Repository
ntorga/agent-starter-kit agent skills
- skills
- 21
- GitHub stars
- 146
GitHub description: “The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .”
- Stars
- 146 (34 forks)
- Licence
- MIT
- Last push
- Sep 2026
- Created
- Mar 2026
- agent-framework
- ai-agents
- coding-assistant
- llm-orchestration
- model-agnostic
- multi-agent
- prompt-engineering
- starter-kit
- ai-harness
- prompt-framework
- natural-language
- nlah
Install all skills
npx skills add ntorga/agent-starter-kitAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in ntorga/agent-starter-kit, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework. | ntorga/ | 146 | — | ~1.7k | Automated safety check: Pass | MIT | 25 days ago |
| 2 | Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit. | ntorga/ | 146 | — | ~2.7k | Automated safety check: Pass | MIT | 25 days ago |
| 3 | Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path. | ntorga/ | 146 | — | ~1.2k | Automated safety check: Pass | MIT | 25 days ago |
| 4 | Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing. | ntorga/ | 146 | — | ~944 | Automated safety check: Pass | MIT | 25 days ago |
| 5 | 5.Boot Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet. | ntorga/ | 146 | — | ~937 | Automated safety check: Pass | MIT | 25 days ago |
| 6 | Browser inspection and interaction for verifying rendered web UI during development. | ntorga/ | 146 | — | ~2k | Automated safety check: Pass | MIT | 25 days ago |
| 7 | Reviews code and plans for logic coherence, correctness, and structural integrity. | ntorga/ | 146 | — | ~2.8k | Automated safety check: Pass | MIT | 25 days ago |
| 8 | Reviews code and plans against the project's coding rules. An agent skill from ntorga/agent-starter-kit. | ntorga/ | 146 | — | ~1.3k | Automated safety check: Pass | MIT | 25 days ago |
| 9 | How to maintain .context.md files and docs/FEATURE-MAP.md as the project evolves. | ntorga/ | 146 | — | ~1.2k | Automated safety check: Pass | MIT | 25 days ago |
| 10 | 10.Dispatch Assembles sub-agent prompts with task brief and routes to the correct provider. | ntorga/ | 146 | — | ~2.5k | Automated safety check: Pass | MIT | 25 days ago |
| 11 | 11.Grill Protocol that interviews the user in rounds over the Architect's design tree. | ntorga/ | 146 | — | ~1.3k | Automated safety check: Pass | MIT | 25 days ago |
| 12 | Plan lifecycle — grill entry point, grounding, artifact review, per-epic execution, revision. | ntorga/ | 146 | — | ~1.8k | Automated safety check: Pass | MIT | 25 days ago |
| 13 | 13.Review Loop Two-mode review loop — single reviewer per epic, three reviewers for full branch. | ntorga/ | 146 | — | ~1.3k | Automated safety check: Pass | MIT | 25 days ago |
| 14 | Adversarial plan review — structural validation and assumption attack on grill artifacts before implementation begins. | ntorga/ | 146 | — | ~2.6k | Automated safety check: Pass | MIT | 25 days ago |
| 15 | File-based to-do tracking for multi-step and multi-session work. | ntorga/ | 146 | — | ~949 | Automated safety check: Pass | MIT | 25 days ago |
| 16 | 16.Web Search Web search and page fetch through the TinyFish CLI. An agent skill from ntorga/agent-starter-kit. | ntorga/ | 146 | — | ~945 | Automated safety check: Pass | MIT | 25 days ago |
| 17 | Structured review summary format with verdict logic and coverage scoring. | ntorga/ | 146 | — | ~393 | Automated safety check: Pass | MIT | 25 days ago |
| 18 | Deterministic self-evaluation rubric for Coder — scored every run using the GRASP framework. | ntorga/ | 146 | — | ~2.4k | Automated safety check: Pass | MIT | 25 days ago |
| 19 | Deterministic self-evaluation rubric for Contextualizer — scored every run using the TRACE framework. | ntorga/ | 146 | — | ~2.3k | Automated safety check: Pass | MIT | 25 days ago |
| 20 | Structured recovery and escalation when an agent hits a retry loop. | ntorga/ | 146 | — | ~649 | Automated safety check: Pass | MIT | 25 days ago |
| 21 | Deterministic self-evaluation rubric for Reviewer — scored every run using the SHIELD framework. | ntorga/ | 146 | — | ~2.3k | Automated safety check: Pass | MIT | 25 days ago |
Questions, answered from the data.
What is the best skill in ntorga/agent-starter-kit?
Agent Decision from ntorga/agent-starter-kit ranks first of the 21 skills in ntorga/agent-starter-kit listed here, with the highest score: its repository has 146 GitHub stars, its SKILL.md loads about 1.7k tokens and it passes the automated safety check with no findings. Next come Agent Memory and Architect Design Tree.
Are the skills in ntorga/agent-starter-kit official?
None yet. All 21 skills in ntorga/agent-starter-kit listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from ntorga/agent-starter-kit?
Run npx skills add ntorga/agent-starter-kit in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.