task-decomposition-coarse

Name: task-decomposition-coarse
Author: pavel-molyanov

241stars75forks

How to install task-decomposition-coarse?

pavel-molyanov/molyanov-ai-dev/task-decomposition-coarse

$npx -y skills add pavel-molyanov/molyanov-ai-dev --skill task-decomposition-coarse

Installs into the current project.

Summary

Decompose approved coarse tech-spec into task files with parallel creation and validation. Coarse variant: each Implementation Task in tech-spec produces one task file covering one skill's cohesive scope. Use when: "разбей на задачи coarse", "декомпозиция крупно", "разбей задачи

Files · 1

View on GitHub

SKILL.md

1	<!-- Generated by sync-to-codex v1. Do not edit directly. -->
2
3	# Task Decomposition (Coarse Variant)
4
5	Decompose coarse tech-spec Implementation Tasks into individual task files with parallel creation and validation. Each task covers one skill's cohesive scope — not atomic units.
6
7	Input: `work/{feature}/tech-spec.md` (status: approved, produced by tech-spec-planning-coarse)
8	Output: `work/{feature}/tasks/*.md` (validated)
9	Language: Task files in English; communication with the user in the language the user writes in
10
11	## Phase 1: Create Tasks
12
13	1. Ask user for feature name if not provided.
14
15	2. Read `work/{feature}/tech-spec.md`. Check frontmatter `status: approved`.
16	If not approved — tell the user (in their language): "tech-spec is not approved. Run `/new-tech-spec-coarse` first and get it to approved." Stop.
17
18	3. Read `work/{feature}/user-spec.md`.
19
20	4. Note the task template path: `~/.claude/shared/work-templates/tasks/task.md.template`
21
22	5. Read skills/reviewers catalog from [skills-and-reviewers.md](~/.claude/skills/tech-spec-planning/references/skills-and-reviewers.md) — shared across standard and coarse variants.
23
24	6. For each task in Implementation Tasks — launch [`task-creator-coarse`](~/.claude/agents/task-creator-coarse.md) subagent in parallel.
25	Pass each task-creator-coarse:
26	- feature_path, task_number, task_name
27	- template_path: `~/.claude/shared/work-templates/tasks/task.md.template`
28	- files_to_modify, files_to_read (from tech-spec)
29	- depends_on, wave, skills, reviewers, verify (from tech-spec)
30	- teammate_name (if specified in tech-spec, optional)
31
32	Each task-creator-coarse copies the template to `tasks/{N}.md` first, then edits each section in place — this ensures no sections are skipped. For coarse tasks: What to do is filled as a checklist of related steps with commit points between them.
33
34	Coarse rule: each task scopes to exactly one skill from the catalog. Exception: audit/QA tasks (Code Audit, Security Audit, Test Audit, pre-deploy-qa, post-deploy-qa) use methodology skills and sit in their own waves — they are not subject to the one-skill-per-task rule.
35
36	7. Confirm each task-creator-coarse returned a file path. Skip reading task content — preserve context budget for validation phase.
37	8. Git commit: `draft(tasks): create {N} coarse tasks from tech-spec for {feature}`
38
39	Checkpoint:
40	- [ ] All `tasks/*.md` files created
41	- [ ] Each task-creator-coarse returned file path
42	- [ ] Draft committed
43
44	## Phase 2: Validation (up to 3 iterations)
45
46	Tech-spec was already validated. This phase checks only: (1) task-creator-coarse correctly expanded tasks by template with coarse-specific content, (2) no mismatches with real code appeared during detailing, (3) one-skill-per-task rule holds.
47
48	### Validators
49
50	Launch both in parallel:
51
52	[`task-validator-coarse`](~/.claude/agents/task-validator-coarse.md) (sonnet) — Template Compliance + Scope + AC/TDD carry-forward:
53	- Batch: 5 tasks per call
54	- Pass: feature_path, task_numbers array, batch_number, iteration
55	- Report: `logs/tasks/template-batch{N}-review.json`
56
57	[`reality-checker`](~/.claude/agents/reality-checker.md) (sonnet) — Reality & Adequacy (shared agent, no coarse variant needed):
58	- Batch: 3 tasks per call
59	- Pass: feature_path, task_numbers array, batch_number, iteration
60	- Report: `logs/tasks/reality-batch{N}-review.json`
61
62	### Process
63
64	1. Launch both validators in parallel.
65	2. Read JSON reports, collect findings.
66	3. If issues found — for each task with issues, launch [`task-creator-coarse`](~/.claude/agents/task-creator-coarse.md) in fix mode:
67	- Pass: same inputs as creation + `mode: fix` + `findings` from validators
68	- task-creator-coarse reads existing task, applies fixes, overwrites file
69	4. After each validation round, git commit: `chore(tasks): validation round {N} — {summary}`
70	5. Re-validate fixed tasks. Maximum 3 iterations.
71	6. If problems remain after 3rd iteration — show the user (in their language): "Here's what's left — let's resolve it together."
72
73	### Cross-Task Integration Check
74
75	After individual validation passes, run a final cross-task check:
76
77	1. Launch both validators on ALL tasks in a single batch:
78	- `task-validator-coarse` — focus: skill overlap across tasks (two tasks with same skill on same module = merge candidate), shared resource ownership, no competing instances in same wave
79	- `reality-checker` — focus: duplicate heavy resource init, hidden dependencies, inconsistent approaches

