & template\n\n`inputs.md` · `settings.md` · `command-detection.md` · `decision-tree.md` · `tdd-loop.md` · `team-exec.md` · `workflow-exec.md` · `escalation.md` — all in [`.\u002Freferences\u002F`](.\u002Freferences\u002F).\n","# Skill: implement-tasks (SDLC stage 17 — Code)\n\nThe implementation engine — the keystone that closes the cycle. It turns `tasks.json` into committed, tested code through a strict TDD cycle per task — `SELECT → RED → GREEN → REFACTOR → GATE → COMMIT` — and orchestrates that cycle in one of three modes (sequential \u002F agent-team \u002F dynamic-workflow) picked by an unambiguous decision tree. Everything is stack-agnostic: the test, lint, and vet commands are **detected**, never hard-coded.\n\nThis file is the spine. Each step delegates to a file in `references\u002F`.\n\n## Owner\n\nTech Lead drives; the engine runs the cycle. Four subagents ship with the plugin: [`test-author`](..\u002F..\u002Fagents\u002Ftest-author.md) (`sdlc:test-author`, RED), [`implementer`](..\u002F..\u002Fagents\u002Fimplementer.md) (`sdlc:implementer`, GREEN), [`refactor`](..\u002F..\u002Fagents\u002Frefactor.md) (`sdlc:refactor`, REFACTOR — isolated, tidies while green), [`reviewer`](..\u002F..\u002Fagents\u002Freviewer.md) (`sdlc:reviewer`, read-only review). GATE + COMMIT stay on the engine, which owns the settings and the `require_integration` policy.\n\n## Inputs\n\n- `\u003Cslug>` — feature slug.\n- **Gate (hard refuse):** `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks\u002Ftasks.json` (legacy fallback: `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks.json`, used only when the first is absent). Both missing → «run `\u002Fsdlc:break-tasks \u003Cslug>` first». Greenfield skeleton: `\u003Cslug>` = `_scaffold` (written by `map-architecture`).\n- Read for context (the agents read these directly, not via paraphrase): `PRD.md` (AC), `data-model.md` + the **staged** migrations under `docs\u002Ffeatures\u002F\u003Cslug>\u002Fmigrations\u002F` (a `layer: migration` task **promotes** these into the live migrations tree — see [`.\u002Freferences\u002Finputs.md`](.\u002Freferences\u002Finputs.md)), `contracts\u002Fopenapi.yaml`, `test-plan.md`, `sad.md`, Accepted `adr\u002F`.\n- Settings: `.claude\u002Fsdlc.local.md` (auto-created with documented defaults if absent — normally by `write-prd` at the backbone start; `implement-tasks` creates it too if you jump straight here) → [`.\u002Freferences\u002Fsettings.md`](.\u002Freferences\u002Fsettings.md).\n\n## Protocol\n\n1. **Preconditions.** Resolve the plan path — `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks\u002Ftasks.json`, else the legacy `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks.json` (warn that it's legacy) — verify it parses; load the upstream artifacts list. Detail → [`.\u002Freferences\u002Finputs.md`](.\u002Freferences\u002Finputs.md).\n2. **Settings.** Read `.claude\u002Fsdlc.local.md`; if absent, auto-create it with the documented defaults (frontmatter + the «What each key does» body, self-documenting) and patch `.gitignore` (`.claude\u002F*.local.md`, `.worktrees\u002F`) — the same template `write-prd` writes. → [`.\u002Freferences\u002Fsettings.md`](.\u002Freferences\u002Fsettings.md).\n3. **Detect commands.** Run the stack-agnostic cascade (settings override → Makefile → package scripts → language manifests → Docker probe for the integration tier) to resolve unit \u002F integration \u002F lint \u002F vet commands. Print what was detected. → [`.\u002Freferences\u002Fcommand-detection.md`](.\u002Freferences\u002Fcommand-detection.md).\n4. **Build the DAG.** Parse `tasks.json`, validate `deps` is acyclic, topologically sort into phases (Kahn). Compute `task_count`, `longest_chain`, `parallel_width`. Mark serialization lanes (`layer: migration`; tasks with overlapping `files_hint`). `layer: ui` is **not** auto-serialized — UI tasks parallelize unless their `files_hint` overlaps.\n5. **Pick the mode.** Run the decision tree (below; full form → [`.\u002Freferences\u002Fdecision-tree.md`](.\u002Freferences\u002Fdecision-tree.md)). Apply the guards.\n6. **Generate the run-plan.** Sequential → an ordered task list. Team → a shared TaskList with the full task text in each body. Workflow → a generated `Workflow` script (DAG → Kahn phases → fan-out pipeline). → [`.\u002Freferences\u002Fteam-exec.md`](.\u002Freferences\u002Fteam-exec.md) \u002F [`.\u002Freferences\u002Fworkflow-exec.md`](.\u002Freferences\u002Fworkflow-exec.md).\n7. **Banner.** Print the active mode and the settings that drove it: `mode=\u003C…> tdd=\u003C…> isolation=\u003C…> parallel=\u003Cn> integration=\u003C…>`. The user sees exactly how the engine will behave before it acts.