devflow
End-to-end agent development process. Use when coordinating work, dispatching agents, or reviewing PRs.
What this skill does
# DEVFLOW: Agent Development
5-phase workflow for coordinated multi-agent development.
## ⚠️ MANDATORY: 100% Issue/Task Coverage
**Every phase must verify that 100% of original issue/task requirements are being addressed.**
- Phase 1: Extract ALL requirements from original issue
- Phase 2: Dispatch agents with complete requirement lists
- Phase 3: Review must verify 100% coverage before quality check
- Phase 5: Cannot merge until 100% of original requirements implemented
**Incomplete implementations = SEND BACK, do not proceed.**
## Phase 1: Oracle Assessment
- Assess codebase state with Oracle
- Identify completed work, remaining work, dependencies
- **Extract ALL requirements from original issue/task** (`gh issue view <number>`)
- Break down into parallelizable tasks ensuring ALL requirements are covered
## Phase 2: Parallel Implementation
Dispatch Docker agents:
- Clone repo, format locally (`cargo +nightly fmt`)
- Branch as `feat/name` or `fix/name`
- Open PR to correct base branch with **`Closes #X` in body**
- Never push to existing branches
**PR MUST include issue links:**
- `Closes #X` or `Fixes #X` for issues being addressed
- "Related Issues" section in PR body
- Verify: `gh pr view --json closingIssuesReferences`
## Phase 3: Ultra-Critical Review
After CI passes, run 6-pass review:
| Pass | Focus |
|------|-------|
| **0.5** | **100% issue/task coverage verification (MANDATORY FIRST)** |
| 1 | Runtime/compile failures |
| 2 | Patterns, imports, dead code |
| 3 | Abstractions, hard-coded values |
| 4 | Environment compatibility |
| 5 | Verification commands |
| 6 | Context synthesis |
**CRITICAL**: Pass 0.5 (issue coverage) MUST pass before proceeding. If coverage < 100%, send agent back immediately.
### Review Escalation
1. **Escalate to coordinator first** — Architecture/tradeoff questions
2. **Coordinator applies good judgment** — Based on codebase patterns
3. **Escalate to human when needed** — Significant risk or uncertainty
### Review Timing
- **Pre-PR review**: After agent work, before PR creation
- **Post-PR review**: After PR creation, before merge
## Phase 4: Human Approval
**Pause for:** PR approval, complex decisions requiring human judgment.
**Continue through:** workstream setup, agent dispatch, CI fixes, review feedback.
## Phase 4.5: FINAL COVERAGE GATE
**MANDATORY**: Before any merge, perform LINE-BY-LINE requirement verification.
```bash
# Extract ALL requirements from issue
gh issue view <number> --json body --jq '.body' | grep -E "^\- \["
gh issue view <number>
```
**Create verification table:**
```markdown
| Requirement | Status | Evidence |
|-------------|--------|----------|
| [from issue] | ✅ | `file:line` |
| [from issue] | ❌ MISSING | Not in PR |
| [from issue] | ⚠️ PARTIAL | [what's missing] |
**Honest Assessment**: X% (Y of Z requirements)
```
| Coverage | Action |
|----------|--------|
| **100%** | ✅ Proceed to merge |
| **< 100%** | ❌ Return to Phase 2 with line-by-line gap list |
## Phase 5: Merge & Continue
**Before merge, verify issue linking:**
```bash
gh pr view <NUMBER> --json closingIssuesReferences
# Must show linked issues - if empty, send back to fix
```
Merge PRs in dependency order. **Only after Final Coverage Gate passes AND issues are linked.** Issues auto-close on merge.
---
## Mermaid Diagrams in Reviews and PRs
**Reviews and PRs SHOULD include Mermaid diagrams when changes involve flows, states, or architecture.**
| Change Type | Diagram |
|-------------|---------|
| Flow change | `flowchart` before/after |
| API modification | `sequenceDiagram` |
| State handling | `stateDiagram-v2` |
| Architecture change | `flowchart` with subgraphs |
Example in review:
````markdown
### New Token Flow
```mermaid
sequenceDiagram
Client->>Server: Request (expired token)
Server-->>Client: 401 + refresh
Client->>Server: New request
```
````
---
## Anti-Patterns
| Wrong | Right |
|-------|-------|
| **Merge with incomplete coverage** | **100% of issue requirements implemented first** |
| **PR without issue links** | **Every PR has `Closes #X` for related issues** |
| Push to branch | Feature branch + PR |
| Checkbox review | 6-pass analysis (starting with coverage check) |
| Coordinator implements | Dispatch agents |
| Pause every step | Pause for PR decisions |
| Skip CI | Wait for CI |
| **"Core requirements done"** | **ALL requirements done, no exceptions** |
| **Merge then close issue manually** | **Use `Closes #X` for auto-close on merge** |
| **Text-only complex changes** | **Mermaid diagrams for flows/states** |
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.