papadopouloskyriakos/agentic-chatops/tasks
Claude Code and agent skill by papadopouloskyriakos/agentic-chatops
- community
Checking that the SKILL.md file is still in the repository.
Phase E of greenfield project bootstrap. Atomize design.md + contracts into tasks.json with files_owned + dependencies + acceptance_test + risk_score per task. Iterates until task-dag-validate passes.
Install
npx vskill@latest install papadopouloskyriakos/agentic-chatops/tasksSKILL.md
/tasks — atomize design into parallel-dev work_units
After /plan produced design.md + contracts, this skill decomposes the work into atomic tasks suitable for ≤4 parallel Claude workers.
Output
spec/001-<slug>/tasks.json per <bootstrap-pack>/templates/tasks.schema.json.
Atomization rules (load-bearing)
For each task you write:
- files_owned — exact file paths (relative to repo root) the task will create or modify. Must be non-empty. NEW files OK.
- dependencies — list of task_ids this task depends on. Empty list = wave-0 task.
- parallelizable —
trueif it can run alongside other tasks in the same wave;falseif it needs exclusive write access. - acceptance_test — executable command (e.g.
go test ./... -run TestFoo) that returns exit 0 iff the task succeeded. NOT prose. - bounded_context — exactly one value from
PROJECT.json#bounded_contexts. - requirement_ids — list of REQ-NNN this task fulfills (must exist in
requirements.md). - risk_score — 0.0 to 1.0. >0.7 triggers needs-human auto-merge gate.
- complexity — 1 to 10. >5 should be split.
Hard constraints (rejected at validation time)
- No two
parallelizable: truetasks in the same wave may share anyfiles_ownedentry. The validator'sparallelizable_no_file_collisioncatches this. - Dependency graph must be acyclic (
tasks_dag_no_cycles). - Every
requirement_idsentry must exist (req_cross_references). - Max 4 parallel tasks per wave (matches MAX_WORKERS in parallel-dev).
Validation loop
After writing tasks.json, run:
If any fail, iterate. Don't exit until all 6 pass.
Template
<bootstrap-pack>/templates/tasks.json.tmpl shows the per-task schema.
Definition of done
- [ ] tasks.json exists at spec/001-*/
- [ ] All 6 task-related validator checks pass
- [ ] No more than 4 parallelizable tasks per wave
- [ ] Operator has reviewed the decomposition + accepted
What's next
Operator runs /bootstrap (meta-skill) which chains all of /specify → /constitute → /plan → /tasks → validator, or directly runs project-onboard.sh to register the project with the gateway.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingbootstrap-pack/.claude/skills/tasks/SKILL.md
Popularity
- Repository stars
- 107
- Repository forks
- 26
- 7-day trend score
- 23
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/papadopouloskyriakos/agentic-chatops/tasks)