GitHub organization
Agent skills by AgentToolkit
- skills
- 21
- repository
- 1
Repositories by AgentToolkit
Skills by AgentToolkit, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Contrasts successful and failed agent runs of the same task and derives guidelines backed by evidence from transcripts, tool calls and outcome judgments. | AgentToolkit/ | 122 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Turns a saved agent trajectory into a reusable skill with a SKILL.md and supporting scripts, so later sessions can call the workflow instead of rediscovering it. | AgentToolkit/ | 122 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Copies a memory the agent just saved into the shared evolve store with a retrieval trigger, so it can be shared across a team and audited like other entities. | AgentToolkit/ | 122 | — | ~922 | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Has the agent read a project wiki's AGENTS.md and pull the guidelines that fit the task it is about to start, instead of loading the wiki at session start. | AgentToolkit/ | 122 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | Reads a normalized Claude Code trajectory JSON and turns its errors and solutions into reusable guideline pages in wiki-twobatch/guidelines. | AgentToolkit/ | 122 | — | ~2k | Automated safety check: Pass | Apache-2.0 | today |
| 6 | Ingest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end — convert, summarize, extract guidelines, synthesize skills, optionally compare… | AgentToolkit/ | 122 | — | ~4k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | Read a normalized Claude Code trajectory JSON and write an episodic summary page to wiki-twobatch/summaries/. | AgentToolkit/ | 122 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Read a normalized Claude Code trajectory JSON and produce a wiki-resident SKILL.md page that future agents can invoke. | AgentToolkit/ | 122 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | today |
| 9 | 9.Learn Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns. | AgentToolkit/ | 122 | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | 10.Provenance Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions. | AgentToolkit/ | 122 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 11 | 11.Publish Publish a private guideline to a configured write-scope repo. | AgentToolkit/ | 122 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 12 | 12.Recall Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before… | AgentToolkit/ | 122 | — | ~950 | Automated safety check: Pass | Apache-2.0 | today |
| 13 | 13.Retention Apply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default) | AgentToolkit/ | 122 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 14 | Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning | AgentToolkit/ | 122 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 15 | 15.Subscribe Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list. | AgentToolkit/ | 122 | — | ~535 | Automated safety check: Pass | Apache-2.0 | today |
| 16 | 16.Doctor Diagnose evolve health on Claude — verify the CLAUDE.md @import is actually loading the thin EVOLVE.md into sessions | AgentToolkit/ | 122 | — | ~415 | Automated safety check: Pass | Apache-2.0 | today |
| 17 | 17.Sync Pull the latest guidelines from every configured repo (read- and write-scope). | AgentToolkit/ | 122 | — | ~259 | Automated safety check: Pass | Apache-2.0 | today |
| 18 | 18.Unsubscribe Remove a repo from the unified repos list and delete its local clone. | AgentToolkit/ | 122 | — | ~329 | Automated safety check: Pass | Apache-2.0 | today |
| 19 | Read all atomic guidelines in wiki-twobatch/guidelines/ and propose themed clusters that group near-duplicates. | AgentToolkit/ | 122 | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
| 20 | Discover task families across summaries and write per-family comparison pages with findings narrative. | AgentToolkit/ | 122 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | today |
| 21 | 21.Save Captures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scripts | AgentToolkit/ | 122 | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill by AgentToolkit?
Agent Wiki Compare Outcomes from AgentToolkit/altk-evolve ranks first of the 21 skills by AgentToolkit listed here, with the highest score: its repository has 122 GitHub stars, its SKILL.md loads about 1.7k tokens and it passes the automated safety check with no findings. Next come Trajectory Skill Synthesizer and Evolve Memory Mirror.
Are AgentToolkit's skills official?
None yet. All 21 skills by AgentToolkit listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
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.