rename: awesome_agent_skills -> agent_skills, matches repo naming convention

Every other top-level content folder is snake_case without a 'awesome_'
prefix (starter_ai_agents, advanced_ai_agents, always_on_agents...);
this one now matches. All internal references updated: main README,
category README, both skill READMEs, CI workflow paths, evals tooling.
Git tracked the moves as renames, so per-file history is preserved.

Also:
- Model name corrected: 'Gemini Flash' -> 'Gemini 3.5 Flash' (SKILL.md
  and README table) — it was already correct everywhere else in the
  skill, this was the one straggler
- Main README skills blurb rephrased: 'Browse all skills' folded into
  the intro sentence as a link, agent-count claim softened to 'Claude
  Code, Codex, Cursor, and other coding agents' instead of a number

All four CI-equivalent gates re-verified against the new path: lint
strict (both skills), security scan, trigger & routing, deterministic
evals — all pass.

Known consequence: this changes the install path for project-graveyard,
already merged to main and already installed by at least one user via
the old awesome_agent_skills/ URL. The old npx skills add command stops
resolving once this merges; anyone who has it installed keeps their
local copy (skills CLI doesn't phone home), but the previously-shared
install link needs reposting with the new agent_skills/ path.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.github/workflows/skill-evals.yml

@@ -3,11 +3,11 @@ name: skill-evals
 on:
   pull_request:
     paths:
-      - "awesome_agent_skills/**"
+      - "agent_skills/**"
   push:
     branches: [main]
     paths:
-      - "awesome_agent_skills/**"
+      - "agent_skills/**"
 
 jobs:
   evals:
@@ -26,7 +26,7 @@ jobs:
         run: |
           set -e
           found=0
-          for t in awesome_agent_skills/evals/*/test_*.py; do
+          for t in agent_skills/evals/*/test_*.py; do
             [ -e "$t" ] || continue
             found=1
             echo "== $t"
@@ -46,12 +46,12 @@ jobs:
         run: |
           set -e
           found=0
-          for s in awesome_agent_skills/*/SKILL.md; do
+          for s in agent_skills/*/SKILL.md; do
             [ -e "$s" ] || continue
             found=1
             d=$(dirname "$s")
             echo "== $d"
-            python3 awesome_agent_skills/evals/tools/skill_lint.py "$d" --strict
+            python3 agent_skills/evals/tools/skill_lint.py "$d" --strict
           done
           [ "$found" = "1" ] || { echo "no skills found"; exit 1; }
 
@@ -64,7 +64,7 @@ jobs:
         with:
           python-version: "3.11"
       - name: Scan all skills for supply-chain and injection patterns
-        run: python3 awesome_agent_skills/evals/tools/skill_scanner.py awesome_agent_skills
+        run: python3 agent_skills/evals/tools/skill_scanner.py agent_skills
 
   trigger-routing:
     name: trigger & routing
@@ -75,4 +75,4 @@ jobs:
         with:
           python-version: "3.11"
       - name: Positives must clear near-misses on description vocabulary
-        run: python3 awesome_agent_skills/evals/tools/run_trigger_evals.py
+        run: python3 agent_skills/evals/tools/run_trigger_evals.py

README.md

@@ -92,11 +92,11 @@ streamlit run travel_agent.py
 
 | Template | What it does | Stack |
 |---|---|---|
-| [⚰️ Project Graveyard Skill](awesome_agent_skills/project-graveyard/) | Finds your dead side projects, tells you why each one died, and helps you finish the one worth going back to | Agent Skill · Runs locally |
+| [⚰️ Project Graveyard Skill](agent_skills/project-graveyard/) | Finds your dead side projects, tells you why each one died, and helps you finish the one worth going back to | Agent Skill · Runs locally |
 | [📰 Always-on Hacker News Briefing Agent](always_on_agents/always_on_hn_briefing_agent/) | Scheduled Hacker News scout that filters AI agent and LLM app signals into a delivery-ready daily brief | ADK + Agent Runtime |
 | [🛡️ Insurance Claim Live Agent Team](voice_ai_agents/insurance_claim_live_agent_team/) | Real-time voice claim intake with Gemini Live and ADK | Voice + ADK |
 | [🏠 Home Renovation Agent](advanced_ai_agents/multi_agent_apps/ai_home_renovation_agent) | Photo → AI redesign with Nano Banana Pro | Vision + Multi-agent |
-| [♾️ Self-Improving Agent Skills](awesome_agent_skills/self-improving-agent-skills/) | Automatically optimize agent skills using Gemini and ADK | Agent Skills + ADK |
+| [♾️ Self-Improving Agent Skills](agent_skills/self-improving-agent-skills/) | Automatically optimize agent skills using Gemini and ADK | Agent Skills + ADK |
 
 > 📬 [Subscribe on Unwind AI](https://www.theunwindai.com) to get new template drops + tutorials in your inbox.
 
