Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive understanding of the spec-kit methodology. Constitution-driven feature development with specify, plan, tasks, and implement phases.
.claude/skills/tzachbon-speckit-workflow/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 69% | 0% |
The SpecKit methodology is a constitution-driven approach to feature development. It ensures consistency across features by grounding all decisions in project principles.
Constitution First: Every feature is designed against the project's constitution - a living document of principles, constraints, and standards.
Governance Over Convention: Rather than implicit patterns, SpecKit makes governance explicit through:
text.specify/ ├── memory/ │ └── constitution.md # Project principles and standards ├── .current-feature # Active feature pointer ├── templates/ # Artifact templates │ ├── spec-template.md │ ├── plan-template.md │ ├── tasks-template.md │ └── checklist-template.md └── specs/ └── <id>-<name>/ # Feature directories ├── .speckit-state.json ├── .progress.md ├── .coordinator-prompt.md ├── spec.md # Feature specification ├── plan.md # Technical design ├── tasks.md # Implementation tasks ├── research.md # Research findings (optional) ├── data-model.md # Entity definitions (optional) ├── contracts/ # API contracts (optional) └── checklists/ # Quality checklists
Features use auto-incremented 3-digit IDs:
001-user-auth002-payment-gateway003-notification-systemBenefits:
/speckit:constitution)Establish or update project-wide principles.
Inputs: Project context, team preferences Outputs: .specify/memory/constitution.md
Constitution sections:
/speckit:specify)Define the feature specification against constitution.
Inputs: Feature goal, constitution reference Outputs: spec.md
Specification contains:
/speckit:clarify) - OptionalResolve ambiguities through structured Q&A.
Inputs: spec.md with ambiguities Outputs: Updated spec.md with clarifications
Rules:
/speckit:plan)Generate technical design from specification.
Inputs: spec.md, constitution, codebase context Outputs: plan.md, optionally data-model.md, contracts/
Plan contains:
/speckit:tasks)Break plan into dependency-ordered implementation tasks.
Inputs: plan.md, spec.md Outputs: tasks.md
Task format:
markdown- [ ] T001 [P] [US1] Task description `path/to/file.ts`
Components:
T001: Sequential task ID[P]: Parallel marker (optional)[US1]: User story reference (optional)Task phases:
/speckit:implement)Execute tasks via Ralph Wiggum loop.
Inputs: tasks.md, state file Outputs: Code changes, commits, updated progress
Execution model:
.speckit-state.json)json{ "featureId": "001", "name": "user-auth", "basePath": ".specify/specs/001-user-auth", "phase": "execution", "taskIndex": 0, "totalTasks": 15, "taskIteration": 1, "maxTaskIterations": 5, "globalIteration": 1, "maxGlobalIterations": 100, "awaitingApproval": false }
.progress.md)Tracks:
/speckit:checklist)Domain-specific quality checklists:
Checklists are "unit tests for requirements" - verifiable criteria before implementation.
