hafez-decompose
Decompose an active project slice into bounded AI work units with explicit ownership, risk, parallelism, file scopes, verification, and worker tiers so a…
Skill by EngMahmoudHafez
Chalk Labs
Need help deploying hafez-decompose?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/engmahmoudhafez-hafez-decompose
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: sales
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/hafez-decompose
What's inside
- Skill name
hafez-decompose- Description
- Decompose an active project slice into bounded AI work units with explicit ownership, risk, parallelism, file scopes, verification, and worker tiers so a strong lead model can delegate safely to helper models.
- License
- MIT
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Hafez Decompose Act as the lead planner before implementation when an active slice contains more than one independently verifiable concern. Read the active slice, current Git state, architecture policy, serialized paths, gates, and relevant contracts. Produce a small execution graph rather than a generic checklist. Persist the result directly into the active slice's `workUnits` array. Use structured objects, not prose strings. For each work unit record: - id in `WU-01` form and objective; - dependency ids; - risk: low, medium, high; - worker tier: scout, worker, specialist, or lead; - access: read-only or write-worktree; - whether it is parallel-safe; - allowed paths; - required verification commands; - acceptance criteria owned by the unit; - integration notes for shared contracts/files; - initial status: `planned`. Routing rules: - Use scouts for repository research, impact analysis, test discovery, and contract comparison. - Use workers for repetitive, local, low-risk implementation with clear tests. - Use specialists for security-sensitive auth, migrations, concurrency, payment, performance, complex framework behavior, or repeated worker failures. - Keep product decisions, cross-cutting architecture, conflict resolution, shared serialized files, final review, and acceptance with the lead. - Never give two writers overlapping paths. - Treat project `serializedPaths`, lockfiles, root route registries, generated shared contracts, and migration ordering as serialized unless repository evidence proves otherwise. - Parallelize read-only scouts freely when useful. - Prefer the smallest unit that can be independently reviewed and verified; do not fragment trivial edits into delegation overhead. After decomposition, run `hafez dispatch-plan` to validate dependencies and scheduling, then `hafez dispatch --execute` to start the currently ready helper units. Every write result returns through `hafez-review`; successful scout results and verified writer integrations advance their work-unit status automatically. Mark lead-owned units with `hafez work-unit-status <WU-ID> --status completed` when their acceptance criteria are satisfied. Do not ask the project owner to choose worker allocation, file ownership, test strategy, or other technical decomposition details that the lead can determine from repository evidence.
From EngMahmoudHafez/hafez-development-system, MIT.
More from EngMahmoudHafez/hafez-development-system
- 0.567score
hafez-delegate
EngMahmoudHafez
Delegate bounded project work across Codex, Claude Code, Kimi Code, Antigravity, Zed, or compatible providers using structured task packets, isolated write…
SkillAFreshness: AClaude Code +9 - 0.567score
hafez-workspace
EngMahmoudHafez
Model and inspect a software product spanning multiple repositories using explicit members and contract relationships, without inferring architecture from…
SkillAFreshness: AClaude Code +9 - 0.567score
hafez
EngMahmoudHafez
Route a software project from discovery through delivery, or recover and continue a partially built project using Hafez state, evidence, slices, verification…
SkillAFreshness: AClaude Code +9 - 0.565score
hafez-autopilot
EngMahmoudHafez
Run a project continuously from its current state to the next verified milestone, automatically adopting safe Hafez metadata, fixing failures, delegating…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-get-started
EngMahmoudHafez
Set up Hafez safely for an unfamiliar project or multi-repository workspace, explain the available installation modes, and select the first evidence-based…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-handoff
EngMahmoudHafez
Create a durable project handoff when work pauses, changes owner, becomes blocked, or reaches a verified release checkpoint.
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-inspect
EngMahmoudHafez
Inspect an unfamiliar or partially built repository, infer its stack and current project focus from evidence, and recommend the next safe action without…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-laravel
EngMahmoudHafez
Apply evidence-based Laravel API architecture and vertical-slice delivery inside a Hafez-managed project, for either greenfield work or gradual adoption of an…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-nuxt-vue
EngMahmoudHafez
Build or adopt Nuxt and Vue applications in Hafez vertical slices with generated API contracts, mock-to-real adapters, explicit session states, RTL/i18n…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-plan-slice
EngMahmoudHafez
Plan a vertical project slice with business rules, acceptance criteria, dependencies, bounded work units, and verification before implementation begins.
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-security
EngMahmoudHafez
Perform evidence-based application security review and safe remediation for authentication, authorization, input handling, secrets, uploads, dependencies…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-verify
EngMahmoudHafez
Run the project-defined quality gates, record durable evidence, and determine readiness without treating skipped or unavailable checks as success.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 7, 2026 (25 days ago)
- Last release
- Oct 6, 2026 (26 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from EngMahmoudHafez
- 0.567score
hafez-delegate
EngMahmoudHafez
Delegate bounded project work across Codex, Claude Code, Kimi Code, Antigravity, Zed, or compatible providers using structured task packets, isolated write…
SkillAFreshness: AClaude Code +9 - 0.567score
hafez-workspace
EngMahmoudHafez
Model and inspect a software product spanning multiple repositories using explicit members and contract relationships, without inferring architecture from…
SkillAFreshness: AClaude Code +9 - 0.567score
hafez
EngMahmoudHafez
Route a software project from discovery through delivery, or recover and continue a partially built project using Hafez state, evidence, slices, verification…
SkillAFreshness: AClaude Code +9 - 0.565score
hafez-autopilot
EngMahmoudHafez
Run a project continuously from its current state to the next verified milestone, automatically adopting safe Hafez metadata, fixing failures, delegating…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-debug
EngMahmoudHafez
Diagnose and repair reproducible project failures continuously using evidence-first debugging, regression tests, bounded delegation, and repeated verification…
SkillAFreshness: AClaude Code +9 - 0.561score
hafez-database
EngMahmoudHafez
Review and evolve relational database schemas, migrations, indexes, queries, data integrity, and high-volume data changes safely.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get hafez-decompose running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
hafez-decompose skill. Agent Mart. https://agentmart.dev/skills/engmahmoudhafez-hafez-decompose (last updated 2026-10-24)