TDD Workflow
hellangleZ/burn-in-cceverywhere-ralph
A skill your agent uses when writing new features, fixing bugs, or refactoring code.
Defines self-acknowledgments for production declarations and tests.
Install Contracts
$ npx skills add samchon/nestia --skill contracts -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install samchon/nestia contracts --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/samchon/nestia.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/contracts .claude/skills/contracts && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "contracts" agent skill from https://github.com/samchon/nestia/tree/master/.agents/skills/contracts into .claude/skills/contracts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "contracts", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/samchon/nestia/tree/master/.agents/skills/contractsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add samchon/nestia --skill contracts -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install samchon/nestia contracts --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samchon/nestia.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/contracts .agents/skills/contracts && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "contracts" agent skill from https://github.com/samchon/nestia/tree/master/.agents/skills/contracts into .agents/skills/contracts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "contracts", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add samchon/nestia --skill contracts -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install samchon/nestia contracts --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samchon/nestia.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/contracts .cursor/skills/contracts && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "contracts" agent skill from https://github.com/samchon/nestia/tree/master/.agents/skills/contracts into .cursor/skills/contracts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "contracts", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/samchon/nestia.git --path .agents/skills/contracts--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add samchon/nestia --skill contracts -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install samchon/nestia contracts --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samchon/nestia.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/contracts .gemini/skills/contracts && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "contracts" agent skill from https://github.com/samchon/nestia/tree/master/.agents/skills/contracts into .gemini/skills/contracts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "contracts", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install samchon/nestia contractsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add samchon/nestia --skill contracts -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/samchon/nestia.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/contracts .github/skills/contracts && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "contracts" agent skill from https://github.com/samchon/nestia/tree/master/.agents/skills/contracts into .github/skills/contracts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "contracts", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add samchon/nestia --skill contracts -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install samchon/nestia contracts --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samchon/nestia.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/contracts .opencode/skills/contracts && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "contracts" agent skill from https://github.com/samchon/nestia/tree/master/.agents/skills/contracts into .opencode/skills/contracts/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "contracts", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
contracts- GitHub stars
- 2.2k
- Token cost
- ~1.3k tokens
- SKILL.md length
- 591 words
- Files
- 6
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Defines self-acknowledgments for production declarations and tests.
- Reviewing maintained source
- SKILL.md covers Common Implementation Principles, OS-Neutral Implementation, Performance and Testing, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Selecting Evidence checklists
What it does
Contracts is an agent skill from samchon/nestia. Defines self-acknowledgments for production declarations and tests. Use when implementing or reviewing maintained source, unit tests or E2E tests, or selecting Evidence checklists.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `common.md`, `e2e.md` and `performance.md`).
It sits in Testing & QA, covering End-to-end testing and Unit testing. The repository describes itself as: NestJS Helper + AI Chatbot Development. The licence is MIT.
When your agent uses it
- Reviewing maintained source
- Selecting Evidence checklists
Example prompts
- “Use the contracts skill to define self-acknowledgments for production declarations and tests”
- “/contracts”
What it can do on your machine
Read from SKILL.md and the folder at commit d3627e8. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Contracts loads about 1.3k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 591 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from samchon/nestia at commit d3627e8, republished under its MIT licence (© samchon). 591 words, ~1,277 tokens.
Download SKILL.mdSave it as
.claude/skills/contracts/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- contracts
- description
- Defines self-acknowledgments for production declarations and tests. Use when implementing or reviewing maintained source, unit tests or E2E tests, or selecting Evidence checklists.
Implementation Contracts
For production declarations, read common.md and only the scoped topic whose design decisions the declaration owns. Select scoped questions by the operation's responsibility, not membership in a package. For every test, read testing.md; for E2E tests, also read e2e.md. Apply production contracts to maintained helpers when their implementation owns those decisions.
Select types and functions; fields keep native documentation and are covered by their type. Include private helpers in the review of their owning operation so delegation does not hide an implementation decision.
An acknowledgment explains why the approach is appropriate, the assumptions it relies on and any unresolved departure. Production acknowledgments do not enumerate regression cases; test acknowledgments identify the cases and assertions they own. Neither certifies outputs or claims tests passed. State an actual limitation rather than declaring compliance with a requirement the implementation does not meet.
Meet all applicable requirements together. No chapter permits weakening the supported behavior to satisfy another.
Benchmarks, test runs and formal proofs are not universal acknowledgment requirements. The answer supplies grounds for review, not a verification report.
Product behavior belongs to project and package documentation. Development owns test procedures and Evidence adoption owns selection and validation. Evidence checks that answers exist; review checks their truth. Neither replaces behavioral verification.
Keep document links in this entry file. Checklist documents must contain no links, so each checklist remains independently readable.
Apply the documentation skill when writing contract prose and related repository documentation.
Give each requirement one chapter owner. A declaration may answer several chapters about the same implementation, but each answer must address its own question without requesting the other answers again. Maintain these boundaries when revising the checklists:
| Chapter | Question owned |
|---|---|
| Principled Implementation | Why does the method or value representation establish the required meaning under its stated premises? |
| Clear and Simple Design | Why are the responsibilities and structural elements clear and necessary for current requirements? |
| Prohibited Implementation Shortcuts | Does the implementation rely on a forbidden substitution or a compensation for a disproven assumption? |
| Meaningful documentation | What useful information is written for users and maintainers, and does that writing follow the documentation guidance? |
| OS-neutral implementation | How are native platform differences represented at the filesystem or process boundary? |
| Efficient algorithms | What does one necessary computation cost as its input grows? |
| Reuse equivalent work | Which requests can share a computation, and what establishes continued validity of its result? |
| Bound retention and release resources | Who owns retained state and handles, how does their population grow, and when are they released? |
| Behavioral verification | Which actual behavior and defect do the test's assertions distinguish? |
| Independent expectations | What establishes the expected result independently of the implementation under test? |
| Distinguishing cases | Which positive, negative and boundary distinctions does this test own? |
| Execution ownership | Which layer and discoverable entry execute these cases? |
| Necessary boundary | Which real connection requires E2E execution and what unique defect does it detect? |
| Shared execution | Which expensive preparations can the surviving E2E cases share? |
| State isolation and reuse validity | Which identities, resets and resource lifetimes make shared test execution valid? |
| Preserved coverage | Where does every meaningful assertion execute after consolidation or transfer? |
Show full SKILL.md (75 more words)Show less
Common Implementation Principles
Principled implementation and its justification, clear and simple design, prohibited shortcuts and useful documentation that follows the documentation skill.
