ahmadulhoq/agentskel

The skeleton for agentic development — persistent memory, shared standards, and structured workflows for AI coding agents.

13Stars on the repository
61Mods indexed here, across every type
17d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When reading or writing to Jira tickets or Confluence pages via MCP tools. Use before any Jira transition, ticket creation, or Confluence page update to avoid common failure modes.

not rated 13 17d ago A 41 tokens original MIT

code-reviewer

02

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When reviewing a PR, auditing code quality, or validating changes against the project's standards and sacred behaviors.

not rated 13 17d ago A 24 tokens original MIT

codebase-navigator

03

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When searching for code, tracing a bug, or understanding how modules connect. Use before grepping blindly — consult the index first.

not rated 13 17d ago A 31 tokens original MIT

data-model-mapping

04

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When adding, renaming, or removing a field on a data model that has a mapped counterpart elsewhere — an API/DTO, a database/ORM entity, a serializer, or a cross-platform equivalent model (Android/iOS/Backend). Use whenever a model's fields change, before considering the change complete.

not rated 13 17d ago A 67 tokens original MIT

database-migration

05

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When writing, reviewing, or running a database schema migration — adding, dropping, or altering tables, columns, indexes, or constraints — with any migration tool (Alembic, Rails, Prisma, Room, Core Data, Flyway, Liquibase, raw SQL). Use before generating a migration file, or when one appears in a diff/PR.

not rated 13 17d ago A 75 tokens original MIT

developer

06

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When writing, modifying, or reviewing application code. Provides code quality standards, SOLID principles, design philosophy, and platform-specific implementation guidance.

not rated 13 17d ago A 30 tokens original MIT

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When a design discussion or evaluation is interrupted by a task or workflow, or when the user says "present the discussion," "where were we," "show me the discussion," or "resume" — save or resurface the discussion state using Session Notes.

not rated 13 17d ago A 56 tokens original MIT

domain-expert

08

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When working on features that require domain knowledge — business rules, terminology, or invariants specific to this project. [Replace this description and the content below with your project's domain.].

not rated 13 17d ago A 39 tokens original MIT

git-flow

09

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

Git branching, commit, and PR procedures. Use when creating branches, making commits, or opening pull requests. Enforces branch naming, commit message format, and PR rules.

not rated 13 17d ago A 38 tokens original MIT

knowledge-routing

10

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When deciding where to store a piece of knowledge (memory files vs Confluence vs Jira). Use when about to document something, capture a lesson, create a ticket, or publish a decision.

not rated 13 17d ago A 41 tokens original MIT

session-start

11

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

Session initialization procedure. Checks memory mount, reads all required memory files, validates skeleton version, checks dependency freshness, and surfaces alerts. Must be executed at the start of every session before any other work.

not rated 13 17d ago A 43 tokens original MIT

skill-authoring

12

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When creating a new skill or workflow, or improving an existing skill's effectiveness. Use when the user asks to add a capability, write a new workflow, or when a skill isn't triggering or being followed reliably.

not rated 13 17d ago A 46 tokens original MIT

subagent-dispatch

13

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When delegating work to a subagent — implementation, review, research, or exploration. Use when a task benefits from a fresh context window, parallel execution, or isolated scope.

not rated 13 17d ago A 41 tokens original MIT

systematic-debugger

14

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When applying debugging techniques during any investigation — root cause tracing, bisect, defense-in-depth. Enforces hypothesis-first analysis and prohibits guess-and-check changes. Use standalone or inside the debug-issue workflow.

not rated 13 17d ago A 46 tokens original MIT

task-completion

15

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

Post-task checklist for CHANGELOG, TIMELOG, SYMBOLS/MAP, RESUME, and memory commits. Execute after completing a task that modified files outside .memory/. Do NOT run for pure discussion, memory-only maintenance, or skeleton syncs.

not rated 13 17d ago A 55 tokens original MIT

task-planner

16

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When decomposing a feature or spec into implementable subtasks, estimating scope, or orchestrating multi-step work across subagents.

not rated 13 17d ago A 30 tokens original MIT

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When implementing logic changes during develop-feature or implement-task. Use the Red-Green-Refactor cycle to write a failing test before any production code.

not rated 13 17d ago A 34 tokens original MIT

test-engineer

18

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When designing test strategy, analysing coverage, or writing tests outside the TDD cycle. Also use when working with CI pipelines or validating changes end-to-end.

not rated 13 17d ago A 35 tokens original MIT

using-git-worktrees

19

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When running long feature implementations, parallel branch work, or build/test scripts that must not interfere with the user's active working directory. Creates isolated execution environments via git worktrees in sibling directories.

not rated 13 17d ago A 43 tokens original MIT

add-team-member

20

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When a single new person joins the team. Use when .memory/TEAM.md already exists and you need to append one member (with roles, optional module assignments, and optional Jira account ID) without touching the rest of the roster.

not rated 13 17d ago A 48 tokens original MIT

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When adding a new platform (subdir with its own git repo) to an existing workspace dispatcher. Runs setup-skeleton in the subdir and updates the workspace config and dispatcher AGENTS.md.

not rated 13 17d ago A 39 tokens original MIT

brainstorm-feature

22

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When the user wants to think through a feature idea, explore edge cases, or produce a technical spec before implementation. Use before develop-feature to prevent mid-implementation surprises.

not rated 13 17d ago A 34 tokens original MIT

cartographer

23

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When codebase structure has changed, MAP.md/SYMBOLS.md are missing or stale, or after major refactors and initial setup. Also run when a new module is added or files are moved between modules.

not rated 13 17d ago A 43 tokens original MIT

check-dependencies

24

ahmadulhoq/agentskel

Skill Claude CodeCodex

Part of agentskel

When dependency versions need auditing, Last Dependency Check in CONFIG.md is overdue (14-day cadence), or before starting security-sensitive work.

not rated 13 17d ago A 26 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: