Develop
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.
Install
npx skills add flurdy/agent-skills --skill developgit clone --depth 1 https://github.com/flurdy/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/develop ~/.claude/skills/developPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the 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](../diagnose-bug/SKILL.md) first. - If consequential architecture, security, public-contract, migration, or hard-to-reverse
Details
- Skill name
develop- Repository
- flurdy/agent-skills
- Path
skills/develop/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Develop skill do?
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.
How do I install the Develop skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add flurdy/agent-skills --skill develop. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Develop popular?
It lives in flurdy/agent-skills, which has 9 GitHub stars and 0 forks.
Related skills
Architect
9flurdy/agent-skills
Architecture and implementation planning gate for complex or high-blast-radius work. Produces evidence-backed decisions, reviewable slices, acceptance evidence, and conditional human review ownership without editing code.
Artifact Hygiene
9flurdy/agent-skills
Run a local-only, read-only advisory audit of publishable working-tree files and unpublished branch history with redaction-safe findings.
Backlog Groom
9flurdy/agent-skills
Auto-detects workspace unfinished backlogs across unique stores; otherwise local open beads. Flags thin prose, missing labels, drift, lifecycle and duplicates. Report-only; mutations need approval, destructive ones individually.
Implement Solution
9flurdy/agent-skills
Use before non-trivial coding with clear requirements: interacting behavior, state/error paths, or local design trade-offs. Also use when ongoing implementation becomes complex. Premium implementation; skip mechanical edits and unresolved diagnosis.
Codeless Connectors
5dstreefkerk/claude-skills
Use before writing any Microsoft Sentinel connector ARM template, DCR, KQL transform, or createUiDefinition.json. Provides the complete CCF (Codeless Connector Framework) reference for RestApiPoller, Push, and GCP connector types — including escaping rules, authentication, pagination, UI definitions, and deployment gotchas. Also use when debugging connector deployment failures or reviewing existing CCP templates.
Pair Programming
9flurdy/agent-skills
Opt-in conversational pairing when the user explicitly asks to pair: the agent writes authorized code in small agreed steps, discussing decisions and results throughout. Not for ordinary implementation requests.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.