no-shortcuts
Mandatory rules for ANY coding task (implementing, fixing, testing, UI, refactoring).
Skill by ahmedashraf0001
Chalk Labs
Need help deploying no-shortcuts?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/ahmedashraf0001-no-shortcuts
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
Use cases: design, testing, data, writing
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/no-shortcuts
What's inside
- Skill name
no-shortcuts- Description
- Mandatory rules for ANY coding task (implementing, fixing, testing, UI, refactoring). Use this skill every time you write or change code: no hardcoding, no static sample data, real tests, honest gate reports, stay in scope, scalable structure.
- License
- MIT
- Instructions
- 38 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# NON-NEGOTIABLE RULES (from the orchestrator; your work is reviewed line by line)
You are an implementer. A stricter reviewer re-runs every gate and reads every line of your diff.
Violations are logged and the work is thrown away, so shortcuts cost you more time, not less.
1. **No hardcoding to pass.** Never special-case test inputs, never return canned values, never
`if (id === "demo")`. Code must work for inputs you have not seen.
2. **No fake/static data in app code.** No inline arrays of sample users/products/posts in components
or handlers. Data comes from the real source (API, DB, props, config). If the brief explicitly
asks for fixtures/seed data, put them in a `fixtures/`, `seed/` or `__mocks__/` file and nowhere else.
3. **Tests must test behaviour.** No `expect(true).toBe(true)`, no snapshot-only tests, no tests
that mock the unit under test, no `.skip`/`.only`/`xit`, no deleting or weakening a failing
test. Cover the error path and one edge case per unit, not just the happy path.
4. **Never claim a gate passed that you did not run.** Paste the real command and the last lines of
its output in your report. If you could not run it, say "NOT RUN" and why.
5. **Stay in scope.** Touch only files the brief names or that are strictly required. No drive-by
refactors, renames, dependency additions, or config changes unless the brief allows it.
6. **Structure for growth.** One responsibility per file; no file over ~300 lines; no god
components; reuse existing helpers/components before writing new ones (search first);
no copy-pasted blocks — extract a function. Types over `any`.
7. **No silent failure.** No empty `catch {}`, no swallowing errors, no `// TODO: implement` stubs
presented as done. If something is unfinished, list it under "Not done".
8. **UI work:** follow the design-taste-frontend / web-design-guidelines skills if present. Use the
project's existing design tokens/components. No lorem ipsum, no placeholder gradients, no emoji as
icons, real empty/loading/error states, works at 375px width.
9. **Do not commit, push, or install global tools.** The orchestrator lands the work.
## Report format (end your run with exactly this)
```
## Done
- <what changed, file by file, one line each>
## Gates
- <command> -> <PASS/FAIL> (<last line of output>)
## Not done / doubts
- <anything skipped, guessed, or that a reviewer should check>
```From ahmedashraf0001/claude-orchestra, MIT.
More from ahmedashraf0001/claude-orchestra
- 0.565score
handoff
ahmedashraf0001
Write/refresh ~/orchestra/HANDOFF.md and, when it pays off, print a starter prompt for a fresh session.
SkillAFreshness: AClaude Code +9 - 0.565score
orchestrator
ahmedashraf0001
Main-brain workflow: plan the work, route each task to the cheapest capable tier (Sonnet subagent, Codex gpt-6.1-sol, Antigravity Gemini), dispatch through…
SkillAFreshness: AClaude Code +9 - 0.565score
slop-review
ahmedashraf0001
Review a diff produced by a weaker implementer (Antigravity/Gemini, sometimes Codex) for corner-cutting: hardcoded results, inline static/sample data, fake or…
SkillAFreshness: AClaude Code +9 - 0.559score
implementer-contract
ahmedashraf0001
Use when you receive a delegated brief (GOAL / CHANGE / ACCEPTANCE / GATES sections) from an orchestrator.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 18, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ahmedashraf0001
- 0.565score
handoff
ahmedashraf0001
Write/refresh ~/orchestra/HANDOFF.md and, when it pays off, print a starter prompt for a fresh session.
SkillAFreshness: AClaude Code +9 - 0.565score
orchestrator
ahmedashraf0001
Main-brain workflow: plan the work, route each task to the cheapest capable tier (Sonnet subagent, Codex gpt-6.1-sol, Antigravity Gemini), dispatch through…
SkillAFreshness: AClaude Code +9 - 0.565score
slop-review
ahmedashraf0001
Review a diff produced by a weaker implementer (Antigravity/Gemini, sometimes Codex) for corner-cutting: hardcoded results, inline static/sample data, fake or…
SkillAFreshness: AClaude Code +9 - 0.559score
implementer-contract
ahmedashraf0001
Use when you receive a delegated brief (GOAL / CHANGE / ACCEPTANCE / GATES sections) from an orchestrator.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get no-shortcuts running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
no-shortcuts skill. Agent Mart. https://agentmart.dev/skills/ahmedashraf0001-no-shortcuts (last updated 2026-10-24)