github.com/BigSimmo/PsychSift
| Skill | Added | Review |
|---|---|---|
prlanded .claude/skills/prlanded/SKILL.md Verify a merged PR actually landed correctly in this repo and clean up after it. Use right after a PR merges (especially with auto-merge) to confirm the merge commit, or for older PRs the squashed commit, matches your branch by content, catch late commits that were orphaned by the auto-merge race, and post its review record and update memory. | 72 Impact — No eval scenarios have been run Securityby Medium Suggest reviewing before use Version: 0d5a97a | |
prompt .claude/cloud-profile/skills/prompt/SKILL.md Perfect a rough request or draft prompt using relevant context, attachments, files, and the minimum necessary skills or tools, then answer or execute it. Use when the user invokes $prompt or asks to improve, rewrite, sharpen, expand, contextualize, or optimize their prompt before acting. For code-changing prompts, verify task ownership and use an isolated checkout when needed; preserve verified same-task continuation. Do not use for ordinary code or content review unless prompt improvement is requested. | 66 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 0d5a97a | |
prompt-perfector .agents/skills/prompt-perfector/SKILL.md Refine or evaluate prompts, preserving intent, output controls and authority. Use for prompt refinement or assessment. | 68 Impact — No eval scenarios have been run Securityby Medium Suggest reviewing before use Version: 0d5a97a | |
prompt .claude/skills/prompt/SKILL.md Perfect a rough request or draft prompt using relevant context, attachments, files, and the minimum necessary skills or tools, then answer or execute it. Use when the user invokes $prompt or asks to improve, rewrite, sharpen, expand, contextualize, or optimize their prompt before acting. For code-changing prompts, verify task ownership and use an isolated checkout when needed; preserve verified same-task continuation. Do not use for ordinary code or content review unless prompt improvement is requested. | 68 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 0d5a97a | |
rag .agents/skills/rag/SKILL.md Validate PsychSift retrieval, classification, ranking, grounding, citations, and answer behavior offline before preparing any live evaluation approval gate. Use for RAG changes, golden regressions, search quality, or answer-quality work. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
rag-change-lab .agents/skills/rag-change-lab/SKILL.md Compatibility alias for the rag skill. Use only when the user explicitly invokes the older rag-change-lab name; otherwise use rag for offline-first retrieval and answer validation. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
rag-cloud-sdd .agents/skills/rag-cloud-sdd/SKILL.md Execute one RAG Cloud phase with fresh agents, adaptive effort, immutable review ranges, and fail-closed routing. | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
recovery .agents/skills/recovery/SKILL.md Plan PsychSift restore, rollback, queue recovery, reconciliation, backup validation, and disaster-recovery proof without modifying live systems automatically. Use for failed jobs, corrupted state, rollback planning, or continuity exercises. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
reindex .agents/skills/reindex/SKILL.md Plan and verify PsychSift index generations, backfills, promotions, cleanup, health checks, and rollback without touching live data automatically. Use for reindex jobs, generation changes, index migrations, or backfill operations. | 67 Impact — No eval scenarios have been run Securityby Medium Suggest reviewing before use Version: 0d5a97a | |
release .agents/skills/release/SKILL.md Assemble PsychSift release-readiness evidence, risk-scoped local checks, governance proof, rollback notes, and approval-gated final verification. Use for release, merge readiness, production handoff, or go-live confidence. | 67 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 0d5a97a | |
release-readiness-review .cursor/skills/release-readiness-review/SKILL.md Reviews build validation, linting/type-checking, target database checks, clinical governance preflight approvals, and environment variables. Use before staging or production releases. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
repo-auditor .cursor/skills/repo-auditor/SKILL.md Reviews module dependencies, broken imports, dead files, and structural cleanup as triage — never an automatic delete list. Use during repo-wide audits or refactoring. | 71 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 0d5a97a | |
research .claude/cloud-profile/skills/research/SKILL.md Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
review .agents/skills/review/SKILL.md Review the current PsychSift diff, branch, or explicitly approved PR target for high-confidence correctness, security, privacy, clinical, and reliability defects. Use for code review, diff review, or readiness feedback. | 69 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 0d5a97a | |
review .claude/cloud-profile/skills/review/SKILL.md Use when applies to product pages, local business pages, recipes, apps, books, and any page that aggregates user reviews. Use when auditing rich result eligibility for e-commerce or review sites. | 55 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
run .agents/skills/run/SKILL.md Start or verify the correct local PsychSift application with repository identity checks and return its actual URL. Use when the user says run, asks for the local app, or needs browser work against this project. | 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
run-pr .claude/skills/run-pr/SKILL.md Run the automated open-PR maintenance sweep on bigsimmo/psychsift — fix failing CI on every open PR, address and resolve review threads, merge origin/main into branches with a real conflict, and push fixes. Use when the user types "Run PR" as the task message, or asks to sweep/fix/maintain all open PRs. "Run PR" is standing authorization for GitHub reads, pushes to PR feature branches, thread replies/resolutions, and CI re-runs; it never authorizes merging into main, closing PRs, force-pushes, branch deletion, auto-merge, or provider-backed gates. | 72 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 0d5a97a | |
sarif-parsing .claude/cloud-profile/skills/sarif-parsing/SKILL.md Parse, analyze, and process SARIF (Static Analysis Results Interchange Format) files. Use when reading security scan results, aggregating findings from multiple tools, deduplicating alerts, extracting specific vulnerabilities, or integrating SARIF data into CI/CD pipelines. | 61 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 0d5a97a | |
security .agents/skills/security/SKILL.md Find and validate concrete PsychSift security risks across secrets, input handling, authentication, authorization, storage, dependencies, and trust boundaries. Use for security review, threat analysis, or confirmed finding remediation. | 71 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 0d5a97a | |
security-best-practices .claude/cloud-profile/skills/security-best-practices/SKILL.md Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks. | 80 1.18x Impact 97% 1.18xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 0d5a97a |