refine-story-functionally
ADP Phase 1 — functional story refinement.
Skill by jterratsdev
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jterratsdev-refine-story-functionally
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/refine-story-functionally
What's inside
- Skill name
refine-story-functionally- Description
- ADP Phase 1 — functional story refinement. Runs discovery probes, applies the acceptance-criteria quality framework (INVEST + testable Gherkin), and records a refined, Ready story to the local backlog. USE FOR: refine story functionally, functional refinement, discovery probes, acceptance criteria quality, INVEST check, ADP Phase 1. Reusable by BA, SA, and TA profiles.
- License
- BSD-3-Clause
- Instructions
- 67 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Refine Story Functionally (ADP Phase 1)
## Backlog is Local (CRITICAL)
Refined stories are stored in the **repo-resident backlog**, not an external tracker.
The source of truth is `.setup-agents/state/tasks.jsonl`.
- Persist every refined story with the local task command:
```bash
sf setup-agents task create --id <ID> --summary "<title>" --role <role>
```
- Do **NOT** write stories to Jira as part of refinement. Atlassian MCP is **optional** —
if it is configured you MAY mirror a story outward, but the local backlog remains authoritative.
- This trades against ADP's "agents never store stories in the repo" default on purpose:
setup-agents keeps git as the source of truth.
## 1. Discovery Probes
Before writing any acceptance criteria, ask the probes that surface hidden requirements:
- **Who** is the persona and what is their goal? What is the value delivered?
- **What** is explicitly IN scope, and what is explicitly OUT of scope (non-goals)?
- **When / triggers** — what event starts this? What are the edge and error paths?
- **Data** — which objects/fields are read or written? Any PII or consent implications?
- **Assumptions & dependencies** — what must already exist? Which stories block this one?
Capture the answers; unanswered probes are gaps, not assumptions to invent.
## 2. Acceptance Criteria Quality Framework
Every AC must be **testable** and written in Gherkin (Given / When / Then):
```gherkin
Given <precondition>
When <action>
Then <observable, verifiable outcome>
```
| Quality gate | Rule |
|--------------|------|
| Independent | Story delivers value on its own; dependencies are declared, not hidden. |
| Negotiable | Captures the WHAT, not a locked-in HOW. |
| Valuable | Ties back to a persona goal / business value. |
| Estimable | Enough detail to size (hand to `generate-rom`). |
| Small | Fits one iteration; if not, hand to `decompose`. |
| Testable | Each AC has an observable outcome QA can verify. |
- Reject vague ACs ("works correctly", "is fast") — restate as observable outcomes.
- Every AC that touches PII must carry a Privacy AC (fields, legal basis, retention).
## 3. Ready Definition
A story is **Ready** only when: persona linked, scope + non-goals stated, ACs pass the
quality framework, data/objects listed, dependencies declared, and a sizing signal exists.
If any item is missing, the story is **Not Ready** — do not hand to technical refinement.
## 4. Persist to the Local Backlog
Record the refined story with `sf setup-agents task create` (see above). Include the
persona, Gherkin ACs, non-goals, and dependencies in the summary/goal so the technical
refinement phase and QA can consume them.
## 5. Handoff
A story sized M or larger, or one with technical unknowns, is handed to
`refine-story-technically` (TA) for impact analysis and technical tasking.From jterratsdev/smart-deployment, BSD-3-Clause.
More from jterratsdev/smart-deployment
- 0.570score
elements-sync
jterratsdev
Create and update Requirements and Stories in Elements.cloud from story maps, backlog documents, or free-form descriptions.
SkillAFreshness: AClaude Code +9 - 0.565score
sf-code-analyzer
jterratsdev
Run static code analysis on Salesforce projects using sf code-analyzer.
SkillAFreshness: AClaude Code +9 - 0.565score
prompt-registry
jterratsdev
Maintain the .generated-prompts/ register: read before creating any artifact to infer project conventions, write/update after creation.
SkillAFreshness: AClaude Code +9 - 0.565score
qa-evidence-pack
jterratsdev
Build reviewable QA evidence packs that map acceptance criteria to observable outcomes, command results, screenshots, traces, videos, API contracts…
SkillAFreshness: AClaude Code +9 - 0.565score
record-adr
jterratsdev
Record an Architecture Decision Record (ADR).
SkillAFreshness: AClaude Code +9 - 0.565score
refine-story-technically
jterratsdev
ADP Phase 2 — technical story refinement.
SkillAFreshness: AClaude Code +9 - 0.565score
sf-deploy
jterratsdev
Deploy and validate Salesforce metadata using @jterrats/profiler for complete profile retrieval and @jterrats/smart-deployment for dependency-aware wave…
SkillAFreshness: AClaude Code +9 - 0.565score
backlog-sync
jterratsdev
Push user stories from story maps to issue trackers.
SkillAFreshness: AClaude Code +9 - 0.565score
org-health-assessment
jterratsdev
Assess the health of a Salesforce org across security, automation, permissions, data model, schema limits, license utilization, and large data volumes —…
SkillAFreshness: AClaude Code +9 - 0.565score
project-knowledge-bootstrap
jterratsdev
Scan a Salesforce project structure and populate .setup-agents/project-knowledge.md with architecture decisions, naming conventions, label language, and…
SkillAFreshness: AClaude Code +9 - 0.564score
transcription-evidence
jterratsdev
Transcribe audio/video files and record as workflow evidence
SkillAFreshness: AClaude Code +9 - 0.561score
generate-rom
jterratsdev
Produce a Rough Order of Magnitude (ROM) effort baseline for a story or epic and record it against the local backlog task.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 14
- Last commit (this folder)
- Aug 5, 2026 (2 months ago)
- Last release
- Sep 29, 2026 (29 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- BSD-3-Clause
- Repository
- github.com/jterratsdev/smart-deployment
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jterratsdev
- 0.570score
elements-sync
jterratsdev
Create and update Requirements and Stories in Elements.cloud from story maps, backlog documents, or free-form descriptions.
SkillAFreshness: AClaude Code +9 - 0.565score
project-knowledge-bootstrap
jterratsdev
Scan a Salesforce project structure and populate .setup-agents/project-knowledge.md with architecture decisions, naming conventions, label language, and…
SkillAFreshness: AClaude Code +9 - 0.565score
sf-code-analyzer
jterratsdev
Run static code analysis on Salesforce projects using sf code-analyzer.
SkillAFreshness: AClaude Code +9 - 0.565score
org-health-assessment
jterratsdev
Assess the health of a Salesforce org across security, automation, permissions, data model, schema limits, license utilization, and large data volumes —…
SkillAFreshness: AClaude Code +9 - 0.565score
prompt-registry
jterratsdev
Maintain the .generated-prompts/ register: read before creating any artifact to infer project conventions, write/update after creation.
SkillAFreshness: AClaude Code +9 - 0.565score
qa-evidence-pack
jterratsdev
Build reviewable QA evidence packs that map acceptance criteria to observable outcomes, command results, screenshots, traces, videos, API contracts…
SkillAFreshness: AClaude Code +9
Cite this page
refine-story-functionally skill. Agent Mart. https://agentmart.dev/skills/jterratsdev-refine-story-functionally (last updated 2026-10-24)