Commit Graph

3 Commits

Author SHA1 Message Date
Teknium d4cec15b47 refactor(tools): first-wave simplification of tools/ (file ops split, lazy_deps, code_exec, approval, browser, delegate, mcp, skills, terminal, voice, media)
Behavior-neutral structural pass over tools/*: god-file extractions into
sibling modules (file_operations_common/lint/search, file_tools_paths/
read_tracking/write, code_execution_env/rpc, tool_search_catalog/names/
validation, tts_command_provider, ...), duplicate helper unification,
if/elif -> dispatch tables, dead-code removal, docstring compaction.
Tool schemas (get_tool_definitions) verified byte-identical to base.
2026-09-02 14:43:45 -07:00
Teknium 092ff2b9aa fix: suppress windows-footgun false positives in linter pattern list
The _POSIX_PRIMITIVES tuple holds search-pattern STRINGS the linter
greps for in skill scripts — 'os.setsid' / 'signal.SIGKILL' are data,
not calls. Add inline # windows-footgun: ok suppressions.
2026-08-08 11:12:27 -07:00
Teknium fce314eabd feat(skills): advisory SKILL.md convention linter on create
Adds tools/skill_linter.py — a soft companion to the hard frontmatter
validator. It encodes the CONTRIBUTING 'Skill authoring standards
(HARDLINE)' conventions that today only a human reviewer catches:

- shell-utility references in prose (`grep`/`sed`/`cat`...) that should
  name the native tool (search_files/patch/read_file)
- missing version/author/license/metadata.hermes block
- name != directory, invalid name format
- description over the 60-char prompt budget, marketing words
- dangling references/ links, forbidden scaffolding files
- POSIX-only script primitives without a platforms: gate

Findings are ADVISORY. skill_manage(create) attaches them as
lint_warnings + lint_hint in the success result; nothing is blocked
(the hard rejects already run in _validate_frontmatter). A CLI
(python -m tools.skill_linter <dir>) exits 1 only on ERROR-severity
findings so CI can gate on structural breakage without failing on nits.

Calibrated against the bundled skills/ tree: 76 advisory findings, exit 0,
no false positives after excluding repo-root scripts/ refs.

Inspired by MiniMax Code's skill-creator lint step; adapted to our
existing validator + skill_utils rather than a parallel system.
2026-08-08 11:12:27 -07:00