메뉴
[Planning] Use when calibrating estimates from actual code, diff, PR scope, and developer time.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/duc01226/EasyPlatform --skill estimate-actual명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
[Architecture] Use when designing solution architecture across backend, frontend, deployment, monitoring, testing, and code quality.
[Utilities] Use when you need to answer technical and architectural questions.
[Content] Use when you need to brainstorm as a PO/BA — structured ideation for problem-solving, new product creation, or feature enhancement.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | estimate-actual |
| description | [Planning] Use when calibrating estimates from actual code, diff, PR scope, and developer time. |
| disable-model-invocation | false |
| argument-hint | <plan-file> | --changes | --pr <number> |
Goal: Produce a 3-way estimation calibration report — pre_impl_estimate (from plan) vs true_estimate (from observed scope) vs actual_time (from git/user) — yielding two INDEPENDENT signals: developer execution variance and estimation model calibration variance.
Why two signals matter: They are confounded if not separated. If actual >> pre-impl, the bug could be (a) developer was slow, OR (b) the model under-estimated scope. Without computing TRUE from observed scope, you cannot tell which. Single-sample calibration has near-zero statistical power — the skill always reports this.
Workflow:
--changes / --pr <n>Key Rules:
| Mode | Trigger | What's read |
|---|---|---|
| Plan-file | <path/to/plan.md> | Plan frontmatter (pre-impl estimate) + git diff scoped to plan branch |
| Changes | --changes | git diff working tree + last commit timestamps |
| PR | --pr <n> | gh pr view <n> + gh pr diff <n> + PR open/merge times |
If multiple modes detected (e.g., plan file AND --changes), prefer plan-file (carries the original estimate); use changes for the diff source.
man_days_traditional, story_points, risk_margin_pct, risk_factors, blast_radius, estimate_reasoning if presentrisk_factors), flag in report — comparison is approximateRun (PowerShell or Bash via tool):
git diff --stat <base>..<head> — file count, lines added/removedgit diff --name-only <base>..<head> — file listgit log --format='%H %ai %s' <base>..<head> — commit timelineClassify changed files:
describe|it|Fact|Test\b)python .claude/scripts/code_graph trace <file> --direction both --json for changed entry-point filesApply each tier table (UI / backend / test / risk margin / risk factors) from the inline framework below to the OBSERVED scope. Output:
true_likely_days (single midpoint)true_min_days = likely × 0.9true_max_days = likely × (1 + risk_margin)true_estimate = '<min>-<max>d' rangeTry in order:
AskUserQuestion: "Git suggests N working days from first commit to merge. How much was actual coding time? (excludes meetings, code-review wait, context switches, vacations)"ALWAYS surface the gap between elapsed time and reported coding time — they are different signals.
scope_variance_pct = (true_likely - preimpl_likely) / preimpl_likely × 100
exec_variance_pct = (actual_time - true_likely) / true_likely × 100
Interpretation matrix:
| scope_var | exec_var | Verdict |
|---|---|---|
| ~0% (±15%) | ~0% (±15%) | Estimate matched scope; developer matched estimate. Healthy. |
| ~0% | >+25% | Model OK; developer slower than expected. Performance signal. |
| ~0% | <-25% | Model OK; developer faster than expected. Either skilled or scope simpler than apparent. |
| >+25% | ~0% | Model UNDER-estimated scope; developer matched the harder-than-predicted reality. Model signal — too optimistic. |
| <-25% | ~0% | Model OVER-estimated scope; actual work was simpler. Model signal — too pessimistic. |
| >+25% | >+25% | Both — scope was harder AND developer slower. Disambiguate over multiple samples. |
| <-25% | <-25% | Original estimate was way over; developer also fast. Likely simple task padded heavily. |
| Layer | Pre-impl tier (from plan) | Observed tier (from diff) | Delta |
|---|---|---|---|
| UI | e.g. "Compose components into NEW screen" | e.g. "Add control to existing screen" | -1 tier (~0.7d over) |
| Backend | e.g. "NEW command on existing aggregate" | e.g. "Small update existing handler" | -1 tier (~0.5d over) |
| Tests | e.g. "13 cases" | e.g. "5 cases" | -8 cases (~0.5d over) |
| Blast | e.g. "4 areas, 1 complex" | e.g. "2 areas, 0 complex" | lower regression risk |
| Risk factors | predicted list | applicable in retrospect | call out missing/unused |
Produce a markdown report with sections:
If user wants longitudinal tracking, append the calibration row to plans/_estimation-samples.csv:
date,plan,preimpl_min,preimpl_max,true_min,true_max,actual,scope_var_pct,exec_var_pct,risk_factors_predicted,risk_factors_applicable
After ≥5 rows, run pattern detection on the CSV: if scope_var_pct is consistently negative (model over-estimates), suggest tier adjustment; if consistently positive (under-estimates), suggest adding risk factors or widening tier.
