Adit-Jain-srm

23 mods across 1 repository, 2 stars between them.

skill-forge

02

Adit-Jain-srm/skill-forge

Plugin Claude Code

Self-improving intelligence amplifier: 16 behavioral skills + autonomous discovery + TF-IDF routing + SkillOpt self-improvement loop. Use for systematic debugging, code review, project orchestration, architecture decisions, error resilience, and web performance.

2 2mo ago A tokens not measured original MIT

Adit-Jain-srm/skill-forge

Instructions file CodexOpenCode

Instructions for Adit-Jain-srm/skill-forge, covering agents.md — skill-forge, instructions, for ai agents using this repo, available skills and automation scripts.

2 2mo ago A 1,011 tokens original MIT

Adit-Jain-srm/skill-forge

Instructions file

Instructions for Adit-Jain-srm/skill-forge, covering claude.md — skill-forge, identity, key facts, when modifying and reasoning approach.

2 2mo ago A 450 tokens original MIT

skill-forge

05

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Autonomous self-improving intelligence amplifier. Devours skills, knowledge, and novel approaches from across the internet. Serves two objectives: (1) make itself better at devouring, and (2) produce skills that dominate with stars. Use for finding best skills for any project, creating skills, improving capabilities…

2 2mo ago A 115 tokens original MIT

ai-debt-detector

06

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Use after generating code, after accepting AI suggestions, or when reviewing AI-written modules. Also use when code "works" but feels brittle, when error handling seems thin, when you notice orphaned resources or missing cleanup, or when the agent says "done" but you suspect hidden debt. Catches the specific failure…

2 2mo ago A 77 tokens original MIT

arch-from-code

07

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Generate architecture diagrams, dependency maps, and system documentation directly from your codebase. Reads source files, traces dependencies, identifies boundaries, and outputs Mermaid/PlantUML/C4 diagrams. Use when asked to document architecture, visualize dependencies, generate system diagrams, create C4 models…

2 2mo ago A 78 tokens original MIT

context-builder

08

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Generate a CONTEXT.md shared vocabulary for any project. Reduces agent verbosity by 50-75%, improves variable naming, makes conversations more precise. Interviews the user about domain terms, then produces a structured glossary the agent references every session. Use when starting a new project, onboarding to…

2 2mo ago A 105 tokens original MIT

db-schema

09

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Enforce schema discipline: queries-first design, index-every-filter, safe migrations, verify-at-scale thinking. Prevents the common failure of designing schemas for demos that break in production. Use when creating tables, planning migrations, designing data models, or when user mentions database, schema, migration…

2 2mo ago A 68 tokens original MIT

design-mode

10

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Use when making UI/frontend changes in Cursor's Design Mode, when the user selects elements visually, draws annotations, or uses voice commands to describe changes. Also use when editing components from the integrated browser, when multi-selecting elements to match styles, when making iterative visual refinements, or…

2 2mo ago A 81 tokens original MIT

diagnose

11

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Disciplined diagnosis loop for hard bugs and unexpected behavior. Forces reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when something is broken and you don't know why, when a bug seems intermittent, when a fix didn't work, or when user says diagnose, debug, investigate, or "why is this…

2 2mo ago A 71 tokens original MIT

dynamic-workflow

12

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Design and orchestrate Claude Code dynamic workflows — the new multi-agent system that fans out 10-100 subagents in parallel with verification. Teaches when to use workflows vs single-agent, how to structure fan-out/fan-in patterns, and how to build verification gates. Use when tackling complex tasks that benefit from…

2 2mo ago A 113 tokens original MIT

error-resilience

13

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Build resilient systems with proper error handling, retry patterns, circuit breakers, graceful degradation, and timeout management. Use when implementing API calls, database connections, external service integrations, background jobs, or any code that can fail. Also use when the user mentions retry logic, circuit…

2 2mo ago A 82 tokens original MIT

git-workflow

14

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Enforces disciplined git practices on every commit. Small atomic commits, conventional messages, branch hygiene, and PR readiness checks. Changes how the agent HANDLES git — not just what commands it knows. Auto-triggers on any git operation. Use when committing, branching, merging, or preparing PRs. Also use when git…

2 2mo ago A 87 tokens original MIT

grill

15

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Use when about to create a skill, start a feature, design a system, or plan any non-trivial work. Also use when user says grill me, question my plan, challenge this, stress-test, or validate my thinking. Prevents building the wrong thing by resolving decisions before implementation.

2 2mo ago A 62 tokens original MIT

handoff

16

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Compact the current conversation into a handoff document so another agent or future session can continue the work without losing context. Use when ending a session, switching tasks, the context is getting long, or user says handoff, wrap up, save progress, or "continue this later".

2 2mo ago A 59 tokens original MIT

mcp-conductor

17

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Orchestrate multiple MCP servers together for complex multi-step tasks. Teaches agents to chain Exa search → Bright Data scraping → GitHub API → file operations in intelligent workflows. Use when a task requires data from multiple sources, when combining MCP tools for research, when building multi-step automations…

2 2mo ago A 90 tokens original MIT

prove-it

18

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Use when completing any task, fixing bugs, implementing features, or whenever about to claim work is done. Also use when the agent says "fixed", "done", "implemented", "all set", or "should work now" without showing evidence. Auto-triggers before any completion claim.

2 2mo ago A 61 tokens original MIT

self-review

19

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

After every code change, automatically review your own work before presenting it. Catches bugs, style issues, and missed requirements BEFORE the user sees them. Use when implementing features, fixing bugs, refactoring, or any code modification. Auto-triggers on code changes. Reduces back-and-forth by catching issues…

2 2mo ago A 68 tokens original MIT

session-guard

20

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Prevents long-session corruption AND context compaction amnesia. Monitors session health, detects instruction drift, enforces critical-rule recitation, and splits proactively before degradation hits. Use when working on complex multi-step tasks, when a session is getting long, when the agent starts ignoring rules it…

2 2mo ago A 88 tokens original MIT

setup

21

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

One-time setup for skill-forge. Asks user preferences (search sources, creation style, target platforms, GitHub username, skill categories of interest) and configures all other skills to use those preferences. Run once before using any other skill-forge capability. Use when user says setup, configure, or invokes…

2 2mo ago A 68 tokens original MIT

web-perf

22

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Diagnose and fix web performance through a disciplined measure-first loop. Forces evidence-based optimization: measure → identify bottleneck → fix ONE thing → re-measure → repeat. Prevents guessing. Use when pages load slowly, user mentions performance, LCP, INP, CLS, lighthouse, bundle size, or "make it faster".

2 2mo ago A 71 tokens original MIT

zoom-out

23

Adit-Jain-srm/skill-forge

Skill Claude CodeCodex

Force a perspective shift. Stop looking at the code line-by-line and explain the broader context: how this piece fits in the system, what depends on it, what it depends on, and what the original designer was thinking. Use when lost in unfamiliar code, when changes feel risky because you don't see the full picture, or…

2 2mo ago A 94 tokens original MIT