Skip to content
Skills Library
Programming · Building & coding

s-dev

/s-dev

Implement or repair one coherent product change with behavior-first evidence, useful seams, and proportional architecture. Use for a scoped change or when another workflow delegates a mutation unit.

Repository
skills ↗
Licence
MIT
Last repository change
20.10.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 20.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Implement or repair one coherent product change with behavior-first evidence, useful seams, and proportional architecture. Use for a scoped change or when another workflow delegates a mutation unit.

Original author description

Implement or repair one coherent product change with behavior-first evidence, useful seams, and proportional architecture. Use for a scoped change or when another workflow delegates a mutation unit.

How it works

SKILL.md has no level-two headings · 27 lines, 342 words

SKILL.md preview
---
name: s-dev
description: Implement or repair one coherent product change with behavior-first evidence, useful seams, and proportional architecture. Use for a scoped change or when another workflow delegates a mutation unit.
---

# S Dev

Own maintained-product mutation. Work from the accepted behavior, boundaries, current candidate, and relevant reviewer findings; hold the accepted destination.

Load [data-quality guidance](../sflo-waydriver/references/data-quality.md) for work on the quality or fitness of data itself. When data supplies evidence for another outcome, select expertise for that outcome. Carry the relevant quality rules and evidence into implementation and builder checks.

When implementation changes domain concepts, language, relationships or rules, apply [domain modeling](../s-domain-modeling/SKILL.md) and carry resolved meanings into behavior checks.

Build in vertical slices. For code, repeat this cycle:

1. Add one behavior test at a public seam and run it to establish the failure.
2. Implement that behavior through its required layers and run the check to establish the pass.
3. Use that working slice to choose the next behavior test.

Pair each edit with its check in one tool invocation when sequential execution is supported; inspect the result before the next cycle.

When a failure cannot be represented in an executable test, establish the corresponding observable falsifier. Refactor only while established behavior stays proven. When a rule is demonstrably repeated or already varies, place it behind one local seam that improves locality and leverage; avoid speculative layers and generic abstractions.

For non-code artifacts, establish the cheapest meaningful falsifier before settling the final change. Follow the medium's acceptance conditions rather than translating code rituals mechanically.

UI work follows the project's design system. If none exists, establish a proportional system of reusable tokens and components. Treat light/dark/system appearance, accessibility, responsive and complete states, logical layout, and longer-text tolerance as acceptance, not later polish.

Preserve project conventions and previously proven behavior. Return the candidate identity, changed paths, intended delta, and builder checks to the caller. Builder checks establish readiness; they are not independent acceptance. Standalone use creates no run-state artifact.

For repair, reproduce or validate the finding against its candidate, fix the smallest coherent cause, and issue a new candidate identity. Route unexplained failures to an evidence-first diagnostic capability, including active reproduction when justified. Return the candidate to the checker that owns the invalidated evidence.
Files in this package (2)
  • SKILL.md 3 KB
  • agents/openai.yaml 1 KB

Versions

The database has no other skills named s-dev.

Database snapshot: 13.11.2026 · package version 877210e2a37c (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90dev-feature
    Use when adding or changing behavior: a new feature, a behavior change, or a user-visible improvement.
  • 100dev-story
    Implement one story: code, check, evidence. Use when the user says to build or implement a story.
  • 86implement-work
    Implement an assigned change and report behavior evidence. Use for delegated implementation with a task brief and explicit file ownership.
  • 85flats-implement
    Implement a defined Flats repository change with development-time tests and independent adversarial code review. Use when the user explicitly limits work to implementation or when called by flats-dev-workflow; requires current design-review evidence. Unqualified implement or fix…
  • 100dev-spec-driven-implementation
    Use to implement a scoped multi-step change from an existing spec, handoff, issue, or explicit delivery request. Do not trigger for read-only analysis, planning, or a trivial localized edit.
  • 100dx-agent-dev
    Dev Agent: implement code from an RE spec — implement, self-check (build/test/lint), fix failures, commit. Use for 'dev agent', 'implement from spec'.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.