Project Planner
adrianpuiu/claude-skills-marketplace
Comprehensive project planning and documentation generator for software projects.
Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v07-epic-scoping --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prd-v07-epic-scoping .claude/skills/prd-v07-epic-scoping && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prd-v07-epic-scoping" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v07-epic-scoping into .claude/skills/prd-v07-epic-scoping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v07-epic-scoping", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v07-epic-scopingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v07-epic-scoping --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/prd-v07-epic-scoping .agents/skills/prd-v07-epic-scoping && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prd-v07-epic-scoping" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v07-epic-scoping into .agents/skills/prd-v07-epic-scoping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v07-epic-scoping", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v07-epic-scoping --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/prd-v07-epic-scoping .cursor/skills/prd-v07-epic-scoping && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prd-v07-epic-scoping" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v07-epic-scoping into .cursor/skills/prd-v07-epic-scoping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v07-epic-scoping", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mattgierhart/PRD-driven-context-engineering.git --path .claude/skills/prd-v07-epic-scoping--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v07-epic-scoping --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/prd-v07-epic-scoping .gemini/skills/prd-v07-epic-scoping && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prd-v07-epic-scoping" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v07-epic-scoping into .gemini/skills/prd-v07-epic-scoping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v07-epic-scoping", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v07-epic-scopingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/prd-v07-epic-scoping .github/skills/prd-v07-epic-scoping && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prd-v07-epic-scoping" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v07-epic-scoping into .github/skills/prd-v07-epic-scoping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v07-epic-scoping", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v07-epic-scoping --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/prd-v07-epic-scoping .opencode/skills/prd-v07-epic-scoping && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prd-v07-epic-scoping" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v07-epic-scoping into .opencode/skills/prd-v07-epic-scoping/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v07-epic-scoping", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
prd-v07-epic-scopingTransform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution.
Prd V07 Epic Scoping is an agent skill from mattgierhart/PRD-driven-context-engineering. Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution. Triggers on requests to create epics, scope work, break down implementation, or when user asks "create epics", "scope work", "break down work", "context window sizing", "what to build first?", "implementation planning", "epic breakdown". Consumes API-, DBT-, FEA-, ARC-. Outputs EPIC- entries with objectives, ID references, dependencies, and context windows. Feeds v0.7 Test Planning.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files and assets (for example `assets/epic.md`, `references/dependency-mapping.md` and `references/examples.md`).
It sits in Product & Project Management, covering Context engineering, PRD writing and User stories. It works with dbt. The repository describes itself as: PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD… The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGlobGrepBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
supabasegitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use supabase and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Prd V07 Epic Scoping loads about 4.3k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 129 tokens; SKILL.md has 1,084 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Write, Edit, Glob, Grep, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 1,084 words, ~4,296 tokens.
.claude/skills/prd-v07-epic-scoping/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Position in workflow: v0.6 Technical Specification → v0.7 Epic Scoping → v0.7 Test Planning
This skill requires prior work from v0.6 Technical Specification:
This skill assumes v0.6 Technical Specification is complete with API-/DBT- entries providing implementation contracts.
This skill creates/updates:
All EPIC- entries are work package specifications, not confidence-based. They are:
Example EPIC- entry (Auth Infrastructure):
EPIC-01: User Authentication
State: Planned
Lifecycle: v0.7 Build Execution
Branch: epic/EPIC-01-auth
## 0. Context Capsule
### Resource Envelope
| Dimension | Target | Notes |
|-----------|--------|-------|
| Pre-load Context | ~40k tokens | Auth SoT + API-001–005 specs + DBT-010/011 schema |
| Working Room | ~160k tokens | Plenty of space for implementation |
| Session Goal | Checkpoint C1 | Database schema complete |
### Dependencies
| Type | Items | Status |
|------|-------|--------|
| Requires | None | First EPIC — foundation |
| External | Supabase project created | Ready |
| Enables | EPIC-02 (reports), EPIC-03 (data sources) | Blocked until auth completes |
### Pre-load Checklist
- [ ] SoT/SoT.BUSINESS_RULES.md — IDs: BR-001, BR-002 (auth rules)
- [ ] SoT/SoT.API_CONTRACTS.md — IDs: API-001–005 (auth endpoints)
- [ ] SoT/SoT.TECHNICAL_DECISIONS.md — IDs: TECH-003 (Clerk), ARC-003 (JWT strategy)
## 2. Objective & Scope
Goal: Enable users to authenticate with email/password, manage sessions, and maintain security.