\n8. **Execute** in the chosen mode. Every task runs the TDD cycle → [`.\u002Freferences\u002Ftdd-loop.md`](.\u002Freferences\u002Ftdd-loop.md). A `layer: migration` task first **promotes** its staged migration(s) (`docs\u002Ffeatures\u002F\u003Cslug>\u002Fmigrations\u002F\u003CNN>_*`) into the live migrations tree — assigning the real sequence number \u002F timestamp per the repo's convention, in ordinal order — *then* applies + reverts them; detail → [`.\u002Freferences\u002Finputs.md`](.\u002Freferences\u002Finputs.md).\n9. **Per-task gate + commit.** RED runs in `sdlc:test-author`, GREEN in `sdlc:implementer`, REFACTOR in the isolated `sdlc:refactor` agent. After GREEN+REFACTOR the **engine** runs the gate — unit + (integration if available) + lint + vet must be clean — then commits task-scoped with trailers `SDLC-Task: \u003Cid>` and `SDLC-AC: \u003Cid>` (one per satisfied AC). GATE + COMMIT are the engine's, not any agent's. Update `tasks\u002Ftracker.md` → `done`.\n10. **Summary + hand off.** Report covered AC, commits made (with `SDLC-Task` trailers), any task dropped\u002Fblocked, and the per-task gate results. Then **emit the stage-handoff block** per [`..\u002F_shared\u002Fhandoff.md`](..\u002F_shared\u002Fhandoff.md) — *What I did* (covered AC, commits with `SDLC-Task` trailers, gate results) + *Review* (the committed diff + `tasks\u002Ftracker.md`) + *Run next* (`\u002Fclear`, then `\u002Fsdlc:review-feature \u003Cslug>` — a clean-context pass over the whole diff), then `\u002Fsdlc:ship-feature \u003Cslug>`. In team mode the [`reviewer`](..\u002F..\u002Fagents\u002Freviewer.md) may also run per-task, but the authoritative independent review of the whole change lives in the `review-feature` skill — `implement-tasks` does not self-certify.\n\n## Decision tree (compact)\n\n```\nparallel_eligible := isolation==worktree AND max_parallel>1 AND parallel_width>=2\n                     AND (size in {M,L,XL} OR task_count>=4)\n\nif team_mode AND parallel_eligible:                          → AGENT TEAM (TeamCreate) over the DAG\nelif workflow_mode==\"auto\" AND parallel_eligible AND Workflow-available: → DYNAMIC WORKFLOW\nelse:                                                        → SEQUENTIAL single-agent TDD (topo order)\n```\n\n**Guards (apply before dispatch):** `team_mode` but not eligible → warn + downgrade to the next mode. `max_parallel>1` with `isolation: inplace` → clamp parallel to 1 (no two agents edit one tree). `workflow_mode: off` → never generate a Workflow. `tdd: false` → skip RED (warn loudly — you lose the safety net). `require_integration: always` but Docker absent → **BLOCK** before dispatch; `auto` → run unit-only and mark integration NON-red; `never` → skip the integration tier. Full table → [`.\u002Freferences\u002Fdecision-tree.md`](.\u002Freferences\u002Fdecision-tree.md). Graceful degrade: if `Workflow`\u002F`TeamCreate` is unavailable at runtime, fall through to sequential.\n\n## TDD cycle (per task)\n\n`SELECT → RED → GREEN → REFACTOR → GATE → COMMIT` — RED in `sdlc:test-author`, GREEN in `sdlc:implementer`, REFACTOR in the isolated `sdlc:refactor`, GATE + COMMIT on the engine. The RED step is load-bearing: write the test first, run it, and **classify the first run** — GOOD red (assertion fails \u002F unimplemented) vs BAD red (the test itself won't compile → fix the test) vs false-pass (green immediately → the test is too weak, strengthen it) vs NON-red (skipped because Docker is absent → governed by `require_integration`, counts as neither red nor green). Quote the failing line before writing any production code. Escalation on persistent red → [`.\u002Freferences\u002Fescalation.md`](.\u002Freferences\u002Fescalation.md): more-capable model → retry → split the task → if the test encodes a wrong AC, **ask a human** (never weaken the test) → rollback to the last green. `stop_on_red` decides halt vs drop-and-continue (dependents auto-block).\n\n## Definition of Done\n\n- Every task in `docs\u002Ffeatures\u002F\u003Cslug>\u002Ftasks\u002Ftasks.json` is either committed (test-first, gate-clean, `SDLC-Task`\u002F`SDLC-AC` trailers) or explicitly reported as dropped\u002Fblocked with the reason.\n- Unit gate green; integration green where available (or NON-red recorded with the policy reason); lint + vet clean per the detected commands.\n- The active mode + settings were printed in the banner before execution.\n- `tasks\u002Ftracker.md` reflects final status; the summary reports the gate results and hands off to `review-feature` (the independent review gate) — `implement-tasks` does not self-certify the whole change.\n\n## Anti-patterns\n\n- **Code before the test.** RED first, always (unless `tdd: false`, which warns).