The canonical framework lives in the Estimation Framework sync block at the end of this skill; Step 4 applies it verbatim to the observed (post-hoc) scope.
# Estimation Calibration Report — <plan or branch name>
## Summary
| Metric | Range / Value | Source |
| ----------------- | -------------------------- | ---------------------------------------- |
| Pre-impl estimate | <min>-<max>d (likely <m>d) | <plan path frontmatter> |
| TRUE estimate | <min>-<max>d (likely <m>d) | observed scope (post-hoc) |
| Actual time | <n>d | git <first commit→merge>, user-confirmed |
**Scope variance** (TRUE vs pre-impl): <±n>% — <under/over/matched>
**Execution variance** (actual vs TRUE likely): <±n>% — <fast/slow/matched>
## Verdict
| Signal | Direction | Magnitude | Confidence |
| ------------------- | ----------------------------------------------- | --------- | ----------------- |
| Estimation model | <too optimistic / too pessimistic / calibrated> | <±n>% | <low/medium/high> |
| Developer execution | | <±n>% | |
| Layer | Predicted tier | Observed tier | Delta |
| ------------ | ------------------ | ------------------ | --------------- |
| UI | … | … | … |
| Backend | … | … | … |
| Tests | … cases | … cases | … |
| Blast radius | … areas, … complex | … areas, … complex | … |
| Risk factors | | | |
No model adjustment from one data point. Logged to (row N). Re-run /estimate-actual on future plans to build calibration corpus. Suggested adjustment after ≥3-5 samples with consistent direction.
e.g. "UI tier 'Compose components into NEW screen' overshoots in 4/5 samples by ~0.5d → suggest splitting into two tiers OR widening band to 1-2.5d"
Actual time derived from ;
Pre-impl estimate format — comparison
Confidence in TRUE estimate: — observed scope
| Evasion | Rebuttal |
|---|---|
| "Single sample is enough — clearly the dev was slow" | NO. Without separating scope from execution variance, you confound model error and performance. State signal + caveat. |
| "Use git timestamps as actual time" | Wrong. Includes weekends, meetings, code-review wait, sleep. Always confirm with user. |
| "Skip TRUE estimate — just compare pre-impl vs actual" | That's the data point that's MISSING and exactly why estimates don't improve over time. Never skip Step 4. |
| "Apply hindsight to pump up TRUE estimate" | Use the SAME framework that was used for pre-impl. Hindsight bias inflates TRUE and falsely vindicates the original estimate. |
| "One signal is fine, no need to split" | Two signals is the entire point. Performance review needs execution variance; model tuning needs scope variance. Confounded data is unactionable. |
Estimation Framework — Bottom-up first; SP DERIVED; output min-max range when likely ≥3d. Stack-agnostic. Baseline: 3-5yr dev, 6 productive hrs/day. AI estimate assumes Claude Code + project context.
