Updated 5mo ago
by Sounder25
Foundational-Agent-Skills
Operational capabilities for high-leverage AI coding agents. Features deterministic execution, 100% tested safety gates, impasse detection, and adversarial review. Includes 'Gold Standard' meta-skills like Pre-Action Guard and Failure Postmortem to prevent loops and data loss.
29 GitHub stars (29)
+1 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | +1 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 24 skills (24 skills found in its SKILL.md files)
- 7 forks (7 forks)
- 5mo ago last update (Last updated 5mo ago)
Install
Skills CLI
npx skills add Sounder25/Foundational-Agent-Skills
Asks which skills and agents to install. Just one: npx skills add Sounder25/Foundational-Agent-Skills --skill 'Workspace Forensics Audit' — add -g for every project.
Claude Code
git clone https://github.com/Sounder25/Foundational-Agent-Skillscp -r "Foundational-Agent-Skills/00_workspace_forensics" ~/.claude/skills/
Copies the Workspace Forensics Audit skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Sounder25/Foundational-Agent-Skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
Workspace Forensics Audit
Generate comprehensive workspace profile with git signals, build configs, and forensics completeness tracking. Foundation skill for all other workspace operations.
00_workspace_forensics/skill.md on GitHub (opens in a new tab) -
Run EELS Test Suite
Automates running the Ethereum Execution Layer Specification (EELS) tests against a local EVM implementation. Handles venv setup, execution, and result parsing.
01_run_eels_tests/SKILL.md on GitHub (opens in a new tab) -
Project-Wide Rename
Safely renames a .NET project (solution, projects, namespaces, directories) from one name to another. Supports Planned (clean) and Recovery (dirty) modes.
02_project_rename/SKILL.md on GitHub (opens in a new tab) -
Sync Multi-Repo State
Detects drift between multiple git repositories (e.g. forks, mirrors, or multi-module projects). Generates a drift report and optionally applies sync actions.
03_sync_repos/SKILL.md on GitHub (opens in a new tab) -
Clean Build Artifacts
Removes ignored build artifacts (bin, obj, node_modules) to reclaim space and fix ghost build errors. Safely respects .gitignore.
04_clean_artifacts/SKILL.md on GitHub (opens in a new tab) -
Update Intent Breadcrumbs
Updates standardized intent files (NEXT.md, STATE.json) to maintain context across agent sessions.
05_update_breadcrumbs/SKILL.md on GitHub (opens in a new tab) -
Error-State Recovery
Wraps command execution in a self-healing loop. Uses heuristics to auto-fix common errors (missing deps, locked files) or escalates to the Agent with structured error context.
06_error_recovery/SKILL.md on GitHub (opens in a new tab) -
Deterministic Planner
Enforces a structural planning phase before execution. Generates and validates PLAN.json to ensure every task has a clear objective, steps, verification method, and rollback strategy.
07_deterministic_planner/SKILL.md on GitHub (opens in a new tab) -
Context Window Pruner
Optimize information density by filtering workspace files based on relevance to the current task. Excludes high-noise files (lockfiles, assets) and prioritizes source code matching semantic queries.
08_context_pruner/SKILL.md on GitHub (opens in a new tab) -
Agent-Swarm Spawner
Prepares isolated sub-workspaces for parallel agent execution. Copies context and generates specific mission instructions for "Worker" agents.
09_multi_agent_delegation/SKILL.md on GitHub (opens in a new tab) -
Async Feedback Loop
Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
10_async_feedback/SKILL.md on GitHub (opens in a new tab) -
llms.txt & Doc Parsing
Rapidly ingest documentation via the /llms.txt standard to gain "fast-track" understanding of libraries without scraping entire sites.
11_llmstxt_doc_parsing/SKILL.md on GitHub (opens in a new tab) -
Dependency Tree Mapping
Generate comprehensive dependency graphs to identify "single-points-of-failure" and impact analysis chains.
12_dependency_tree_mapping/SKILL.md on GitHub (opens in a new tab) -
Environment-Specific Bash Mastery
Generate optimized scripts that utilize the specific hardware (cores, GPU, OS) of the execution environment.
13_env_bash_mastery/SKILL.md on GitHub (opens in a new tab) -
Detect Duplicate Files
Identify duplicate files across the workspace using SHA256 hashing to reduce redundancy and confusion.
14_detect_duplicate_files/SKILL.md on GitHub (opens in a new tab) -
Generate .gitignore
Create or update .gitignore files by fetching standard templates from the GitHub/gitignore repository.
15_generate_gitignore/SKILL.md on GitHub (opens in a new tab) -
MCP Connector
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
16_mcp_connector/SKILL.md on GitHub (opens in a new tab) -
Impasse Detector
Detects when the agent is stuck in a reasoning loop or unproductive state by analyzing tool usage and sentiment patterns.
17_impasse_detector/SKILL.md on GitHub (opens in a new tab) -
Pre-Action Guard
A QA gate that validates potentially destructive or irreversible actions before execution.
18_pre_action_guard/SKILL.md on GitHub (opens in a new tab) -
Adversarial Reviewer
Generates a 'Red Team' critique of recent code or plans to identify weak assumptions and edge cases.
19_adversarial_reviewer/SKILL.md on GitHub (opens in a new tab) -
Failure Postmortem
Structured logging and analysis of execution failures to prevent recurrence.
20_failure_postmortem/SKILL.md on GitHub (opens in a new tab) -
Skill Gap Identifier
Analyzes failures or user requests to automatically scaffold new skills, ensuring structural evolution.
21_skill_gap_identifier/SKILL.md on GitHub (opens in a new tab) -
State Overlay Consistency Checker
Detect and prevent state-visibility violations across execution contexts within a single transaction.
22_state_overlay_consistency/SKILL.md on GitHub (opens in a new tab) -
Paste Sanitizer
Convert mixed terminal output and instructions into safe, paste-ready command blocks.
23_paste_sanitizer/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills