develop
Implement a feature or fix from agreed requirements, then verify it and resolve an independent spec review.
Skill by lithammer
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lithammer-develop
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/develop
What's inside
- Skill name
develop- Description
- Implement a feature or fix from agreed requirements, then verify it and resolve an independent spec review. Use when carrying a defined change through implementation.
- License
- MIT
- Instructions
- 76 lines in SKILL.md · view on GitHub
Files (3)
- REVIEW.md
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Develop ## 1. Establish the scope Read the request, its spec or tickets, and the documented standards the review will hold the change to. Resolve ambiguities that would change observable behavior. Stay on the current branch unless the user asks otherwise; preserve unrelated changes and existing staging. Pin the review base before editing and record pre-existing changes. ## 2. Implement **Encode meaning and invariants in the model.** Use types, APIs, and enforced constraints to express distinctions callers would otherwise need to remember: units, identities, valid states, and permitted operations. Prefer representations that prevent misuse over conventions, repeated checks, or tests that merely detect it. Validate external inputs at the boundary. **Shape the code for its production callers.** Choose the cleanest design for the code that runs, then bring the tests to it. When that design breaks an existing test that pins internal structure rather than a contract, rewrite the test against the contract. Reach behavior and resolve uncertainty through real runs and throwaway probes; add a seam only tests use when nothing else can reach it, and name it in the report. Continue until the requested behavior is implemented through the agreed interfaces. ## 3. Establish correctness Verify the change against real behavior with existing tests, a real run, or throwaway tests and probes. Derive expected results from the requirements, reviewed examples, or a trusted reference, rather than the implementation's current output. Choose cases that distinguish plausible mistakes. Fix defects the checks expose, record what each check showed, and delete the throwaway code. A new test encodes your reading of the requirements, the same reading the implementation encodes. Retain one only when the user asks for a test. Propose a test only where a regression would go unnoticed by types, existing tests, or a quick real run, and an incidental edit, made while changing nearby code for another reason, could bring it back. Propose every test that meets this, each on its own line: the contract, the incidental edit that would break it, and how you verified it now. Continue until the relevant tests pass after the fixes; record pre-existing failures separately. ## 4. Review and finish Follow [FINAL-REVIEW.md](FINAL-REVIEW.md) for fresh reviews against the spec and the documented standards. Keep the reviewed files unchanged while reviewers work. Assess each finding against its evidence. Fix confirmed issues and record why others do not apply. Send fixes back to the affected reviewers, including the other axis when a fix changes what it reviewed. Close findings on the final state; a report about an earlier version is not final verification. Run the repository's required checks on the final state. Leave the task's edits uncommitted and unstaged unless the user asks otherwise. Report the changes, including fixes beyond the request, what each check showed, each review's outcome, test proposals, and any remaining limits. If a required check or a review cannot complete, report that gap and leave the task open.
From lithammer/ai, MIT.
More from lithammer/ai
- 0.565score
code-review
lithammer
Review changed code for correctness bugs and instruction-file violations, verify each candidate, and report the survivors without editing.
SkillAFreshness: AClaude Code +9 - 0.565score
create-pr
lithammer
Create a draft or ready-for-review PR for the current branch.
SkillAFreshness: AClaude Code +9 - 0.561score
simplify
lithammer
Clean up changed code without changing behavior — review it for reuse, simplification, efficiency, and altitude, then apply the fixes.
SkillAFreshness: AClaude Code +9 - 0.558score
review-docs
lithammer
Reviews doc, docstring, and comment diffs for AI-like prose and for comments that no longer have a job.
SkillAFreshness: AClaude Code +9 - 0.558score
nemesis
lithammer
Challenge a plan, design, or implementation one branch at a time.
SkillAFreshness: AClaude Code +9 - 0.558score
refactor
lithammer
Find structural refactors that remove caller obligations, then implement the chosen change.
SkillAFreshness: AClaude Code +9 - 0.558score
research-codebase
lithammer
Map how the code a ticket touches works today, then name the next step: develop, refactor, or grill-with-docs.
SkillAFreshness: AClaude Code +9 - 0.539score
implement-review
lithammer
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…
SkillAFreshness: AClaude Code +9 - 0.539score
tdd
lithammer
Test-driven development.
SkillAFreshness: AClaude Code +9 - 0.533score
ask-matt
lithammer
Ask which skill or flow fits your situation.
SkillAFreshness: AClaude Code +9 - 0.530score
implement-spec
lithammer
Implement the result of /to-spec and /to-tickets in code.
SkillAFreshness: AClaude Code +9 - 0.528score
implement
lithammer
Implement a piece of work based on a spec or set of tickets.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 24, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lithammer/ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lithammer
- 0.565score
code-review
lithammer
Review changed code for correctness bugs and instruction-file violations, verify each candidate, and report the survivors without editing.
SkillAFreshness: AClaude Code +9 - 0.565score
create-pr
lithammer
Create a draft or ready-for-review PR for the current branch.
SkillAFreshness: AClaude Code +9 - 0.561score
simplify
lithammer
Clean up changed code without changing behavior — review it for reuse, simplification, efficiency, and altitude, then apply the fixes.
SkillAFreshness: AClaude Code +9 - 0.558score
nemesis
lithammer
Challenge a plan, design, or implementation one branch at a time.
SkillAFreshness: AClaude Code +9 - 0.558score
review-docs
lithammer
Reviews doc, docstring, and comment diffs for AI-like prose and for comments that no longer have a job.
SkillAFreshness: AClaude Code +9 - 0.558score
refactor
lithammer
Find structural refactors that remove caller obligations, then implement the chosen change.
SkillAFreshness: AClaude Code +9
Cite this page
develop skill. Agent Mart. https://agentmart.dev/skills/lithammer-develop (last updated 2026-10-24)