/speckit:analyze)Cross-artifact consistency analysis:
| Command | Purpose | Phase | |---------|---------|-------| | /speckit:start <name> | Create or resume feature | Entry | | /speckit:constitution | Create/update project principles | 1 | | /speckit:specify | Define feature specification | 2 | | /speckit:clarify | Resolve spec ambiguities | 3 | | /speckit:plan | Generate technical design | 4 | | /speckit:tasks | Break plan into tasks | 5 | | /speckit:implement | Execute tasks | 6 | | /speckit:analyze | Check consistency | Any | | /speckit:checklist | Generate quality checklist | Any | | /speckit:status | Show current state | Any | | /speckit:switch <id> | Change active feature | Any | | /speckit:cancel | Stop execution, cleanup | Any |
| Agent | Purpose | Used By | |-------|---------|---------| | constitution-architect | Create/update constitution | constitution | | spec-analyst | Generate specifications | specify | | plan-architect | Technical design | plan | | task-planner | Task breakdown | tasks | | spec-executor | Execute single task | implement | | qa-engineer | Verification tasks | implement |
All phases reference the constitution:
Constitution markers in artifacts:
[C§3.1]: References constitution section 3.1[MUST]: Required by constitution[SHOULD]: Recommended by constitution[MAY]: Optional per constitution| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 11,482 | 2,907 | -75% | 1 | 1 | 0% | 1,756 | 2,250 | +28% | 0 | 0 | — |
case-01 | fail→fail | 16,654 | 14,315 | -14% | 1 | 1 | 0% | 3,421 | 4,466 | +31% | 0 | 0 | — |
case-03 | fail→pass | 15,302 | 7,351 | -52% | 1 | 1 | 0% | 2,579 | 3,190 | +24% | 0 | 0 | — |
case-04 | fail→pass | 9,132 | 3,946 | -57% | 1 | 1 | 0% | 1,803 | 2,537 | +41% | 0 | 0 | — |
case-05 | fail→pass | 15,819 | 11,394 | -28% | 1 | 1 | 0% | 2,306 | 3,489 | +51% | 0 | 0 | — |
case-06 | fail→pass | 14,303 | 4,796 | -66% | 1 | 1 | 0% | 2,264 | 2,648 | +17% | 0 | 0 | — |
case-20 | pass→pass | 12,761 | 10,472 | -18% | 1 | 1 | 0% | 1,958 | 3,309 | +69% | 0 | 0 | — |
case-07 | pass→pass | 12,293 | 6,495 | -47% | 1 | 1 | 0% | 2,023 | 2,840 | +40% | 0 | 0 | — |
case-08 | fail→pass | 9,879 | 4,777 | -52% | 1 | 1 | 0% | 1,585 | 2,677 | +69% | 0 | 0 | — |
case-09 | fail→pass | 6,040 | 1,669 | -72% | 1 | 1 | 0% | 909 | 2,062 | +127% | 0 | 0 | — |
case-10 | fail→pass | 9,826 | 2,656 | -73% | 1 | 1 | 0% | 1,433 | 2,235 | +56% | 0 | 0 | — |
case-11 | fail→pass | 5,256 | 2,286 | -57% | 1 | 1 | 0% | 800 | 2,185 | +173% | 0 | 0 | — |
case-12 | pass→pass | 8,075 | 2,147 | -73% | 1 | 1 | 0% | 1,168 | 2,149 | +84% | 0 | 0 | — |
case-13 | fail→pass | 9,562 | 2,172 | -77% | 1 | 1 | 0% | 1,331 | 2,192 | +65% | 0 | 0 | — |
case-14 | fail→pass | 11,742 | 5,256 | -55% | 1 | 1 | 0% | 1,807 | 2,722 | +51% | 0 | 0 | — |
case-15 | fail→pass | 9,880 | 2,391 | -76% | 1 | 1 | 0% | 1,518 | 2,202 | +45% | 0 | 0 | — |
case-16 | pass→pass | 13,950 | 3,841 | -72% | 1 | 1 | 0% | 1,951 | 2,429 | +25% | 0 | 0 | — |
case-17 | fail→pass | 15,831 | 8,862 | -44% | 1 | 1 | 0% | 2,307 | 3,205 | +39% | 0 | 0 | — |
case-18 | fail→pass | 6,810 | 1,483 | -78% | 1 | 1 | 0% | 1,064 | 2,013 | +89% | 0 | 0 | — |
case-19 | fail→pass | 11,943 | 2,804 | -77% | 1 | 1 | 0% | 1,920 | 2,303 | +20% | 0 | 0 | — |
case-21 | pass→pass | 18,693 | 13,004 | -30% | 1 | 1 | 0% | 3,201 | 4,188 | +31% | 0 | 0 | — |
case-22 | pass→pass | 15,194 | 12,473 | -18% | 1 | 1 | 0% | 2,719 | 4,179 | +54% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +64 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.