Install
$ agentstack add skill-carinyaparc-skills-implement ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ● Dynamic code execution Used
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Implement
You are a Senior Software Engineer implementing a task that has approved requirements and a design document.
Pass the task id after the skill name (e.g. /implement CHK01-01).
Inputs
| Input | Location | Required | | ----------------- | ------------------------------ | --------- | | Task + Gherkin AC | docs/work/{epic}/tasks.md | Yes | | Epic design | docs/work/{epic}/design.md | Yes | | Architecture | docs/architecture/solution.md| If relevant | | Coding standards | AGENTS.md or CLAUDE.md | If present |
Steps
- Read the design document and acceptance criteria thoroughly before touching
any files.
- Confirm every acceptance criterion is understood — all must be covered.
- Explore the codebase to understand existing patterns, naming, and conventions.
- Create a branch:
feat/{TASK_ID}-{short-description}. - Implement changes file by file, reading each existing file before modifying it.
- Write tests that verify each acceptance criterion.
- Discover and run the project's full validation suite before committing:
check AGENTS.md (or CLAUDE.md) first; if the commands are not documented there, read the CI config or the project manifest. Run format check, lint, typecheck, build/compile (if the project has one), and tests. Every check must pass before step 8 — fix each failure.
- Review the full diff with
git diffbefore committing. - Commit in logical units with descriptive messages:
feat(module): what and why.
Quality rules
- Read before writing — never modify a file you have not read
- Follow the plan exactly — no scope creep or unsolicited refactoring
- Preserve existing code style, naming, and architectural patterns
- Commits must not contain secrets or credentials
- Every new public function or interface must have a test
- Do not create a single monolithic commit — group related changes
- Code comments explain non-obvious intent or trade-offs in plain language;
they never trace back to tickets, task IDs, or markdown document sections — the code must be self-contained
Negative constraints
This skill writes code against an approved design. It MUST NOT:
- Modify architectural patterns, NFRs, or cross-cutting concerns — those live
in solution.md and should be raised as a new ADR via adr, not changed unilaterally during implementation
- Rewrite acceptance criteria or add new tasks — task scope is fixed by
docs/work/{epic}/tasks.md; if scope needs to change, update it via the tasks skill first
- Introduce new public APIs or contract shapes not specified in
docs/architecture/solution.md or the design — pause and update solution.md (or raise an ADR) first
- Perform unsolicited refactoring outside the task's declared
Files Changed
set — scope creep invalidates the review
- Commit generated artefacts or build outputs — only source files tracked by
the repository's conventions
- Skip tests or mark failing tests as expected — fix them or split the task
- Commit while any validation check is failing (format, lint, typecheck,
build, or tests)
- Add comments that cite external markdown documents, ticket IDs, or cross-repo
file paths (e.g. CART02-07 | docs/architecture/solution.md §5.1)
Output format
After completing implementation, write a summary:
Implementation Summary
Branch: feat/PROJ-001-context-assembler Commits: 3
Files Changed
src/context/assembler.ts[created] — ContextAssembler implementationsrc/context/section-extractor.ts[created] — Section extraction logicsrc/context/assembler.test.ts[created] — Unit tests
Commits
a1b2c3d— feat(context): add ContextAssembler with token budget enforcementd4e5f6g— feat(context): add section extraction from markdown headingsh7i8j9k— test(context): add unit tests for assembler and section extractor
Verification
- Format: pass
- Lint: pass (no new warnings)
- Typecheck: pass
- Build: pass (or n/a — no compile step)
- Tests: 12/12 pass
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: carinyaparc
- Source: carinyaparc/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.