agentleFS
flurdyflurdy/agent-skills/skills/develop/SKILL.md

develop

Skill9 starsChanged 3 months agoMITView on GitHub

Load before authorized code changes: features, fixes, refactors, tests, and mechanical edits, including discussion-to-coding transitions. Read separately from edits. Skip read-only requests and implementation already owned by a specialist.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use scope, sync and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • YuriNachosSkill

    scope

    Configure claude-scope status line widgets for Claude Code. Use when user wants to customize widgets, change theme, reorder elements, or modify display style.

    Also in 6 projects that use this

  • MicrosoftSkill

    sync

    Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.

    Also in 6 projects that use this

  • nicolasestremSkill

    document

    Create focused documentation for specific components or features

    Also in 5 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 5 projects that use this

  • AnthropicSkill

    debug

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    Also in 9 projects that use this

  • Microsoft AzureSkill

    test

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read this skill once per new coding run, even if its text remains in context from a previous run.

    line 16
  2. Distinctive:

    Never mutate in the same response that loads the skill: keep edits, writes, and shell mutations separate from the read.

    line 19
  3. Distinctive:

    Keep read-only requests read-only.

    line 25
  4. Distinctive:

    If an implementation specialist already owns the work, continue it.

    line 27
  5. Distinctive:

    If a bug's cause is unknown, use diagnose-bug first.

    line 29
  6. Distinctive:

    If consequential architecture, security, public-contract, migration, or hard-to-reverse decisions remain unresolved, use architect before …

    line 30

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “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

Develop

A lightweight coding entry point, not another implementation workflow. Request the runtime's configured standard/high route, then use normal repository-grounded coding judgment. Explicit invocation is /develop <task>; in Pi use /skill:develop <task>. On Claude Code this skill carries no model: pin on purpose: it rides the session model rather than downgrading to the standard alias, while Pi routes by model-tier.

Read this skill once per new coding run, even if its text remains in context from a previous run. Use a standalone skill read before generating mutation calls. Continue on the next model response after the skill read returns, not a new user message. Never mutate in the same response that loads the skill: keep edits, writes, and shell mutations separate from the read. Apply the same separation when loading a specialist below. Already-generated edits are not upgraded by a model switch.

Choose the next step

  • Keep read-only requests read-only. Skill selection does not authorize edits or override plan mode, repository rules, scope, or confirmation requirements.
  • If an implementation specialist already owns the work, continue it; do not restart through this entry point just to request a route.
  • If a bug's cause is unknown, use diagnose-bug first.
  • If consequential architecture, security, public-contract, migration, or hard-to-reverse decisions remain unresolved, use architect before coding.
  • For implementation-ready work with interacting behavior, meaningful state/error paths, or local design trade-offs, load implement-solution. Reassess if an initially simple edit develops those characteristics; hand off without restarting completed work.
  • Otherwise, make the smallest appropriate change using established repository patterns and proportionate tests/checks. Do not add planning, delegation, or review ceremonies merely because this skill loaded.

Routing limits

Automatic loading is best-effort, not a pre-write enforcement mechanism. Metadata requests capability; it does not prove the active model changed. Respect runtime spend and manual-selection controls; do not edit routing configuration or launch another model to force a route.

Pi currently protects against nested tier downgrades only after a routed run begins. The first standard-tier route can replace a stronger session model. This skill does not establish a capability floor; see model routing.

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.