Instructions file CodexOpenCode
Instructions for selftune-dev/selftune, covering agents.md, repository overview, vendored effect reference, agent-first architecture and project structure.
16 2d ago A 3,409 tokens
original MIT
Instructions file
Instructions for selftune-dev/selftune, a project described as: Skill observability & self-improving toolkit for agent skills.
16 2d ago A 9 tokens
original MIT
selftune
03Skill Claude CodeCodex
Self-improving skills toolkit that watches real agent sessions, detects missed triggers, grades execution quality, and improves skill packages through evals, replay, baselines, review, and post-deploy watch. Use when verifying or publishing a skill, improving instructions or routing, checking skill health, grading…
16 2d ago A 138 tokens
original MIT
Agent
Use when a specific skill has recurring low grades, warning or critical status, regressions, or unclear failures after basic doctor/status review. Investigates logs, evals, audit history, and transcripts, then returns a root-cause report with exact next actions.
16 2d ago A 58 tokens
original MIT
Agent
Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.
16 2d ago A 26 tokens
original MIT
Agent
Use when reviewing a dry-run or pending evolution proposal before deployment, especially for high-stakes skills, marginal improvements, or recent regressions. Compares old vs new content, checks evidence quality, and returns an approve or reject verdict with conditions.
16 2d ago A 54 tokens
original MIT
Agent
Use when setting up selftune in a complex repo: monorepo, multi-skill workspace, mixed agent platforms, unclear hook state, or install problems that basic init/doctor does not resolve. Detects project structure, validates configuration, and returns or applies a verified setup plan.
16 2d ago A 61 tokens
original MIT
Agent
Use when multiple skills may overlap, misroute, or interfere with each other, or when composability results suggest moderate or severe conflict. Analyzes trigger ownership, query overlap, and cross-skill health, then returns a conflict matrix and routing recommendations.
16 2d ago A 56 tokens
original MIT
seo-audit
09Skill Claude CodeCodex
When the user wants help with SEO on their website.
16 2d ago A 15 tokens
original MIT
seo-audit
10Skill Claude CodeCodex
--- name: seo-audit description: > When the user wants to audit, review, or diagnose SEO issues on their site. Also use when they mention SEO audit, technical SEO, traffic drops, lost rankings, indexing problems, crawl errors, page speed, core web vitals, robots.txt, or sitemap issues. metadata: version: 1.1.0 --- #…
16 2d ago A 533 tokens
original MIT
CodeReview
11Skill Claude CodeCodex
Reviews code for quality, security issues, and best practices. Provides structured feedback.
16 2d ago A 19 tokens
original MIT
Deploy
12Skill Claude CodeCodex
Helps deploy applications to production environments with safety checks, rollback support, and monitoring.
16 2d ago A 19 tokens
original MIT
Skill Claude CodeCodex
Facilitates creation of visual content using generative AI models including DALL-E, Midjourney prompts, and Stable Diffusion workflows.
16 2d ago A 32 tokens
original MIT
find-skills
14Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities.
16 2d ago A 46 tokens
original MIT
Skill Claude CodeCodex
Delivers instruction on UI/UX design principles for web applications including layout, typography, color theory, and responsive design.
16 2d ago A 27 tokens
original MIT