improve-spec

Included with Lifetime

$97 forever

Use to polish a spec/PRD/feature doc. Adds testable acceptance criteria, surfaces ambiguities, identifies missing edge cases. Output is a marked-up version of the spec, not a rewrite.

Writing & Docs

What this skill does


# improve-spec

Spec polish. Adds rigour. Surfaces gaps. Doesn't rewrite the user's voice.

## Method

1. **Read the spec.** Quote sections back in your output as you address them — keeps the user oriented.
2. **Ambiguity sweep.** Find every:
   - Unbounded quantifier ("fast", "many", "good")
   - Passive voice hiding the actor
   - Tense ambiguity (will/may/should)
   - Missing units (seconds vs minutes, MB vs GB)
3. **Acceptance criteria.** Every behaviour bullet should map to a testable assertion. If it doesn't:
   - Propose 1-3 testable criteria
   - Mark which become unit tests vs integration vs manual UAT
4. **Edge cases.**
   - Empty / zero / null input
   - Very large input
   - Concurrent calls
   - Failure of each downstream
   - Auth boundaries (anonymous, expired, revoked)
   - Time boundaries (epoch, far future, DST)
5. **Out-of-scope explicit.** Spec should name what it's NOT doing — half the value is the negative space.

## Output shape

Markup the original spec inline (annotated). Keep the user's voice; add precision in `> [improve-spec]: ...` callouts.

```
## Original Spec (annotated)

### Overview
Build a "buy now" button on the product page.

> [improve-spec] Ambiguity: "product page" — applies to all product types or
> excludes digital goods?

### Behaviour
- Click triggers checkout
- Show confirmation

> [improve-spec] Acceptance criteria proposed:
>   AC1 [unit]    Click on "Buy now" emits {event: "buy.click", productId} 
>   AC2 [integ]   On checkout success, confirmation page shows order id 
>                 within 2s p95
>   AC3 [manual]  Confirmation visible to assistive tech
>
> [improve-spec] Edge cases not covered:
>   - User not signed in (redirect to login? or guest checkout?)
>   - Out-of-stock item (button state? error?)
>   - Network failure mid-purchase (idempotency? retry?)

### Non-goals (proposed addition)
- Recurring subscriptions (separate spec)
- Volume pricing (separate spec)
- Cart consolidation (use existing flow)
```

## Rules

- **Don't rewrite.** Annotate. Keep the user's voice.
- **Every ambiguity gets a question or a proposal.** No bare flagging.
- **Acceptance criteria are testable.** "Behaves correctly" doesn't qualify.
- **Edge cases are concrete.** Not "handle errors" — name the error mode.
- **Out-of-scope is part of the spec.** Always propose if missing.

## Anti-patterns

- Replacing the user's prose with consultant-speak
- Marking everything as "needs clarification" — pick the load-bearing ones
- Acceptance criteria that just restate the requirement
- Edge cases not relevant to the actual stack

## When NOT to use

- Final spec already through review — too late
- One-line feature request — overkill
- Scratch / dream stage — `/dream` instead

## Subagent dispatch

- `Plan` for acceptance criteria generation
- `general-purpose` for edge-case enumeration
- Memory MCP for prior similar specs

## Value over native CC

CC will critique a doc on request. CC won't naturally produce annotated-in-place output, separate ambiguity from acceptance from edge cases, or insist on out-of-scope being explicit. The structure IS the value.

Files: 1

Size: 3.3 KB

Complexity: 7/100

Category: Writing & Docs

Source: https://github.com/ialameh/sift-coder/tree/main/skills/spec/improve-spec

Related in Writing & Docs

jax-development

Included

Use this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.

Writing & Docsscripts

nature-article-writer

Included

Drafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.

Writing & Docsscripts

deckrd

Included

Document-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.

Writing & Docsscripts

clinical-decision-support

Included

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

Writing & Docsscripts

handling-sf-data

Included

Salesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).

Writing & Docsscripts

accelint-ac-to-playwright

Included

Convert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.

Writing & Docsscripts