Deliverables:
- [ ] User registration with email/password (API-001)
- [ ] Login/logout functionality (API-002, API-003)
- [ ] Session management with refresh tokens (API-004)
- [ ] Password reset flow (API-005)
- [ ] Users and sessions schema (DBT-010, DBT-011)
Out of Scope: Social auth (EPIC-02), team invites (EPIC-05), admin user management (EPIC-07)
## 3. Context & IDs
| Type | IDs |
|------|-----|
| Business Rules | BR-001 (email uniqueness), BR-002 (password requirements), BR-010 (auth workflow) |
| User Journeys | UJ-000 (onboarding), UJ-010 (login) |
| APIs | API-001 to API-005 |
| Data Models | DBT-010 (users), DBT-011 (sessions) |
| Architecture | ARC-003 (JWT strategy), TECH-003 (Clerk) |
| Features | FEA-010 (signup), FEA-011 (login) — both in MVP-SCOPE |
| Tests | TEST-001 to TEST-015 (auth test suite) |
## 4. Execution Plan (5 Phases)
[Phase structure from skill as is]
Related IDs: TECH-003, ARC-003, FEA-010/011, API-001–005, DBT-010/011, BR-001/002/010An EPIC is not a "big user story." It is a cognitive boundary—a scope of work that fits in working memory (human or AI). The goal is to load exactly what's needed to complete a focused task without distraction.
The question is not "How long will this take?" but "Can an agent complete this without needing more context than fits in a session?"
| Size | Characteristics | Action |
|---|---|---|
| Right-sized | 3-5 API endpoints, 2-4 DBT tables, 1-2 UJ flows | Good fit ✓ |
| Too big | >10 APIs, >5 tables, multiple unrelated features | Split by domain |
| Too small | Single endpoint, no meaningful deliverable | Merge with related |
Rule of thumb: If you can't describe the EPIC's goal in one sentence, it's too big.
EPICs are context capsules — work units sized for AI agent handoffs.
| Dimension | Target | Rationale |
|---|---|---|
| Pre-load context | <100k tokens | SoT files + EPIC + code references |
| Working room | >100k tokens | Space for tool outputs, debugging, iteration |
| Session goal | 1 checkpoint | Clear "done" state per session |
Context Monitoring: Don't estimate upfront — monitor during work. If context exceeds 100k tokens mid-session, pause and checkpoint immediately.
Splitting Signal: If you need to load >5 SoT files or >10 code files to understand the EPIC, it's probably too big.
Simplicity Signal: Resist creating more EPICs "just in case." Each EPIC adds coordination overhead (context capsule, session state, branch management, dependency tracking). If the MVP has 12 APIs and 6 tables, 3-5 EPICs is almost always sufficient. The overhead of an unnecessary EPIC is higher than a slightly larger EPIC that stays within context budget.
Each EPIC gets its own branch. This creates:
Naming: epic/EPIC-{NUMBER}-{slug}
Examples:
epic/EPIC-01-auth-endpointsepic/EPIC-02-user-dashboardepic/EPIC-03-payment-integrationWorkflow:
git checkout -b epic/EPIC-{NUMBER}-{slug}Inventory implementation items from API-, DBT-, FEA-, ARC-
Identify natural boundaries
Size each potential EPIC against context window capacity
Sequence EPICs by dependencies
Create EPIC- entries with full ID references
Validate: Can an agent complete this EPIC without needing more context than fits in a session?
