GitHub organization
Agent skills by block
- skills
- 16
- official
- 16
- repositories
- 3
Repositories by block
- berdOfficiala desktop app for getting work done with any model969 stars · 11 skills
- trailblazeOfficial🥾 AI-Driven UI Testing Framework with Recorded Trails321 stars · 4 skills
- codecrucibleOfficialA purpose-built Go CLI tool that analyses Git repositories for security vulnerabilities using LLM-based analysis117 stars · 1 skill
Skills by block, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Create, edit, or inspect Berd agents/personas stored as Agent Markdown files with YAML frontmatter under ~/.agents/agents. | block/ | 969 | — | ~644 | Automated safety check: Pass | Apache-2.0 | today |
| 2 | A skill your agent uses when adding, reviewing, designing, testing, or managing Assistive UX moments in Berd, including discover, suggest, and autoApply guidance, adaptive settings, behavior… | block/ | 969 | — | ~706 | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Write or update a devlog entry in the devlog directory. An agent skill from block/trailblaze. | block/ | 321 | — | ~586 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4 | Runs the codecrucible CLI for LLM-backed security scans of a repository, checks scope and cost first with a dry run, and reads the SARIF results. | block/ | 117 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | Read and hand off Buzz channels or threads in a private agent conversation using the installed Buzz CLI. | block/ | 969 | — | ~893 | Automated safety check: Pass | Apache-2.0 | today |
| 6 | A skill your agent uses when turning a captured human demonstration (a Trailblaze App demonstration bundle: demo.yaml + actions.ndjson + per-action screenshots and view hierarchies) into a durable… | block/ | 321 | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 7 | Create a GitHub PR from the current branch: handle uncommitted changes, generate a summary, submit via gh CLI, then watch the PR to a ready state — fixing failing checks and addressing review… | block/ | 969 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 8 | A skill your agent uses when validating or evaluating Trailblaze's out-of-box (OOB) user experience — does what the trailblaze skill claims actually match the real installed CLI? | block/ | 321 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 9 | A skill your agent uses when adding, reviewing, configuring, graduating, or removing Berd experiments. | block/ | 969 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | A skill your agent uses when working with Trailblaze — natural-language device control for coding agents across iOS, Android, and web, with replayable .trail.yaml files as the artifact. | block/ | 321 | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 11 | Create, edit, or inspect Berd skills stored as skill folders with SKILL.md files. | block/ | 969 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | today |
| 12 | Help with Berd the desktop app: how-to, troubleshooting, settings, agents, skills, automations, projects, sessions, providers, connections, feedback, or berdctl. | block/ | 969 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Run a long-lived command outside the current Berd turn and wake the owning session with actionable stdout. | block/ | 969 | — | ~467 | Automated safety check: Pass | Apache-2.0 | today |
| 14 | Senior engineer code review focused on catching issues before they become PR comments. | block/ | 969 | — | ~5.3k | Automated safety check: Pass | Apache-2.0 | today |
| 15 | A skill your agent uses when adding, extending, modifying, or removing berdctl commands, verbs, nouns, schemas, help text, or any of the berdctl surface. | block/ | 969 | — | ~574 | Automated safety check: Pass | Apache-2.0 | today |
| 16 | Coordinate work across Berd sessions while keeping one conversation available to the user. | block/ | 969 | — | ~277 | Automated safety check: Pass | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill by block?
Agent Builder (official) from block/berd ranks first of the 16 skills by block listed here, with the highest score: its repository has 969 GitHub stars, its SKILL.md loads about 644 tokens and it passes the automated safety check with no findings. Next come Assistive UX and Devlog.
Are block's skills official?
16 of the 16 skills by block are official, published by the vendor's own GitHub organization: Agent Builder, Assistive UX, Devlog, CodeCrucible Security Scans, Buzz Handoff and 11 more.
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.