increment SKILL.md skillA

increment from a-lottes/aspark is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add a-lottes/aspark/increment@git:20260821.b0d0761

Pins git:20260821.b0d0761 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
a-lottes/aspark
Path
skills/increment/SKILL.md
Versions recorded
4
Latest version
git:20260821.b0d0761, committed Aug 21, 2026
First version recorded
Jul 13, 2026
Size
3,978 bytes
Repository stars
24
License
MIT

Start the Act phase of the SPARK loop: build the increment strictly following the approved plan, task by task, with progress tracked in the plan. Use after the plan is approved, or to fix findings that came back from /peer-review or /demo-day.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# /increment — Act (Developer)

You are running the **Act** ceremony — and this time *you* are the team
member: the developer. No delegation; you build the increment yourself, in
this conversation, so the user can watch and steer.

## Input

Optional argument: the feature name. Resolve as usual.

## Steps

1. **Check the gate.** `.spark/<feature-name>/plan.md` must exist with
   status `approved`. If not, STOP and point to `/sprint-plan`.
2. **Load the working set — not the whole files.** From `plan.md`: §1
   Architecture Decision, §2 Affected Components, §3 Task Breakdown, §4 Test
   Strategy. From `spec.md`: §4 User Stories with their ACs, §5
   Non-Functional Requirements, §6 Out of Scope. That is your backlog, your
   definition of correct, and your scope fence. The rest — personas,
   assumptions, the clarification log, the design review, the risk table —
   is material the Plan phase already consumed and turned into tasks;
   re-reading it here buys nothing and costs the context that the tasks
   themselves need. Pull a further section only when a task actually calls
   for it. The plan is your backlog — the task table top to bottom,
   dependencies respected.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add a-lottes/aspark/increment@sha256:787d9ad9baef27db

The line at the top of this page pins the label git:20260821.b0d0761, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pei6q3khwfzsubu7.svg)](https://markdownregistry.com/a/art_pei6q3khwfzsubu7)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 13, 2026 and Aug 21, 2026, about one every 13 days.

versioncommittedcommitsizeaudit
git:20260821.b0d0761 latest2026-08-21 b0d0761 3,978 BA view · diff
git:20260817.3d2939d2026-08-17 3d2939d 3,727 BA view · diff
git:20260727.8eadc992026-07-27 8eadc99 3,204 BA view · diff
git:20260713.ca08cab2026-07-13 ca08cab 2,661 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3978 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

a-lottes/aspark · 24 stars · license MIT · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pei6q3khwfzsubu7
GET https://markdownregistry.com/api/v1/resolve?ref=a-lottes/aspark/increment
GET https://markdownregistry.com/api/v1/blob/787d9ad9baef27dbcea83605d6af34da7c59af83f2033b1781fc8156cff2b39c

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from a-lottes/aspark

CLAUDE.md CLAUDE.md file
a-lottes/aspark · CLAUDE.md
git:20261015.1afbf84 · audit A · 24 stars
backlog SKILL.md skill
a-lottes/aspark · skills/backlog/SKILL.md · Seed a backlog from the project's documents: the Product Owner reads docs/ (plus the constitution and ROADMAP.md)…
git:20261028.36cf3fb · audit A · 24 stars
campaign SKILL.md skill
a-lottes/aspark · skills/campaign/SKILL.md · Start a campaign draft: build `.spark/campaigns/<name>/campaign.md` from an existing campaign kind, asking only what…
git:20261016.a7b9a4e · audit A · 24 stars
charter SKILL.md skill
a-lottes/aspark · skills/charter/SKILL.md · Establish or amend the project constitution — the standing principles and constraints that bind every SPARK phase. Use…
git:20261028.ccb5df1 · audit A · 24 stars
demo-day SKILL.md skill
a-lottes/aspark · skills/demo-day/SKILL.md · Hands-on QA in a real browser: the QA Tester clicks through the running app, verifies every acceptance criterion from…
git:20261028.486dc7f · audit A · 24 stars
go-live SKILL.md skill
a-lottes/aspark · skills/go-live/SKILL.md · Start the Keep phase of the SPARK loop: the Release Manager runs fresh pre-flight checks, writes the user-facing…
git:20261028.35230f3 · audit A · 24 stars
look-and-feel SKILL.md skill
a-lottes/aspark · skills/look-and-feel/SKILL.md · Run the Designer over a spec (design risks, usability heuristics, accessibility) or over an implemented UI…
git:20260917.f32be5c · audit A · 24 stars
next-steps SKILL.md skill
a-lottes/aspark · skills/next-steps/SKILL.md · Have the Product Owner survey the project's current state — shipped features, in-flight work, open findings, standing…
git:20261028.50d2efb · audit A · 24 stars
peer-review SKILL.md skill
a-lottes/aspark · skills/peer-review/SKILL.md · Start the Review phase of the SPARK loop: the Reviewer audits the diff produced by /increment — plan conformance…
git:20261028.486dc7f · audit A · 24 stars
spark SKILL.md skill
a-lottes/aspark · skills/spark/SKILL.md · Run the full SPARK loop end-to-end for one feature: Specify → Plan → Act → Review → Keep, pausing at every gate for the…
git:20261028.ccb5df1 · audit A · 24 stars
sprint-plan SKILL.md skill
a-lottes/aspark · skills/sprint-plan/SKILL.md · Start the Plan phase of the SPARK loop: the Engineering Manager turns an approved spec into a technical plan —…
git:20260727.8eadc99 · audit A · 24 stars
story-time SKILL.md skill
a-lottes/aspark · skills/story-time/SKILL.md · Start the Specify phase of the SPARK loop: the Product Owner interrogates a product idea and turns it into a spec with…
git:20261028.29e973c · audit A · 24 stars

Every file in a-lottes/aspark

Browse by kind, by grade A, or by owner.