| Order | Priority | Rationale | Examples |
|---|---|---|---|
| 1 | Infrastructure EPICs | Everything depends on these | Auth, DB setup, project scaffold |
| 2 | Core data model EPICs | Foundation for features | User, Workspace, base entities |
| 3 | Critical path EPICs | Journeys that drive KPIs | UJ- that affects KPI-001 |
| 4 | Supporting feature EPICs | Secondary features | Settings, admin, nice-to-haves |
EPIC-XXX: [Epic Name]
State: [Planned | In Progress | Testing | Complete]
Lifecycle: v0.7 Build Execution
Branch: epic/EPIC-XXX-[slug]
## 0. Context Capsule
### Resource Envelope
| Dimension | Target | Notes |
|-----------|--------|-------|
| Pre-load Context | ~[N]k tokens | SoT files + EPIC + code |
| Working Room | ~[200-N]k tokens | Space for work |
| Session Goal | [Checkpoint target] | What "done" looks like |
### Dependencies
| Type | Items | Status |
|------|-------|--------|
| Requires | EPIC-YYY | Complete/Pending |
| External | [Setup needed] | Ready/Blocked |
| Enables | EPIC-ZZZ | Blocked until this completes |
### Pre-load Checklist
- [ ] SoT/SoT.[X].md — IDs: [key IDs]
- [ ] SoT/SoT.[Y].md — IDs: [key IDs]
## 1. Session State (The "Brain Dump")
### Current State
- **Last Action**: [What was just completed — reference IDs]
- **Stopping Point**: [File/line or test failure]
- **Next Steps**: [Exact instructions for next session]
- **Blockers**: [Any blockers — or "None"]
- **Decisions Made**: [Key decisions with rationale]
### Resume Instructions
[Exactly what the next session should do — or "N/A - EPIC Complete"]
## 2. Objective & Scope
Goal: [One sentence describing what this EPIC achieves]
Deliverables:
- [ ] [Specific deliverable A]
- [ ] [Specific deliverable B]
- [ ] [Specific deliverable C]
Out of Scope: [What we are NOT doing in this EPIC]
## 3. Context & IDs
| Type | IDs |
|------|-----|
| Business Rules | BR-XXX, BR-YYY |
| User Journeys | UJ-XXX, UJ-YYY |
| APIs | API-XXX to API-ZZZ |
| Data Models | DBT-XXX, DBT-YYY |
| Architecture | ARC-XXX |
| Features | FEA-XXX, FEA-YYY |
| Tests | TEST-XXX to TEST-ZZZ |
## 4. Execution Plan (The 5 Phases)
### Phase A: Plan
- [ ] Context loaded
- [ ] Dependencies verified
- [ ] Strategy defined
- [ ] Branch created
**Checkpoint A**: Planning complete, branch exists.
### Phase B: Design
- [ ] Specs updated
- [ ] Architecture documented
- [ ] TEST- entries created
**Checkpoint B**: Specs drafted, tests defined.
### Phase C: Build (Context Windows)
Window 1: [Focus Area]
- [ ] Task A
- [ ] Task B
- [ ] Verification: [How to confirm complete]
**Checkpoint C1**: [What exists when done]
Window 2: [Focus Area]
- [ ] Task C
- [ ] Task D
**Checkpoint C2**: [What exists when done]
### Phase D: Validate
- [ ] All TEST- entries pass
- [ ] Manual verification of UJ-
- [ ] Code has @implements tags
- [ ] SoT matches implementation
**Checkpoint D**: Tests green, verification complete.
### Phase E: Finish
- [ ] Temp cleanup
- [ ] SoT finalized
- [ ] Learning capture
- [ ] Resume Instructions = "N/A - EPIC Complete"
- [ ] PR ready
**Checkpoint E**: EPIC complete.
## 5. Acceptance Criteria
- [ ] All deliverables done
- [ ] All TEST- entries pass
- [ ] Resume Instructions = "N/A - EPIC Complete"
- [ ] No orphan ID references
- [ ] Branch merged or PR approvedExample EPIC- entry:
EPIC-01: User Authentication
State: Planned
Lifecycle: v0.7 Build Execution
Branch: epic/EPIC-01-auth
## 0. Context Capsule
### Resource Envelope
| Dimension | Target | Notes |
|-----------|--------|-------|
| Pre-load Context | ~40k tokens | Auth SoT + API specs + schema |
| Working Room | ~160k tokens | Plenty of space |
| Session Goal | Checkpoint C1 | Database schema complete |
### Dependencies
| Type | Items | Status |
|------|-------|--------|
| Requires | None | First EPIC |
| External | Supabase project | Ready |
| Enables | EPIC-02, EPIC-03 | Blocked until this completes |
### Pre-load Checklist
- [ ] SoT/SoT.BUSINESS_RULES.md — IDs: BR-001, BR-002
- [ ] SoT/SoT.API_CONTRACTS.md — IDs: API-001 to API-005
- [ ] SoT/SoT.TECHNICAL_DECISIONS.md — IDs: TECH-003, ARC-003
## 1. Session State (The "Brain Dump")
### Current State
- **Last Action**: N/A (not started)
- **Stopping Point**: N/A
- **Next Steps**:
1. Create branch epic/EPIC-01-auth
2. Begin with Phase A: Plan
3. Load context from pre-load checklist
- **Blockers**: None
- **Decisions Made**: Using Supabase Auth per TECH-003
### Resume Instructions
> Start fresh: create branch and load context per pre-load checklist.
