Updated 1mo ago
by ashutoshsinghpr7
wikiskill
WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.
275 GitHub stars (275)
+25 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | +1 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | +2 |
| Oct 3 | +3 |
| Oct 4 | +3 |
| Oct 5 | +4 |
| Oct 6 | +2 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | +2 |
| Oct 11 | 0 |
| Oct 12 | +1 |
| Oct 13 | +2 |
| Oct 14 | +2 |
| Oct 15 | +1 |
| Oct 16 | +1 |
- 8 skills (8 skills found in its SKILL.md files)
- 26 forks (26 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add ashutoshsinghpr7/wikiskill
Asks which skills and agents to install. Just one: npx skills add ashutoshsinghpr7/wikiskill --skill script-exec-blocked — add -g for every project.
Claude Code
git clone https://github.com/ashutoshsinghpr7/wikiskillcp -r "wikiskill/skills/script-exec-blocked" ~/.claude/skills/
Copies the script-exec-blocked skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add ashutoshsinghpr7/wikiskill
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
script-exec-blocked
Sandbox approval policy blocks execute_code and python3 -c; use read_file/write_file + manual transforms instead of retrying both runners.
skills/script-exec-blocked/SKILL.md on GitHub (opens in a new tab) -
search-miss-binary
ripgrep/search_files silently skips binary-detected files — verify empty search results with grep -a / file / xxd before concluding 'not found'.
skills/search-miss-binary/SKILL.md on GitHub (opens in a new tab) -
spec-literal-execution
Apply ONLY the spec clauses literally — no aggregation, dedup, or cleanup transforms; each input record maps to its own output line.
skills/spec-literal-execution/SKILL.md on GitHub (opens in a new tab) -
trace-harness-launch-failure
Empty session traces mean launch failure, not agent behavior — verify api_call_count/tool_call_count and stdout.txt before analyzing.
skills/trace-harness-launch-failure/SKILL.md on GitHub (opens in a new tab) -
verify-output-readback
After write_file, re-read the deliverable (or ls + hexdump/line-print) and re-check the last format clauses before finishing.
skills/verify-output-readback/SKILL.md on GitHub (opens in a new tab) -
wikiskill-evolve
Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict R_val > R_best gating.
skills/wikiskill-evolve/SKILL.md on GitHub (opens in a new tab) -
wikiskill-maintainer
Consolidate traces into the persistent wiki (WikiSkill).
skills/wikiskill-maintainer/SKILL.md on GitHub (opens in a new tab) -
wikiskill-proposer
Propose skills from wiki patterns and traces (WikiSkill).
skills/wikiskill-proposer/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.