Method:
- Blast Radius pass (below) — drives code AND test cost
- Decompose phases → hours/phase →
bottom_up_hours = Σ phase_hourslikely_days = ceil(bottom_up_hours / 6) × productivity_factor- Sum Risk Margin (base + add-ons) →
max_days = likely_days × (1 + margin)min_days = likely_days × 0.9- Output as range when
likely_days ≥3; single point allowed<3(still record margin)man_days_ai= same range × AI speedupstory_pointsDERIVED fromlikely_daysvia SP-Days — NEVER driver. Disagreement >50% → trust bottom-upProductivity factor: 0.8 strong scaffolding+codegen+AI hooks · 1.0 mature default · 1.2 weak patterns · 1.5 greenfield
Cost Driver Heuristic (apply BEFORE work-type row):
- UI dominates in CRUD/business apps — 1.5-3x backend (states, validation, responsive, a11y, polish)
- Backend dominates ONLY: multi-aggregate invariants, cross-service contracts, schema migrations, heavy query/perf, new event flows
Reuse-vs-Create axis (PRIMARY lever, per layer):
UI tier Cost Reuse component on existing screen 0.1-0.3d Add control/column to existing screen 0.3-0.8d Compose components into NEW screen 1-2d NEW screen, custom layout/states/validation 2-4d NEW shared/common component (themed, tested) 3-6d+
Backend tier Cost Reuse query/handler from new place 0.1-0.3d Small update existing handler/entity 0.3-0.8d NEW query on existing repo/model
AI Mistake Prevention — Failure modes to avoid on every task:
Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.
Protocols in force (concise digest of the SYNC/shared blocks this skill carries):
file:line proof per claim, confidence >80% to act, no guess-as-fact.IMPORTANT MUST ATTENTION compute TRUE estimate using the SAME canonical framework — fair comparison requires identical methodology
IMPORTANT MUST ATTENTION separate developer execution signal from model calibration signal — never collapse to single verdict
IMPORTANT MUST ATTENTION never claim model adjustment from a single sample — explicitly state "needs ≥3 samples for signal"
IMPORTANT MUST ATTENTION never trust git timestamps as coding time — always ask user to confirm/override
IMPORTANT MUST ATTENTION list per-layer deltas (UI/backend/tests/blast) — aggregate variance hides where model went wrong
IMPORTANT MUST ATTENTION use min-max ranges for both pre-impl and TRUE — comparing single points is dishonest about uncertainty
IMPORTANT MUST ATTENTION apply Blast Radius pass on observed diff before applying tier tables
IMPORTANT MUST ATTENTION persist samples to plans/_estimation-samples.csv for longitudinal calibration
IMPORTANT MUST ATTENTION state confidence per verdict — uncertainty about actual time goes in caveats
[IMPORTANT] Use
TaskCreateto break ALL work into small tasks BEFORE starting.
Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.
MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.
[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.
| 0.5-1d |
| NEW command/handler on existing aggregate (additive) | 1-2d |
| NEW aggregate/entity (repo, validation, events) | 2-4d |
| NEW cross-service contract OR schema migration | 2-4d each |
| Multi-aggregate invariant / heavy domain rule | 3-5d |
Rule: Sum tiers across UI+backend+tests, apply productivity factor. Reuse short-circuits tiers — call out.
Test-Scope drivers (compute test_count EXPLICITLY — "+tests" hand-wave is #1 failure):
| Driver | Count |
|---|---|
| Happy-path journeys | 1 per story / AC main flow |
| State-machine transitions | reachable transitions × allowed actors |
| Multi-entity state combos | state(A) × state(B) — REACHABLE only, not Cartesian |
| Authorization matrix | (owner, non-owner, elevated, unauth) × each mutation |
| Validation rules | 1 per required field / boundary / format / cross-field |
| UI states (per new screen/dialog) | happy, loading, empty, error, partial — present only |
| Negative paths / invariants | 1 per violatable business rule |
| Test tier (Trad, incl. setup+assert+flake) | Cost |
|---|---|
| 1-5 cases, fixtures reused | 0.3-0.5d |
| 6-12 cases, 1 new fixture | 0.5-1d |
| 13-25 cases, multi-entity setup | 1-2d |
| 26-50 cases OR new state-machine coverage | 2-3d |
| >50 cases OR full E2E journey | 3-5d |
Test multipliers: new fixture/seed harness +0.5d · cross-service/bus assertion +0.3d each · UI E2E ×1.5 · each new role +1-2 cases
Blast Radius (mandatory pre-pass — affects code AND test):
Rule: Complex touch → add risk_factors. Each downstream consumer → +1-3 regression cases. Blast >5 areas OR >2 complex → re-evaluate SPLIT before estimating.
