agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/development-lifecycle/SKILL.md

development-lifecycle

Skill4 starsChanged 10 days agoMITView on GitHub

Run React, TypeScript, and UI implementation from a high-level outcome through self-verification.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read tickets/body/labels/comments.

    line 28
  2. Very specific:

    Read rules/scripts/configs/CI.

    line 30
  3. Distinctive:

    Ask only for user-reserved decisions or irreversible production, legal/privacy, destructive, or high-security actions.

    line 58
  4. Distinctive:

    Run author delivery: inline self-review, evidence, publication and requested CI/feedback.

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

For multi-step delivery, read Poteto.

/work: one outcome. Before edits, read author delivery for ownership, isolation and endpoints. Use communication; helpers.

Outcome contract

State:

  • Objective -- outcome.
  • Guardrails -- non-inferable/reserved bounds.
  • Verification -- observable behavior.
  • Stop -- endpoint/blockers.

Build/fix/implement: continue immediately; auto-setup within endpoint.

Loop

inspect -> act -> verify -> repeat

Inspect

Read tickets/body/labels/comments; title, clarify refs. Resolve blind spot/volatile unknowns via lookup/probe/reversible assumption/pause; match repo idiom/demonstrated scale.

Read rules/scripts/configs/CI; note baseline failures; keep tools.

T3/Effect work: resolve native context (work); use target guidance/scoped checks.

Load change evidence and owners. Assess risk; capture bases only for useful/required comparisons. Reuse checks.

Figma/image.

Act

A single owner; delegation/background need explicit consent. Implement the smallest functional diff using local conventions. Use tdd for uncovered regressions; reuse checks otherwise. Re-plan only the affected slice; no speculative abstractions or adjacent cleanup.

Per batch: scoped format/fix + lint -> types/tests. Inspect; repair/rerun. Reuse hooks only for identical inputs/coverage; keep project-wide types.

Imports: checks.

Verify

Handoff: repo gates; scoped checks never replace them. Load dogfood for material runnable behavior: real entrypoint + credible failure/recovery. Review objective/guardrails/credible risk; green checks do not prove intent. A failure becomes the next action; repair/repeat. Unrelated baseline failures: report, never claim a pass.

Fix causes, not gates: never weaken checks/tests/strictness to pass. Bad rules need a tooling rationale and known-bad/valid cases. Missing entrypoint: disposable harness; durable gap: /create-verification-skill.

Boundaries

Ask only for user-reserved decisions or irreversible production, legal/privacy, destructive, or high-security actions. Reuse local notes only when a long task needs a checkpoint; routine work needs no evidence/checklist file.

Completion

Run author delivery: inline self-review, evidence, publication and requested CI/feedback. Reuse verification; stop only at the requested endpoint when every exit criterion passes. Refactor.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free