\n- **Weakening a test to make it pass.** If the AC is wrong, ask a human and fix the AC; never edit the test to be less strict.\n- **Skipping the RED classification.** A false-pass that looks green hides a useless test.\n- **Parallel agents editing one working tree.** Parallelism requires worktree isolation — the guard clamps it.\n- **Committing with a red or skipped gate** and calling it done. A NON-red integration tier must be labelled, not hidden.\n- **Spawning a team for \u003C4 tasks** — coordination overhead exceeds the gain; the eligibility check forbids it.\n- **Claiming integration passed when Docker was absent.** Report NON-red honestly.\n\n## References & template\n\n`inputs.md` · `settings.md` · `command-detection.md` · `decision-tree.md` · `tdd-loop.md` · `team-exec.md` · `workflow-exec.md` · `escalation.md` — all in [`.\u002Freferences\u002F`](.\u002Freferences\u002F).\n",{"name":5,"model":24,"stage":25,"agents":26,"effort":31,"triggers":32,"description":34},"inherit","17",[27,28,29,30],"test-author","implementer","refactor","reviewer","medium",[33],"\u002Fsdlc:implement-tasks","Use to implement a feature from its tasks.json with test-driven development — writes a failing test first, makes it pass, refactors, gates, and commits per task. Triggers on \"\u002Fsdlc:implement-tasks {slug}\", \"implement {slug}\", \"build {slug}\", \"TDD {slug}\", \"code up the tasks for {slug}\", \"імплементуй {slug}\", \"реалізуй фічу {slug}\", \"напиши код за задачами {slug}\". Reads docs\u002Ffeatures\u002F{slug}\u002Ftasks\u002Ftasks.json + the upstream artifacts, detects the repo's test\u002Flint\u002Fvet commands stack-agnostically, builds a dependency DAG, and runs one of three modes — sequential single-agent TDD, an agent team (TeamCreate), or a dynamic Workflow — chosen from settings + DAG shape with graceful fallback. Output: committed, tested code + updated tasks\u002Ftracker.md. Hard-refuses if docs\u002Ffeatures\u002F{slug}\u002Ftasks\u002Ftasks.json is missing (the legacy docs\u002Ffeatures\u002F{slug}\u002Ftasks.json is accepted as a fallback) → run `\u002Fsdlc:break-tasks {slug}` first.\n","main","2dc9bdfa5d508a04d414fb0991617e6722ec635a","modules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks",13,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public","https:\u002F\u002Ft.me\u002Fgenkovich","https:\u002F\u002Fgithub.com\u002Fgenkovich","https:\u002F\u002Ft.me\u002Fbeerphp","Beer::PHP 🍺 telegram-channel author \r\n","2026-11-12 03:03:13",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add genkovich\u002Fagentic-engineering-course-public --skill implement-tasks",{"tool":51,"command":52},"bunx","bunx skills add genkovich\u002Fagentic-engineering-course-public --skill implement-tasks",{"tool":54,"command":55},"pnpm","pnpm dlx skills add genkovich\u002Fagentic-engineering-course-public --skill implement-tasks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002FSKILL.md",true,[59,65,69,73,77,81,85,89],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fcommand-detection.md","REFERENCE","参考文档",2932,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Fcommand-detection.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fdecision-tree.md",3531,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Fdecision-tree.md",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fescalation.md",2299,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Fescalation.md",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Finputs.md",7336,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Finputs.md",{"path":78,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fsettings.md",7003,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Fsettings.md",{"path":82,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Ftdd-loop.md",5229,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Ftdd-loop.md",{"path":86,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fteam-exec.md",4156,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Fteam-exec.md",{"path":90,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fworkflow-exec.md",4142,"https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F6-sdlc\u002Fsdlc\u002Fplugin\u002Fskills\u002Fimplement-tasks\u002Freferences\u002Fworkflow-exec.md",[94,102,109,116,123,130],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":101},"01M72YGBW5JKECT8WSRHK1YBCJ","release","Run the whole local release pipeline in order, stopping at each human gate. Triggers on \"run the release\", \"prepare a release\", \"\u002Frelease\", \"зроби реліз\", \"підготуй реліз\". Drives the four stages back to back — bump-version → curate-changelog → release-notes → check-docs-drift — pausing