Risk Margin (drives max bound):
| likely_days | Base margin |
|---|---|
| <1d trivial | +10% |
| 1-2d small additive | +20% |
| 3-4d real feature | +35% |
| 5-7d large | +50% |
| 8-10d very large | +75% |
| >10d | +100% AND flag SHOULD SPLIT |
Risk-factor add-ons (additive — enumerate in risk_factors):
| Factor | +margin |
|---|---|
touches-complex-existing-feature (>500 LOC, multi-handler, central) | +20% |
cross-service-contract change | +25% |
schema-migration-on-populated-data | +25% |
new-tech-or-unfamiliar-pattern | +30% |
regression-fan-out (≥3 downstream areas re-test) | +20% |
performance-or-latency-critical | +20% |
concurrency-race-event-ordering | +25% |
shared-common-code (multi-consumer/multi-app) | +25% |
unclear-requirements-or-design | +30% |
Collapse rule: total margin >100% → STOP, split (padding past 2x is dishonesty). Margin <15% on likely_days ≥5 → under-estimated, widen.
Work-Type Caps (hard ceilings on likely_days):
| Work type | Max SP | Max likely |
|---|---|---|
| Single field / config flag / style fix | 1 | 0.5d |
| Add property to existing model + bind to existing UI | 2 | 1d |
| Additive endpoint + minor UI control (button/menu/column), reuses fixtures | 3 | 2-3d |
| Additive endpoint + NEW UI surface OR additive multi-layer + new domain rule + 2+ test files | 5 | 3-5d |
| NEW model/aggregate OR migration OR cross-module contract OR heavy test (>1.5d) OR NEW UI + non-trivial backend | 8 | 5-7d |
| NEW UI surface + (NEW aggregate OR migration OR cross-service contract) | 13 | SHOULD split |
| Cross-service contract + migration combined | 13 | SHOULD split |
| Beyond | 21 | MUST split |
SP→Days (validation only): 1=0.5d/0.25d · 2=1d/0.35d · 3=2d/0.65d · 5=4d/1.0d · 8=6d/1.5d · 13=10d/2.0d (Trad/AI likely)
AI speedup: SP 1≈2x · 2-3≈3x · 5-8≈4x · 13+≈5x. AI cost = (code_gen × 1.3) + (test_gen × 1.3) (30% review overhead).
MANDATORY frontmatter:
story_points: <n>
complexity: low | medium | high | critical
man_days_traditional: '<min>-<max>d' # range when likely ≥3d; '<N>d' when <3d
man_days_ai: '<min>-<max>d'
risk_margin_pct: <n> # base + add-ons
risk_factors: [touches-complex-existing-feature, regression-fan-out] # closed-list from add-ons; [] if none
blast_radius:
touched_areas: <n>
complex_touched: <n>
downstream_consumers: [list or count]
shared_common_code: yes | no
estimate_scope_included: [code, integration-tests, frontend, i18n, docs]
estimate_scope_excluded: [unit-tests, e2e, perf, deployment, code-review-rounds]
estimate_reasoning: |
5-7 lines covering:
(a) UI tier — row applied
(b) Backend tier — row applied
(c) Test scope — case breakdown by driver, file count, fixtures, tier row
(d) Cost driver — dominant tier + why
(e) Blast radius — touched, complex, regression scope
(f) Risk factors — list driving margin; why not larger/smaller
Example: "UI: compose Form/Table/Dialog → NEW screen (~1.5d). Backend: NEW command on existing aggregate,
reuses validation+repo (~1d). Tests: 4 transitions × 2 actors + 3 validation + 2 UI states = 13 cases,
1 new fixture → tier 13-25 ~1.5d. Driver: UI composition + new states. Blast: 4 areas, 1 complex.
Risk: base 35% + touches-complex +20% = 55% → max 3.9d → range 2.5-4d."
Sanity self-check:
likely_days ≥3d and single-point? → reject, must be rangelikely_days ≥5d? → under-estimated, widen(c)? → reject>5 areas OR >2 complex, no split discussion? → rejectbottom_up_hours / 6 vs SP-Days disagreement >50%? → trust bottom-up, downgrade SP