GitHub user
Agent skills by Archive228
- skills
- 52
- repository
- 1
Repositories by Archive228
Skills by Archive228, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop. | Archive228/ | 755 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 2 | Get JSON out of the model reliably. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~830 | Automated safety check: Pass | MIT | 2 mo ago |
| 3 | A skill your agent uses when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including… | Archive228/ | 755 | — | ~1.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 4 | Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). | Archive228/ | 755 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 5 | Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed. | Archive228/ | 755 | — | ~876 | Automated safety check: Pass | MIT | 2 mo ago |
| 6 | Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order. | Archive228/ | 755 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 7 | Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn. | Archive228/ | 755 | — | ~735 | Automated safety check: Pass | MIT | 2 mo ago |
| 8 | Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. | Archive228/ | 755 | — | ~1k | Automated safety check: Pass | MIT | 2 mo ago |
| 9 | Negotiate a pre-code contract between generator and evaluator personas that defines what "done" means before any code is written. | Archive228/ | 755 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 10 | Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so featurelist.json stays immutable | Archive228/ | 755 | — | ~1.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 11 | Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off. | Archive228/ | 755 | — | ~1k | Automated safety check: Pass | MIT | 2 mo ago |
| 12 | Review a diff against the goal spec assuming the code is BROKEN. | Archive228/ | 755 | — | ~454 | Automated safety check: Pass | MIT | 2 mo ago |
| 13 | Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh. | Archive228/ | 755 | — | ~447 | Automated safety check: Pass | MIT | 2 mo ago |
| 14 | A skill your agent uses for ANY bug, test failure, crash, or unexpected behavior. | Archive228/ | 755 | — | ~432 | Automated safety check: Pass | MIT | 2 mo ago |
| 15 | Before picking new work, smoke-test the last "completed" feature. | Archive228/ | 755 | — | ~899 | Automated safety check: Pass | MIT | 2 mo ago |
| 16 | Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs. | Archive228/ | 755 | — | ~1.1k | Automated safety check: Pass | MIT | 2 mo ago |
| 17 | Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity. | Archive228/ | 755 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 18 | Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on. | Archive228/ | 755 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 19 | Get a PDF into the model without blowing the context window or losing structure. | Archive228/ | 755 | — | ~969 | Automated safety check: Pass | MIT | 2 mo ago |
| 20 | Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list. | Archive228/ | 755 | — | ~1k | Automated safety check: Pass | MIT | 2 mo ago |
| 21 | Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. | Archive228/ | 755 | — | ~1.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 22 | Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. | Archive228/ | 755 | — | ~1k | Automated safety check: Pass | MIT | 2 mo ago |
| 23 | Test the boundary between two systems by the contract, not the implementation. | Archive228/ | 755 | — | ~219 | Automated safety check: Pass | MIT | 2 mo ago |
| 24 | Make frontend output look intentional, not AI-generated. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~242 | Automated safety check: Pass | MIT | 2 mo ago |
| 25 | 25.Flaky Hunter Diagnose and fix tests that pass sometimes and fail other times. | Archive228/ | 755 | — | ~222 | Automated safety check: Pass | MIT | 2 mo ago |
| 26 | Design the three states every data UI forgets. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~206 | Automated safety check: Pass | MIT | 2 mo ago |
| 27 | Write safe, reversible database migrations for this repo's conventions. | Archive228/ | 755 | — | ~204 | Automated safety check: Pass | MIT | 2 mo ago |
| 28 | 28.Simplify Reduce a change to the minimum that solves the problem. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~234 | Automated safety check: Pass | MIT | 2 mo ago |
| 29 | Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. | Archive228/ | 755 | — | ~230 | Automated safety check: Pass | MIT | 2 mo ago |
| 30 | Don't over-equip an agent with tools/MCP servers. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~234 | Automated safety check: Pass | MIT | 2 mo ago |
| 31 | 31.A11y Pass Catch the accessibility failures that ship in almost every AI-built UI. | Archive228/ | 755 | — | ~216 | Automated safety check: Pass | MIT | 2 mo ago |
| 32 | 32.Authz Check Verify that an endpoint checks ownership, not just authentication. | Archive228/ | 755 | — | ~220 | Automated safety check: Pass | MIT | 2 mo ago |
| 33 | Find the exact commit that introduced a bug. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~207 | Automated safety check: Pass | MIT | 2 mo ago |
| 34 | Turn messy WIP into clean, atomic commits with messages that explain why. | Archive228/ | 755 | — | ~208 | Automated safety check: Pass | MIT | 2 mo ago |
| 35 | Keep the agent's context lean so accuracy doesn't collapse. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~241 | Automated safety check: Pass | MIT | 2 mo ago |
| 36 | Validate and constrain untrusted input at the boundary. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~222 | Automated safety check: Pass | MIT | 2 mo ago |
| 37 | 37.PR From Diff Write a PR description a reviewer can approve fast. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~188 | Automated safety check: Pass | MIT | 2 mo ago |
| 38 | 38.Readme Audit Check whether a README actually lets a stranger run the project. | Archive228/ | 755 | — | ~207 | Automated safety check: Pass | MIT | 2 mo ago |
| 39 | Rebase, squash, or rewrite history without losing work or breaking shared branches. | Archive228/ | 755 | — | ~216 | Automated safety check: Pass | MIT | 2 mo ago |
| 40 | Undo a bad change without nuking unrelated work. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~211 | Automated safety check: Pass | MIT | 2 mo ago |
| 41 | 41.Spec First Write the goal spec on disk before the agent acts, so it can't drift. | Archive228/ | 755 | — | ~221 | Automated safety check: Pass | MIT | 2 mo ago |
| 42 | 42.SQL Review Review SQL and ORM queries for correctness, safety, and performance before they ship. | Archive228/ | 755 | — | ~217 | Automated safety check: Pass | MIT | 2 mo ago |
| 43 | Before fixing any bug, write a test that reproduces it and watch it fail. | Archive228/ | 755 | — | ~197 | Automated safety check: Pass | MIT | 2 mo ago |
| 44 | Turn a set of commits or a diff into a clean, user-facing changelog entry. | Archive228/ | 755 | — | ~196 | Automated safety check: Pass | MIT | 2 mo ago |
| 45 | Find the untested code paths that actually matter, not just the coverage percentage. | Archive228/ | 755 | — | ~207 | Automated safety check: Pass | MIT | 2 mo ago |
| 46 | Capture an architectural decision so the next session (or engineer) knows WHY. | Archive228/ | 755 | — | ~201 | Automated safety check: Pass | MIT | 2 mo ago |
| 47 | Decide whether to add, keep, or remove a dependency. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~199 | Automated safety check: Pass | MIT | 2 mo ago |
| 48 | Find and remove unreachable/unused code safely. An agent skill from Archive228/loopkit. | Archive228/ | 755 | — | ~197 | Automated safety check: Pass | MIT | 2 mo ago |
Questions, answered from the data.
What is the best skill by Archive228?
Hitl Escalate from Archive228/loopkit ranks first of the 52 skills by Archive228 listed here, with the highest score: its repository has 755 GitHub stars, its SKILL.md loads about 1.2k tokens and it passes the automated safety check with no findings. Next come Structured Output and Using Loopkit.
Are Archive228's skills official?
None yet. All 52 skills by Archive228 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.