Dependency audit across the service repositories.
Skills in this repository
stbenjam/skillsaw - Page 2
SkillsMP has collected 173 skills from stbenjam/skillsaw. Open a skill to review its source and details.
stbenjam/skillsawShowing 40 of 173 collected skills.
Deployment helper for the payments service.
Access grants for production systems.
Onboards a new service onto the platform.
Latency profiling for a single HTTP endpoint.
Provisions a short-lived preview environment.
Runbook authoring and publication.
Point-in-time restore for the primary datastore.
Reviews database migrations before they merge.
Rotates the database and message-broker credentials.
Capacity changes for the shared Kubernetes clusters.
Pager triage for the platform team.
Alert threshold tuning for noisy services.
Backup restore verification for stateful services.
Postmortem authoring for production incidents.
Review the current changes before they are committed. Use when asked to review a diff.
Solve competition mathematics problems with rigorous proofs. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', or 'find all functions satisfying'.
Enforces the accessibility checklist for user-facing components. Applies when touching anything under src/components/ or adding a new page.
Formats and validates Terraform modules. Claude should use this skill whenever editing .tf files or reviewing an infrastructure change.
Runs the repository's database migrations safely. Load this skill whenever a change touches a file under migrations/ or alters a SQLAlchemy model.
Reference for the Claude API and Anthropic SDK — model ids, pricing, parameters, streaming, tool use. TRIGGER — read BEFORE opening the target file whenever the prompt names Claude or Anthropic in any form, or the task is LLM-shaped with the provider…
Requests the right reviewers and posts the checklist comment. Use after opening a pull request against the main branch.
Demonstrate how informational lint findings are handled during autofix. Use when testing severity-based fix selection.
Guides the {{SKILL_ID}} workflow. Use when the user needs {{SKILL_ID}} task support; customize this description with concrete triggers and outcomes.
Use when checking compatibility with legacy Windsurf conventions.
Use when testing an autofixable external APM skill.
Use when testing an externally installed dependency.
Use when testing a copy sourced from this repository.
Use when testing an unlocked skill authored in this repository.
Use when providing the repository-owned source for a local lock entry.
Run a portable workflow. Use when an Agent Skills host must complete the task.
Build stateful web artifacts. Use for complex applications requiring routing or component libraries.
Apply the official brand system to an artifact. Use it when colors, typography, or visual standards apply.
Use when reviewing a skillsaw PR. Dispatches 7 specialist reviewers (Architecture, Python Expert, Security & Supply Chain, QA Engineer, Technical Writer, Ecosystem, Slopinator) as parallel sub-agents by default, then synthesizes a single verdict. Use --serial…
Use when skillsaw reports a likely false positive, misses an edge case, behaves incorrectly, or needs an RFE. Gather a safe report and, only with explicit user permission, create a feedback bundle or open a GitHub issue.
Streamline service deployments with guided rollout, rollback, and environment bootstrap steps.
Assemble release notes for a billing-api tag from merged pull requests. Use when cutting a release or when asked what shipped in a version.
Triage incoming Jira tickets for the acme-platform board — classify, label, and assign. Use when the sprint backlog has unclassified issues.
Create a skillsaw rule plugin — a pip-installable Python package that adds custom lint rules to skillsaw. Walks through scaffolding the package, writing rules against the lint tree, testing, and publishing to PyPI. Use when a user wants to share skillsaw…
Walk through the release checklist before a production deploy, confirming test results, change approvals, rollback readiness, and on-call awareness. Use when the user asks to prepare, review, or verify a deploy.