@@ -126,12 +126,11 @@ streamlit run travel_agent.py
 ## 📂 Featured AI Projects
 
 ### 🧩 Agent Skills
-*Give your coding agent new abilities. One command to install, plain English to use. Works with Claude Code, Codex, Cursor, and 70+ agents.*
+*Give your coding agent new abilities. One command to install, plain English to use. Works with Claude Code, Codex, Cursor, and other coding agents. [Browse all skills →](agent_skills/)*
 
-*   [🧩 Browse all skills →](awesome_agent_skills/)
-*   [⚰️ Project Graveyard](awesome_agent_skills/project-graveyard/) - Finds every side project you abandoned, tells you why each one died, and helps you finish the one worth going back to
-*   [🧠 Advisor Executor Worker](awesome_agent_skills/advisor-executor-worker/) - Your agent runs a model team: cheap models do the work in parallel, a stronger model reviews the plan, your agent manages it all
-*   [♾️ Self-Improving Agent Skills](awesome_agent_skills/self-improving-agent-skills/) - Automatically optimize agent skills using Gemini and ADK
+*   [⚰️ Project Graveyard](agent_skills/project-graveyard/) - Finds every side project you abandoned, tells you why each one died, and helps you finish the one worth going back to
+*   [🧠 Advisor Executor Worker](agent_skills/advisor-executor-worker/) - Your agent runs a model team: cheap models do the work in parallel, a stronger model reviews the plan, your agent manages it all
+*   [♾️ Self-Improving Agent Skills](agent_skills/self-improving-agent-skills/) - Automatically optimize agent skills using Gemini and ADK
 
 ### 🌱 Starter AI Agents
 *Single-file agents that run with just an API key - a great place to start.*

agent_skills/README.md

@@ -31,7 +31,7 @@ More coming, released one at a time.
 One command, any agent — the [skills CLI](https://skills.sh) detects what you have installed (Claude Code, Codex, Cursor, Copilot, Antigravity, OpenClaw, Hermes — 70+ agents) and puts the skill in the right place:
 
 ```bash
-npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/awesome_agent_skills/<skill>
+npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/<skill>
 ```
 
 Prefer manual? Clone the repo and copy the skill folder into your agent's skills dir:

agent_skills/advisor-executor-worker/README.md

@@ -11,7 +11,7 @@ This skill turns your coding agent into the orchestrator of a three-tier model t
 | Role | Default model <sub>(July 2026 — swap freely)</sub> | What it does | What it never does |
 |---|---|---|---|
 | **Executor** | Codex | Frames success criteria, plans waves, dispatches briefs, verifies every result, synthesizes the deliverable | Worker-level grunt work |
-| **Workers** | Gemini Flash | One self-contained subtask each, in parallel, stateless — each sees only its brief | Talk to each other, expand scope, get a second chance on the same call |
+| **Workers** | Gemini 3.5 Flash | One self-contained subtask each, in parallel, stateless — each sees only its brief | Talk to each other, expand scope, get a second chance on the same call |
 | **Advisor** | Claude Fable 5 | Plan review before any dispatch, taste pass before delivery, called mid-run only at commitment boundaries | Execute anything |
 
 The economics are the point: cheap parallel generation where volume wins, expensive judgment only where it changes a decision. Budgeted — **20 worker calls, 5 consults** — so a run can't quietly burn a hole in your API bill. Models are knobs: the tier pattern is the durable part, the defaults were current in July 2026.
@@ -27,7 +27,7 @@ Multi-model loops usually die from context leaks, silent partial failures, or ju
 ## Install
 
 ```bash
-npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/awesome_agent_skills/advisor-executor-worker
+npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/advisor-executor-worker
 ```
 