People who liked this also viewed

6 picks

Type

task-decomposition-coarse

241stars75forks

View on GitHub

How to install task-decomposition-coarse?

pavel-molyanov/molyanov-ai-dev/task-decomposition-coarse

$npx -y skills add pavel-molyanov/molyanov-ai-dev --skill task-decomposition-coarse

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	<!-- Generated by sync-to-codex v1. Do not edit directly. -->
2
3	# Task Decomposition (Coarse Variant)
4
5	Decompose coarse tech-spec Implementation Tasks into individual task files with parallel creation and validation. Each task covers one skill's cohesive scope — not atomic units.
6
7	Input: `work/{feature}/tech-spec.md` (status: approved, produced by tech-spec-planning-coarse)
8	Output: `work/{feature}/tasks/*.md` (validated)
9	Language: Task files in English; communication with the user in the language the user writes in
10
11	## Phase 1: Create Tasks
12
13	1. Ask user for feature name if not provided.
14
15	2. Read `work/{feature}/tech-spec.md`. Check frontmatter `status: approved`.
16	If not approved — tell the user (in their language): "tech-spec is not approved. Run `/new-tech-spec-coarse` first and get it to approved." Stop.
17
18	3. Read `work/{feature}/user-spec.md`.
19
20	4. Note the task template path: `~/.claude/shared/work-templates/tasks/task.md.template`
21
22	5. Read skills/reviewers catalog from [skills-and-reviewers.md](~/.claude/skills/tech-spec-planning/references/skills-and-reviewers.md) — shared across standard and coarse variants.
23
24	6. For each task in Implementation Tasks — launch [`task-creator-coarse`](~/.claude/agents/task-creator-coarse.md) subagent in parallel.
25	Pass each task-creator-coarse:
26	- feature_path, task_number, task_name
27	- template_path: `~/.claude/shared/work-templates/tasks/task.md.template`
28	- files_to_modify, files_to_read (from tech-spec)
29	- depends_on, wave, skills, reviewers, verify (from tech-spec)
30	- teammate_name (if specified in tech-spec, optional)
31
32	Each task-creator-coarse copies the template to `tasks/{N}.md` first, then edits each section in place — this ensures no sections are skipped. For coarse tasks: What to do is filled as a checklist of related steps with commit points between them.
33
34	Coarse rule: each task scopes to exactly one skill from the catalog. Exception: audit/QA tasks (Code Audit, Security Audit, Test Audit, pre-deploy-qa, post-deploy-qa) use methodology skills and sit in their own waves — they are not subject to the one-skill-per-task rule.
35
36	7. Confirm each task-creator-coarse returned a file path. Skip reading task content — preserve context budget for validation phase.
37	8. Git commit: `draft(tasks): create {N} coarse tasks from tech-spec for {feature}`
38
39	Checkpoint:
40	- [ ] All `tasks/*.md` files created
41	- [ ] Each task-creator-coarse returned file path
42	- [ ] Draft committed
43
44	## Phase 2: Validation (up to 3 iterations)
45
46	Tech-spec was already validated. This phase checks only: (1) task-creator-coarse correctly expanded tasks by template with coarse-specific content, (2) no mismatches with real code appeared during detailing, (3) one-skill-per-task rule holds.
47
48	### Validators
49
50	Launch both in parallel:
51
52	[`task-validator-coarse`](~/.claude/agents/task-validator-coarse.md) (sonnet) — Template Compliance + Scope + AC/TDD carry-forward:
53	- Batch: 5 tasks per call
54	- Pass: feature_path, task_numbers array, batch_number, iteration
55	- Report: `logs/tasks/template-batch{N}-review.json`
56
57	[`reality-checker`](~/.claude/agents/reality-checker.md) (sonnet) — Reality & Adequacy (shared agent, no coarse variant needed):
58	- Batch: 3 tasks per call
59	- Pass: feature_path, task_numbers array, batch_number, iteration
60	- Report: `logs/tasks/reality-batch{N}-review.json`
61
62	### Process
63
64	1. Launch both validators in parallel.
65	2. Read JSON reports, collect findings.
66	3. If issues found — for each task with issues, launch [`task-creator-coarse`](~/.claude/agents/task-creator-coarse.md) in fix mode:
67	- Pass: same inputs as creation + `mode: fix` + `findings` from validators
68	- task-creator-coarse reads existing task, applies fixes, overwrites file
69	4. After each validation round, git commit: `chore(tasks): validation round {N} — {summary}`
70	5. Re-validate fixed tasks. Maximum 3 iterations.
71	6. If problems remain after 3rd iteration — show the user (in their language): "Here's what's left — let's resolve it together."
72
73	### Cross-Task Integration Check
74
75	After individual validation passes, run a final cross-task check:
76
77	1. Launch both validators on ALL tasks in a single batch:
78	- `task-validator-coarse` — focus: skill overlap across tasks (two tasks with same skill on same module = merge candidate), shared resource ownership, no competing instances in same wave
79	- `reality-checker` — focus: duplicate heavy resource init, hidden dependencies, inconsistent approaches

People who liked this also viewed

6 picks

Type