## 2. Objective & Scope
Goal: Enable users to sign up, log in, and manage their sessions.
Deliverables:
- [ ] User registration with email/password
- [ ] Login/logout functionality
- [ ] Session management with refresh tokens
- [ ] Password reset flow
Out of Scope: Social auth (EPIC-02), team invites (EPIC-05)
## 3. Context & IDs
| Type | IDs |
|------|-----|
| Business Rules | BR-001, BR-002 |
| User Journeys | UJ-000, UJ-010 |
| APIs | API-001 to API-005 |
| Data Models | DBT-010, DBT-011 |
| Architecture | ARC-003, TECH-003 |
| Features | FEA-010, FEA-011 |
| Tests | TEST-001 to TEST-015 |
## 4. Execution Plan
### Phase A: Plan
- [ ] Context loaded
- [ ] Dependencies verified (Supabase ready)
- [ ] Strategy: Database → API → UI
- [ ] Branch created: epic/EPIC-01-auth
**Checkpoint A**: Planning complete, branch exists.
### Phase C: Build
Window 1: Database Schema
- [ ] Create users table with RLS
- [ ] Create sessions table
- [ ] Set up Supabase Auth triggers
**Checkpoint C1**: Schema deployed, migrations tested.
Window 2: API Endpoints
- [ ] POST /auth/signup (API-001)
- [ ] POST /auth/login (API-002)
- [ ] POST /auth/logout (API-003)
- [ ] POST /auth/refresh (API-004)
- [ ] POST /auth/reset-password (API-005)
**Checkpoint C2**: All endpoints return correct responses.
Window 3: UI Integration
- [ ] Signup form (SCR-001)
- [ ] Login form (SCR-002)
- [ ] Password reset flow (SCR-003)
- [ ] Auth state management
**Checkpoint C3**: Full auth flow works E2E.
## 5. Acceptance Criteria
- [ ] All deliverables done
- [ ] TEST-001 to TEST-015 pass
- [ ] Resume Instructions = "N/A - EPIC Complete"
- [ ] UJ-000 and UJ-010 verified manually
- [ ] Branch mergedEach EPIC follows 5 phases:
| Phase | Purpose | Activities |
|---|---|---|
| A: Plan | Load context | Read EPIC, load referenced IDs, verify Session State |
| B: Design | Update SoT | Draft/refine ID entries in SoT/ before coding |
| C: Build | Implement | Work through Context Windows, test-first |
| D: Validate | Verify | Run tests, manual checks, traceability audit |
| E: Finish | Clean up | Update SoT, archive temp/, mark complete |
| Anti-Pattern | Signal | Fix |
|---|---|---|
| Epic explosion | 20+ EPICs for MVP | Consolidate; most MVPs need 3-7 |
| One mega-EPIC | Everything in one EPIC | Split by architectural boundary |
| No ID references | EPIC without BR-, API-, DBT- links | Every EPIC must reference SoT/ |
| Circular dependencies | EPIC-01 needs EPIC-02 needs EPIC-01 | Identify shared foundation, extract to EPIC-00 |
| Context overload | Agent can't hold full EPIC context | Split into smaller Context Windows |
| Missing sequencing | No build order defined | Establish explicit dependency chain |
| Vague objectives | "Build the backend" | Specific, measurable: "Implement API-001–005" |
| Silent scope assumptions | EPIC assigns items without explaining boundary rationale | Every ambiguous assignment must note "API-XXX placed here because [reason]; alternative was EPIC-YYY" |
Before proceeding to Test Planning:
EPIC- entries feed into:
| Consumer | What It Uses | Example |
|---|---|---|
| Test Planning | EPIC scope defines test boundaries | TEST- entries for EPIC-01 scope |
| Implementation Loop | EPIC is execution unit | Work happens inside EPIC context |
| Session Management | Session State section tracks progress | Resume from where we left off |
| Progress Tracking | EPIC state shows overall progress | 3/7 EPICs complete |
references/examples.mdassets/epic.mdreferences/dependency-mapping.md© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references, assets) in .claude/skills/prd-v07-epic-scoping of mattgierhart/PRD-driven-context-engineering.