after each so the human reviews the diff before the next stage. Prepares everything in the working tree; never tags, commits, or pushes. The tag push (which fires CI) stays the human's action.","https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F9-collaboration\u002F9.7-release-docs\u002F.claude\u002Fskills\u002Frelease\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":101},"01M72YG87VQ89PRCYQSMNAP5RW","release-notes","Draft partner-facing release notes from the same commits as the changelog. Triggers on \"draft release notes\", \"release notes for the next version\", \"\u002Frelease-notes\", \"нотатки релізу\", \"release notes партнеру\". Same input as curate-changelog, different audience and tone: a short, benefit-first narrative for a user or partner — \"what's new for you\" — not a categorized engineer's list. Keeps only changes a user actually notices; drops internal refactors and tooling. Prints the notes to the chat to seed a GitHub Release description or a partner announcement. Writes no file.","https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F9-collaboration\u002F9.7-release-docs\u002F.claude\u002Fskills\u002Frelease-notes\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":101},"01M72YG4BXJH9R6QQZD3G8E358","curate-changelog","Curate the [Unreleased] section of docs\u002FCHANGELOG.md from git history. Triggers on \"curate the changelog\", \"update the changelog\", \"\u002Fcurate-changelog\", \"онови changelog\", \"курування журналу\". Reads git log since the last tag, FILTERS out what a reader never feels (test\u002Fci\u002Fchore\u002Fmerge), GROUPS commits about one feature into one bullet, and REWRITES technical subjects into plain language under the six Keep a Changelog categories (Added\u002FChanged\u002FDeprecated\u002F Removed\u002FFixed\u002FSecurity). The result must have FEWER lines than the raw log — that is the proof of curation, not a dump. Leaves the edit in the working tree; never commits or pushes.","https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F9-collaboration\u002F9.7-release-docs\u002F.claude\u002Fskills\u002Fcurate-changelog\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":101},"01M72YFZDKNXQ7WF9ARC5KQ4F5","codify-rule","Turn a repeated mistake into a durable, path-scoped rule in .claude\u002Frules\u002F. Triggers on \"codify this rule\", \"make a rule so this doesn't happen again\", \"\u002Fcodify-rule\", \"закодифікуй правило\", \"петля помилка-правило\". Use only when the same mistake showed up TWICE (twice = a pattern, once = noise). Names the wrong shape and the right shape with one short example of each, scopes the rule to the paths that matter, and leaves the edit in the working tree so the next agent on this repo inherits the fix. Edits only .claude\u002Frules\u002F; never commits or pushes.","https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F9-collaboration\u002F9.7-release-docs\u002F.claude\u002Fskills\u002Fcodify-rule\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":101},"01M72YFVKC19NCQDD30R1C282Q","check-docs-drift","Find and fix where docs\u002Fapi.md fell behind the code. Triggers on \"check for doc drift\", \"is the API doc up to date\", \"\u002Fcheck-docs-drift\", \"перевір дрейф документації\", \"docs drift\". Runs the deterministic scripts\u002Fcheck-docs-drift.py (parses the public NoteBook methods with ast, compares to what docs\u002Fapi.md documents — NO LLM finds the gap), reports the drift, and PROPOSES the doc edit that closes it. The gap is found by parsing; the agent writes the missing documentation in the doc's existing style. Edits only docs\u002F; never commits or pushes.","https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F9-collaboration\u002F9.7-release-docs\u002F.claude\u002Fskills\u002Fcheck-docs-drift\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":101},"01M72YFQSJ21QX4SQADQ1SQDZR","bump-version","Decide and apply the next semver for a release. Triggers on \"bump the version\", \"what version is next\", \"\u002Fbump-version\", \"простав версію\", \"яка наступна версія\". Reads the next number from the deterministic scripts\u002Fnext-version.sh (NEVER guesses it), explains in plain language WHICH part moved and why (e.g. \"MINOR, because a feat landed: filter notes by tag\"), edits the version line in pyproject.toml, and proposes the matching `git tag vX.Y.Z`. The number is decided by a rule; the agent explains and applies — the human confirms the tag. Never pushes a tag itself.","https:\u002F\u002Fgithub.com\u002Fgenkovich\u002Fagentic-engineering-course-public\u002Fblob\u002Fmain\u002Fmodules\u002F9-collaboration\u002F9.7-release-docs\u002F.claude\u002Fskills\u002Fbump-version\u002FSKILL.md",[],[]]