OS-Neutral Implementation
Platform assumptions and supported abstractions at native filesystem and process boundaries.
Performance
Separate questions for algorithmic efficiency, required computation reuse and resource lifetime.
Testing
Behavioral assertions, independent expectations, distinguishing cases and execution ownership for every test.
E2E
Necessary real boundaries, shared preparation, valid isolation and preserved assertions when consolidating E2E cases.
© samchon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files in .agents/skills/contracts of samchon/nestia.
- SKILL.md
- common.md
- e2e.md
- performance.md
- portability.md
- testing.md
Open the folder on GitHubat commit d3627e8
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders. This page covers the copy in samchon/nestia, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Contracts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Contracts this skillsamchon/nestia | 2.2k | — | ~1.3k | Automated safety check: Pass | MIT | |
| TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph | 112 | 11 repos | ~2.4k | Automated safety check: Pass | None | |
| Add Acceptance Testtalkincode/toughradius | 691 | — | ~827 | Automated safety check: Pass | MIT | |
| Atdd Mutateswingerman/engineer | 154 | — | ~2.7k | Automated safety check: Pass | MIT | |
| E2E Scenario Testingobra/dotfiles | 116 | — | ~1.8k | Automated safety check: Pass | None | |
| TDD Workflowaffaan-m/ECC | 274k | 2 repos | ~2k | Automated safety check: Pass | MIT |
Similar skills
Add Acceptance Test
talkincode/toughradius
Write CI-executable acceptance/integration tests for protocol or end-to-end changes (TR-F022).
Atdd Mutate
swingerman/engineer
A skill your agent uses to add a third validation layer to the ATDD workflow — after acceptance tests verify WHAT and unit tests verify HOW, mutation testing verifies the tests actually catch bugs.
E2E Scenario Testing
obra/dotfiles
A skill your agent uses when verifying a running application end-to-end through its real interface — a web UI, a CLI, or a TUI — by writing and executing agent-run "scenario cards" against a freshly…
TDD Workflow
affaan-m/ECC
新機能の作成、バグ修正、コードのリファクタリング時にこのスキルを使用します。ユニット、統合、E2Eテストを含む80%以上のカバレッジでテスト駆動開発を強制します。
TDD Workflow
affaan-m/ECC
새 기능 작성, 버그 수정 또는 코드 리팩터링 시 이 스킬을 사용하세요. An agent skill from affaan-m/ECC.
More from samchon/nestia
All 10 skills in this repoProject
samchon/nestia
Defines the nestia product contract, workspace layout, package boundaries, the Go plugin composition model, and canonical commands.
Issue Campaign
samchon/nestia
Defines the default solo repository-wide issue campaign for nestia: exhaustive discovery, lead-vetted issue publication, one unified CI-validated implementation pull request per cycle, solo…
Pull Request
samchon/nestia
Defines nestia branch, commit, pull-request, check, and merge workflows.
Review
samchon/nestia
Defines exhaustive solo review, Self-Review, and solo repository-wide issue-discovery rounds for nestia.
Development
samchon/nestia
Defines nestia implementation rules, testing standards, validation, consequence analysis, and change integrity.
Discussion
samchon/nestia
Runs structured multi-agent discussions for open-ended nestia topics.
Related
Categories
Questions about Contracts
What does Contracts do?
Defines self-acknowledgments for production declarations and tests. Contracts is an agent skill from samchon/nestia. Defines self-acknowledgments for production declarations and tests.
When should I use Contracts?
Contracts fits situations like: reviewing maintained source; selecting Evidence checklists.
How do I install Contracts in Claude Code?
Run `npx skills add samchon/nestia --skill contracts -a claude-code`. Or copy the skill folder (.agents/skills/contracts in samchon/nestia) into .claude/skills/contracts in your project. Claude Code loads it when a task matches its description.
How do I install Contracts in Codex?
Run `npx skills add samchon/nestia --skill contracts -a codex`. Or copy the skill folder (.agents/skills/contracts in samchon/nestia) into .agents/skills/contracts in your project. Codex loads it when a task matches its description.
Can I use Contracts in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add samchon/nestia --skill contracts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/contracts, .gemini/skills/contracts, .github/skills/contracts and .opencode/skills/contracts in your project.
What does Contracts need to run?
SKILL.md names no scripts, command-line tools or credentials: Contracts is instructions for the agent only.
Does Contracts access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Contracts safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Contracts use?
Contracts is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Contracts use?
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Contracts?
Skills that share tags, products or a category with Contracts: TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars), Add Acceptance Test (talkincode/toughradius, 691 stars), Atdd Mutate (swingerman/engineer, 154 stars) and E2E Scenario Testing (obra/dotfiles, 116 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Contracts?
samchon (a GitHub user) maintains it in samchon/nestia, which has 2,179 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.
Source: samchon/nestia on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.