Open the folder on GitHubat commit 30ed1b0
Prd V07 Epic Scoping next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prd V07 Epic Scoping this skillmattgierhart/PRD-driven-context-engineering | 180 | — | ~4.3k | Automated safety check: Notes | MIT | |
| Project Planneradrianpuiu/claude-skills-marketplace | 100 | 1 repos | ~6k | Automated safety check: Pass | None | |
| Feature ForgeJeffallan/claude-skills | 12k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Spec Driven Loopsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Spec Workflowhashgraph-online/awesome-codex-plugins | 1.3k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Ralph Tui Create Beadssubsy/ralph-tui | 2.5k | 1 repos | ~2.6k | Automated safety check: Pass | MIT |
adrianpuiu/claude-skills-marketplace
Comprehensive project planning and documentation generator for software projects.
Jeffallan/claude-skills
Runs a structured requirements interview to produce a feature specification with EARS requirements, acceptance criteria and an implementation checklist.
sickn33/agentic-awesome-skills
Freeze PRD, technical design, and acceptance criteria before medium-to-large Codex work; coordinate agents with explicit ownership, then judge delivery from diffs, tests, and evidence.
hashgraph-online/awesome-codex-plugins
This skill should be used when the user asks to "create a spec", "write requirements", "design a feature", "plan implementation", "use EARS notation", "create user stories", "break down tasks"…
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
mattgierhart/PRD-driven-context-engineering
Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py).
mattgierhart/PRD-driven-context-engineering
Extracts durable insights from temp/ files to SoT during EPIC Phase E.
mattgierhart/PRD-driven-context-engineering
Validates and registers new SoT IDs with cross-reference integrity.
mattgierhart/PRD-driven-context-engineering
Creates new Source of Truth (SoT) files when existing templates don't fit your needs.
mattgierhart/PRD-driven-context-engineering
Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark.
mattgierhart/PRD-driven-context-engineering
Transform validated pain points into articulated user value statements for PRD v0.1 Spark.
Works with
Transform v0.6 specifications into context-window-sized work packages (EPICs) during PRD v0.7 Build Execution. Prd V07 Epic Scoping is an agent skill from mattgierhart/PRD-driven-context-engineering.7 Build Execution.
Prd V07 Epic Scoping fits situations like: requests to create epics; break down implementation; user asks create epics; break down work.
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a claude-code`. Or copy the skill folder (.claude/skills/prd-v07-epic-scoping in mattgierhart/PRD-driven-context-engineering) into .claude/skills/prd-v07-epic-scoping in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a codex`. Or copy the skill folder (.claude/skills/prd-v07-epic-scoping in mattgierhart/PRD-driven-context-engineering) into .agents/skills/prd-v07-epic-scoping in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v07-epic-scoping -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-v07-epic-scoping, .gemini/skills/prd-v07-epic-scoping, .github/skills/prd-v07-epic-scoping and .opencode/skills/prd-v07-epic-scoping in your project.
Going by SKILL.md and its folder, Prd V07 Epic Scoping needs the command-line tools its instructions call (supabase and git). Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, Bash.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Prd V07 Epic Scoping is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Prd V07 Epic Scoping: Project Planner (adrianpuiu/claude-skills-marketplace, 100 stars), Feature Forge (Jeffallan/claude-skills, 12k stars), Spec Driven Loop (sickn33/agentic-awesome-skills, 47k stars) and Spec Workflow (hashgraph-online/awesome-codex-plugins, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mattgierhart (a GitHub user) maintains it in mattgierhart/PRD-driven-context-engineering, which has 180 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on August 31, 2026.
Source: mattgierhart/PRD-driven-context-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.