 Or copy this folder into your agent's skills dir (`~/.claude/skills/`, `~/.codex/skills/`, `~/.agents/skills/`).
@@ -53,6 +53,6 @@ advisor-executor-worker/
 └── references/advisor-consult.md     # the consult format the advisor answers in
 ```
 
-Evals live repo-side in `awesome_agent_skills/evals/advisor-executor-worker/` — you install only what runs.
+Evals live repo-side in `agent_skills/evals/advisor-executor-worker/` — you install only what runs.
 
 Part of [awesome-llm-apps](https://github.com/Shubhamsaboo/awesome-llm-apps) · Apache-2.0 · Last verified: July 2026

agent_skills/advisor-executor-worker/SKILL.md

@@ -38,7 +38,7 @@ verification.
 
 ## The team
 
-- **Workers (default: Gemini Flash)**, dispatched as bare API calls, not
+- **Workers (default: Gemini 3.5 Flash)**, dispatched as bare API calls, not
   a CLI. Workers are stateless generation units; the API call is
   faster, cheaper, and leaks zero context. Never paste a brief inline
   into a shell string — briefs carry quotes and arbitrary text, so

agent_skills/evals/README.md

@@ -22,10 +22,10 @@ executable code and his don't:
 
 ```bash
 # Tiers 1–2b, exactly what CI runs — deterministic, git + Python only
-python3 awesome_agent_skills/evals/tools/skill_lint.py awesome_agent_skills/project-graveyard --strict
-python3 awesome_agent_skills/evals/tools/skill_scanner.py awesome_agent_skills
-python3 awesome_agent_skills/evals/tools/run_trigger_evals.py
-python3 awesome_agent_skills/evals/project-graveyard/test_graveyard.py
+python3 agent_skills/evals/tools/skill_lint.py agent_skills/project-graveyard --strict
+python3 agent_skills/evals/tools/skill_scanner.py agent_skills
+python3 agent_skills/evals/tools/run_trigger_evals.py
+python3 agent_skills/evals/project-graveyard/test_graveyard.py
 ```
 
 Tier 3 is on demand and spends tokens: each skill's `evals.json` is in

agent_skills/evals/project-graveyard/test_graveyard.py

@@ -3,7 +3,7 @@
 Executable eval for project-graveyard. Builds a synthetic graveyard with known
 causes of death, runs the scanner against it, and asserts every classifier.
 
-    python3 awesome_agent_skills/evals/project-graveyard/test_graveyard.py
+    python3 agent_skills/evals/project-graveyard/test_graveyard.py
 
 Lives in the repo, not in the installable skill: users install only what
 runs at runtime; this is what you run BEFORE installing, from the clone.

agent_skills/project-graveyard/README.md

@@ -100,14 +100,14 @@ Then it ranks the dead by **pulse** — how close each one is to actually shippi
 One command — the [skills CLI](https://skills.sh) installs it into whatever agents you have (Claude Code, Codex, Cursor, Copilot, Antigravity, OpenClaw, Hermes — 70+):
 
 ```bash
-npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/awesome_agent_skills/project-graveyard
+npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/project-graveyard
 ```
 
 Or clone and copy — which also lets you run the eval first (below):
 
 ```bash
 git clone --depth 1 https://github.com/Shubhamsaboo/awesome-llm-apps.git
-cp -r awesome-llm-apps/awesome_agent_skills/project-graveyard ~/.claude/skills/
+cp -r awesome-llm-apps/agent_skills/project-graveyard ~/.claude/skills/
 # other agents: ~/.openclaw/skills/, ~/.hermes/skills/, or .agents/skills/ in your project
 ```
 
@@ -135,7 +135,7 @@ Skeptical? Good — you should be, about anything you install into an agent. The
 
 ```bash
 # from the cloned repo, before you install anything:
-python3 awesome_agent_skills/evals/project-graveyard/test_graveyard.py
+python3 agent_skills/evals/project-graveyard/test_graveyard.py
 # builds a synthetic graveyard in a temp dir, asserts all 16 behaviors, ~10 seconds
 ```
 
@@ -153,6 +153,6 @@ project-graveyard/                  # ← this is all that gets copied
 └── references/causes-of-death.md   # the taxonomy: signals, confidence, resurrection strategy per cause
 ```
 
-The test suite stays in the repo (`awesome_agent_skills/evals/project-graveyard/`) — run it before installing; don't carry it around after.
+The test suite stays in the repo (`agent_skills/evals/project-graveyard/`) — run it before installing; don't carry it around after.
 
 Part of [awesome-llm-apps](https://github.com/Shubhamsaboo/awesome-llm-apps) · Apache-2.0 · Last verified: July 2026

agent_skills/self-improving-agent-skills/README.md

@@ -139,7 +139,7 @@ Zip any skill folder and upload it — for instance this repo's own
 [project-graveyard](../project-graveyard/):
 
 ```bash
-cd awesome_agent_skills
+cd agent_skills
 zip -r project-graveyard.zip project-graveyard/
 ```