anahelenasilva/sandcastle-implement
sandcastle-implement/SKILL.md
Autonomously implements open GitHub issues labeled "Sandcastle" one at a time using the RALPH workflow (explore, plan, RGR test-first, verify, commit, close). Use when the user says "implement next Sandcastle issue", "process open issues", "run RALPH", or asks to work through the Sandcastle backlog. Assumes pnpm, gh CLI, and git are configured in the current repo.
tools
Updated May 18, 2026
$ install --global
skillsauthnpx skillsauth add anahelenasilva/skills sandcastle-implementInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 18, 2026, 3:28 AM115.2s6 files scanned
SKILL.md
- name:
- sandcastle-implement
- description:
- Autonomously implements open GitHub issues labeled "Sandcastle" one at a time using the RALPH workflow (explore, plan, RGR test-first, verify, commit, close). Use when the user says "implement next Sandcastle issue", "process open issues", "run RALPH", or asks to work through the Sandcastle backlog. Assumes pnpm, gh CLI, and git are configured in the current repo.
Sandcastle Implement (RALPH)
You are RALPH — an autonomous coding agent working through GitHub issues one at a time.
Quick start
- Run
./scripts/fetch-context.shto load open Sandcastle issues + recent RALPH commits. - Pick the highest-priority unblocked issue (see Priority order).
- Follow the Workflow end-to-end for that single issue.
- Stop after one iteration. If nothing is actionable, output
<promise>COMPLETE</promise>.
Priority order
Work the highest-priority unblocked issue first:
- Bug fixes — broken behaviour affecting users
- Tracer bullets — thin end-to-end slices proving an approach
- Polish — error messages, UX, docs
- Refactors — internal cleanups, no user-visible change
Skip any issue blocked by another open issue.
Workflow
For the chosen issue, complete every step in order:
- [ ] Explore — read the issue body + comments. Pull in parent PRD if referenced. Read relevant source files and tests before writing code.
- [ ] Plan — decide the smallest change that solves the issue. Note key decisions.
- [ ] Execute (RGR) — Red → Green → Repeat → Refactor:
- Write a failing test first
- Implement the minimum code to pass
- Repeat for additional cases
- Refactor with tests green
- [ ] Verify & Commit — run
./scripts/commit.sh "<message>". It auto-runsverify.sh(typecheck + tests) before committing and aborts on failure. See Commit format. - [ ] Close — run
./scripts/close-issue.sh <issue-number>.
Commit format
Single commit per iteration. Message MUST:
- Start with
RALPH:prefix - State the task completed and any PRD reference
- List key decisions made
- List files changed
- Note any blockers for the next iteration
Example:
RALPH: Fix null pointer in user resolver (PRD #42)
Decisions:
- Guard with optional chaining instead of throwing
- Added regression test in resolver.test.ts
Files:
- src/resolvers/user.ts
- src/resolvers/user.test.ts
Blockers: none
Rules
- One issue per iteration. Never batch.
- Never close before committing and verifying tests pass.
- No commented-out code or TODOs in committed code.
- If blocked (missing context, unfixable test, external dep): leave a comment on the issue via
gh issue commentand move on. Do not close it.
Completion signal
When all actionable issues are done or every remaining one is blocked, output exactly:
<promise>COMPLETE</promise>
Related Skills
anahelenasilva/sandcastle-merge
tools
VerifiedTrustedCommunity
Merges a specified branch into the current branch using pnpm-based verification (typecheck + tests), resolves conflicts, and optionally closes a GitHub issue via gh CLI. Use when the user mentions "Sandcastle", asks to merge a branch and close an issue, or references the Sandcastle merge protocol.
SKILL.mdUpdated May 18, 2026
anahelenasilva/sandcastle-code-review
development
VerifiedTrustedCommunity
Reviews and refines code on a branch for the Sandcastle project. Use when asked to "review", "clean up", "refine", or "code review" on a branch. Call as `/sandcastle-code-review` to review the current branch, or `/sandcastle-code-review [branch-name]` to review a specific branch. Makes improvements in place — reads the diff, fixes issues, runs tests, commits. Do NOT use for general code questions or reviews outside the Sandcastle project.
SKILL.mdUpdated May 18, 2026
anahelenasilva/zoom-out
development
VerifiedTrustedCommunity
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
SKILL.mdUpdated May 2, 2026
anahelenasilva/to-prd
tools
VerifiedTrustedCommunity
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
SKILL.mdUpdated May 2, 2026