Best for
- Context injection for epic planning and task decomposition tasks spawned via cleo-subagent. Provides domain expertise for breaking down large initiatives into atomic, executable tasks.
kryptobaseddev/cleo/packages/skills/skills/ct-epic-architect/SKILL.md
Epic planning and task decomposition for breaking down large initiatives into atomic, executable tasks. Provides dependency analysis, wave-based parallel execution planning, hierarchy management, and research linking. Use when creating epics, decomposing initiatives into task trees, planning parallel workflows, or analyzing task dependencies. Triggers on epic creation, task decomposition requests, or planning phase work.
Decision brief
Protocol: @src/protocols/decomposition.md Type: Context Injection (cleo-subagent) Version: 3.0.0
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Declared | Source record | Install path and trigger |
| Gemini CLI | Declared | Source record | Install path and trigger |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/kryptobaseddev/cleo --skill "packages/skills/skills/ct-epic-architect"Inspect the Agent Skill "ct-epic-architect" from https://github.com/kryptobaseddev/cleo/blob/77fb47e0495c2456dfd45bdbe480198e7445123b/packages/skills/skills/ct-epic-architect/SKILL.md at commit 77fb47e0495c2456dfd45bdbe480198e7445123b. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
Review the “Phase Assignment” section in the pinned source before continuing.
Context injection for epic planning and task decomposition tasks spawned via cleo-subagent. Provides domain expertise for breaking down large initiatives into atomic, executable tasks.
1. Epic Creation - Parent epic with full metadata and file attachments 2. Task Decomposition - Atomic tasks with acceptance criteria 3. Dependency Analysis - Wave-based parallel execution planning 4. Research Linking - Connect research outputs to tasks 5. HITL Clarification - As…
@skills/shared/task-system-integration.md
1. Read task: cleo show {{TASKID}} 2. Start task: cleo start {{TASKID}} 3. Check existing work: cleo find "keyword", cleo list --type epic 4. Create epic and child tasks 5. Attach files and link research 6. Start session: cleo session start --scope epic:{{EPICID}} --auto-start 7…
Permission review
The documentation asks the agent to create, modify, or delete local files.
### Create Epic with File AttachmentsEvidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 97/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 160 | Source | Repository attention, not individual Skill quality |
| Compatibility | 3 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Protocol: @src/protocols/decomposition.md Type: Context Injection (cleo-subagent) Version: 3.0.0
Context injection for epic planning and task decomposition tasks spawned via cleo-subagent. Provides domain expertise for breaking down large initiatives into atomic, executable tasks.
@skills/_shared/task-system-integration.md
cleo show {{TASK_ID}}cleo start {{TASK_ID}}cleo find "keyword", cleo list --type epiccleo session start --scope epic:{{EPIC_ID}} --auto-startcleo complete {{TASK_ID}}MUST check for related work BEFORE creating:
cleo find "auth" --status pending # Related tasks
cleo list --type epic --status pending # Existing epics
cleo phase show # Current phase
cleo list --tree --parent T001 # Hierarchy view
Epic (type: epic, size: large)
├── Task 1 (no deps) [Wave 0]
├── Task 2 (depends: T1) [Wave 1]
├── Task 3 (depends: T1) [Wave 1] ← Parallel
├── Task 4 (depends: T2,T3) [Wave 2] ← Convergence
└── Task 5 (depends: T4) [Wave 3]
DO NOT redefine here. The strict definitions live in .cleo/adrs/ADR-073-above-epic-naming.md
§1.1 (tier table) + §1.2 (8 invariants I1–I8) + §1.3 (lifecycle decision table).
Quick reference for decomposition:
| Tier | Scope-of-change | Sizing |
|---|---|---|
| Saga | Theme grouping ≥2 Epics across ≥2 releases | ≥2 child Epics |
| Epic | One releasable slice; ≥1 PR to main | 4–10 child Tasks |
| Task | One atomic PR-sized change; single wave | 1–7 child Subtasks (or leaf); single PR |
| Subtask | One commit; ≤2 files OR one module boundary | 1 commit; contributes to parent Task's single PR |
I8 (load-bearing): A Task ships as exactly ONE PR. Multiple Subtasks contribute commits to that single PR. Subtasks never own a PR — if a unit warrants its own PR, it MUST be a Task. When decomposing, ask: "does this unit need its own PR?" → Task. "Is this a commit inside a larger PR?" → Subtask.
A Saga groups multiple Epics into a multi-release theme. Use a Saga when the work spans
more than one releasable Epic and you want a stable handle for rollup/reporting. A Saga uses
type='saga' (NOT label='saga') — it is a peer type discriminator at the top of the
parent ladder. All IDs are stored as T####; prefixes (SG-, E-) are display-only.
