Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
.claude/skills/hoangnguyen0403-implement-feature/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -3% | 0% |
> !IMPORTANT] > Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.
When the user asks to perform this workflow, execute the following steps:
Goal: Build an approved feature through TDD slices and route completed work to verification.
docs/prd/ and docs/srs/ for a matching [slug]; if absent, use the newest matching artifact.REQ-*, AC-*, trace, or required SRS/test lanes are missing, stop and route to plan-feature, design-solution, or implementation-readiness.snc_tier/model_tier from handoff (score per common-task-complexity-routing if absent); high adds specialist-architecture-guard and specialist-security-reviewer before verify-work.npm ci/pnpm i/yarn, flutter pub get, ./gradlew dependencies, or pip install -e . from the lockfile); isolated worktrees lack ignored toolchains.verification_infra_failed with the exact command/error; never claim tests passed or silently skip verification.docs/srs/srs-task-list.md with small vertical slices.REQ-* and AC-* for each slice; do not invent scope from code inspection.docs/srs/srs-task-list.md or docs/prd/prd-plan-[slug].md.docs/prd/prd-[slug].md and docs/srs/srs-[slug].md before closing the slice.docs/srs/srs-walkthrough.md.verify-work.REQ-*/AC-* trace and required SRS/test lanes.slug, operator_profile (carried, not re-inferred), snc_tier, model_tier, completed slices, tests run, changed contracts, delegation packets, outcome report, next workflow.md# Implementation Handoff: [Name] ## Completed Slices ## Tests Run ## Changed Contracts ## Requirement Trace Updates ## Evidence ## Known Risks ## Delegation Packets ## Outcome Report feature_status: partially_implemented | implemented | blocked requirement_trace: BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* -> evidence completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: verify-work | plan-feature | design-solution ## Next Workflow verify-work ## Cost Report Call `get_session_cost(workflow="implement-feature")` before final handoff.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 11,548 | 5,370 | -53% | 1 | 1 | 0% | 1,706 | 1,859 | +9% | 0 | 0 | — |
case-13 | pass→pass | 10,192 | 4,514 | -56% | 1 | 1 | 0% | 1,416 | 1,768 | +25% | 0 | 0 | — |
case-01 | fail→fail | 27,177 | 14,720 | -46% | 1 | 1 | 0% | 5,915 | 1,413 | -76% | 0 | 0 | — |
case-02 | fail→fail | 5,154 | 10,027 | +95% | 1 | 1 | 0% | 261 | 1,453 | +457% | 0 | 0 | — |
case-03 | fail→fail | 4,656 | 34,357 | +638% | 1 | 1 | 0% | 182 | 1,418 | +679% | 0 | 0 | — |
case-04 | pass→fail | 16,347 | 5,831 | -64% | 1 | 1 | 0% | 2,538 | 1,452 | -43% | 0 | 0 | — |
case-05 | pass→fail | 5,593 | 4,466 | -20% | 1 | 1 | 0% | 813 | 1,293 | +59% | 0 | 0 | — |
case-06 | pass→fail | 26,291 | 5,089 | -81% | 1 | 1 | 0% | 4,332 | 1,396 | -68% | 0 | 0 | — |
case-14 | fail→pass | 12,896 | 4,204 | -67% | 1 | 1 | 0% | 1,923 | 1,725 | -10% | 0 | 0 | — |
case-07 | pass→pass | 7,277 | 2,853 | -61% | 1 | 1 | 0% | 1,015 | 1,575 | +55% | 0 | 0 | — |
case-08 | fail→pass | 12,398 | 4,834 | -61% | 1 | 1 | 0% | 1,791 | 1,978 | +10% | 0 | 0 | — |
case-09 | fail→fail | 9,229 | 7,155 | -22% | 1 | 1 | 0% | 1,496 | 1,529 | +2% | 0 | 0 | — |
case-10 | fail→pass | 10,140 | 5,541 | -45% | 1 | 1 | 0% | 1,564 | 2,005 | +28% | 0 | 0 | — |
case-11 | fail→pass | 13,599 | 3,554 | -74% | 1 | 1 | 0% | 2,112 | 1,644 | -22% | 0 | 0 | — |
case-15 | fail→pass | 12,901 | 4,817 | -63% | 1 | 1 | 0% | 1,900 | 1,847 | -3% | 0 | 0 | — |
case-16 | fail→pass | 10,860 | 3,003 | -72% | 1 | 1 | 0% | 1,536 | 1,593 | +4% | 0 | 0 | — |
case-17 | fail→pass | 14,758 | 4,664 | -68% | 1 | 1 | 0% | 2,433 | 1,914 | -21% | 0 | 0 | — |
case-18 | fail→pass | 7,733 | 5,528 | -29% | 1 | 1 | 0% | 1,195 | 2,002 | +68% | 0 | 0 | — |
case-19 | fail→pass | 17,082 | 3,907 | -77% | 1 | 1 | 0% | 2,734 | 1,664 | -39% | 0 | 0 | — |
case-20 | pass→fail | 10,593 | 1,972 | -81% | 1 | 1 | 0% | 1,730 | 1,416 | -18% | 0 | 0 | — |
case-21 | pass→pass | 9,984 | 3,646 | -63% | 1 | 1 | 0% | 1,438 | 1,617 | +12% | 0 | 0 | — |
case-22 | fail→pass | 10,663 | 4,138 | -61% | 1 | 1 | 0% | 1,540 | 1,699 | +10% | 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, and 15 counted toward the lift figure. The other 7 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +27 percentage points is the difference between those two pass rates over the 15 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v2, not the version currently listed.
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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/2/2026 | +18% |
Other measured skills in the registry, with their headline benchmark lift.