Saga membership uses parent_id containment (NOT task_relations.groups).
cleo saga create --title "Auth Modernization" --description "..." --acceptance "ac1|ac2|ac3|ac4|ac5"
# returns SG-id (stored as T#### with type=saga)
cleo saga add <sagaId> <epicId> # sets epic.parent_id = sagaId (containment edge)
cleo saga members <sagaId> # returns members via parent_id containment
cleo saga rollup <sagaId> # aggregates child statuses + completionPct
cleo add "Auth System Implementation" \
--type epic --size large --priority high --phase core \
--labels "feature,auth,v1.0" \
--description "Complete authentication with JWT and session management" \
--acceptance "All child tasks completed" \
--acceptance "Integration tests pass" \
--files "docs/auth-spec.md,docs/api-design.md" \
--notes "Initial planning: JWT chosen for stateless API support"
# Wave 0: No dependencies
cleo add "Create auth schema" \
--type task --size medium --priority high \
--parent T001 --phase setup \
--description "Define user, session, and token tables" \
--acceptance "Schema validates against requirements" \
--files "src/db/schema.ts"
# Wave 1: Depends on Wave 0
cleo add "Implement JWT middleware" \
--type task --size medium --priority high \
--parent T001 --phase core --depends T002 \
--description "Token generation, validation, refresh" \
--acceptance "All token operations tested"
# Wave 2: Convergence
cleo add "Integration tests" \
--type task --size medium --priority high \
--parent T001 --phase testing --depends T003,T004 \
--acceptance "E2E auth flow tests pass"
# Link existing research output to task
cleo research link T001 research-auth-patterns-20260126
# View linked research
cleo show T001 # Shows .linkedResearch array
| Method | Use Case | Storage |
|---|---|---|
--files | Input context (specs, designs, code) | Task .files array |
research link | Output artifacts (research findings) | Task .linkedResearch array |
cleo add "Implement auth" --files "spec.md,design.md"
cleo update T001 --files "additional-context.md"
| Constraint | Value | Enforcement |
|---|---|---|
| Max depth | 3 | epic (0) → task (1) → subtask (2) |
| Max active siblings | 8 (default) | hierarchy.maxActiveSiblings |
| Max siblings | unlimited (default) | hierarchy.maxSiblings=0 |
| Parent must exist | Validated | cleo exists {{PARENT_ID}} |
Validation Before Creation:
cleo exists T001 --quiet || echo "ERROR: Parent not found"
cleo list --parent T001 --status pending,active | jq '.tasks | length'
| Wave | Description | Execution |
|---|---|---|
| Wave 0 | No dependencies | Start immediately |
| Wave 1 | Depends on Wave 0 | Parallel within wave |
| Wave N | Depends on prior waves | Convergence points |
| Phase | Purpose |
|---|---|
setup | Schema, config, structure |
core | Features, components |
testing | Tests, validation |
polish | Docs, optimization |
maintenance | Fixes, updates |
cleo phase show # Current phase
cleo list --phase $(cleo phase show -q) # Tasks in phase
Ask when:
Template:
Before proceeding, I need clarification:
1. [Question about scope]
2. [Question about constraints]
Options:
A. [Option with trade-offs]
B. [Option with trade-offs]
Recommendation: [Your recommendation]
@skills/_shared/subagent-protocol-base.md
{{OUTPUT_DIR}}/{{DATE}}_{{TOPIC_SLUG}}.md{{MANIFEST_PATH}}| Reference | Content |
|---|---|
| patterns.md | Research, Bug, Brownfield, Refactor patterns |
| commands.md | Complete CLEO command reference |
| shell-escaping.md | Escape $ as \$ in notes |
| feature-epic-example.md | Greenfield feature |
| refactor-epic-example.md | Brownfield modernization |
| Anti-Pattern | Solution |
|---|---|
| Too large tasks | Atomic (one agent session) |
| Missing Wave 0 | At least one no-dependency task |
| Circular deps | Analyze data flow |
| Depth > 3 | Flatten hierarchy |
| Missing acceptance | Add --acceptance |
| Time estimates | Use size only |
cleo find, cleo list --type epic)cleo phase show)| Exit | Meaning | Fix |
|---|---|---|
| 4 | Not found | cleo find to verify |
| 10 | Parent missing | cleo exists {{ID}} |
| 11 | Depth exceeded | Flatten (epic→task→subtask max) |
| 12 | Sibling limit | Split to different parent |
| 6 | Validation | Escape $ as \$, check fields |
Shell Escaping: Always \$ in --notes/--description. See shell-escaping.md.
This skill binds to the decomposition LOOM lifecycle stage. Governing ADRs:
LOOM coverage matrix: docs/skills/loom-coverage-matrix.md.
Frequently asked questions
Protocol: @src/protocols/decomposition.md Type: Context Injection (cleo-subagent) Version: 3.0.0
The source record exposes this install command: npx skills add https://github.com/kryptobaseddev/cleo --skill "packages/skills/skills/ct-epic-architect". Inspect the command and pinned source before running it.
The pinned source record declares support for: claude code, cursor, gemini cli.
Static rules flagged write-files in the source; the page lists the matching lines and excerpts.
Alternatives
PramodDutta/qaskills
Generate optimized test combinations using pairwise (all-pairs) testing algorithms to achieve maximum coverage with minimum test cases across multiple input parameters
PramodDutta/qaskills
Gate RAG pipelines in CI with versioned golden eval sets, per-metric thresholds, baseline drift detection, and a build that fails when retrieval or answer quality regresses.
kryptobaseddev/cleo
Multi-source research and investigation combining web search, documentation lookup via Context7, and codebase analysis. Synthesizes findings into actionable recommendations with proper citation and task traceability. Use when conducting research, investigating best practices, gathering technical information, or analyzing existing implementations. Triggers on research tasks, investigation needs, or information discovery requests.
PramodDutta/qaskills
Optimize CI test pipelines through intelligent test splitting, parallelization, caching strategies, and selective test execution based on code changes.