Skip to content

chore: trim bundle to agentv-bench only (supersedes #1226)#1231

Open
tsoyangbot wants to merge 8 commits intoEntityProcess:mainfrom
tsoyangbot:feat/1224-bundled-skills
Open

chore: trim bundle to agentv-bench only (supersedes #1226)#1231
tsoyangbot wants to merge 8 commits intoEntityProcess:mainfrom
tsoyangbot:feat/1224-bundled-skills

Conversation

@tsoyangbot
Copy link
Copy Markdown

Supersedes #1226 — trims the bundled skills to just agentv-bench.

Changes:

  • Drop agentv-eval-review, agentv-eval-writer, agentv-governance, agentv-trace-analyst from skills-data/ and plugin stubs
  • Update eval suite (skill-selection 8→3 tests, output-correctness 7→4 tests)
  • Update fixtures to reflect single-skill bundle
  • Update README with simplified fixture generation

These skills remain in the repo for reference but are not shipped in the npm package.

christso and others added 8 commits May 7, 2026 03:15
Skills are now bundled inside the CLI npm package (`apps/cli/skills/`
→ `dist/skills/` at build time), version-matched to the binary. A new
`agentv skills` subcommand serves the bundled content without any
separate plugin install step.

- `agentv skills list` — list available skill names (--json)
- `agentv skills get <name>` — print SKILL.md content (--full, --json)
- `agentv skills get --all` — print all skills
- `agentv skills path [<name>]` — print resolved skills directory

Resolution walks upward from the module file, validating by SKILL.md
presence to avoid false matches. Prefers `dist/skills/` (production
layout) over bare `skills/` (source layout).

The marketplace plugin SKILL.md files are converted to discovery stubs
that redirect agents to `agentv skills get <name>`. Full skill content
lives in `apps/cli/skills/` as the single source of truth.

Docs: update installation.mdx so the canonical setup is
`npm install -g agentv` alone; the allagents plugin step moves to an
optional "Claude Code Plugin" section.

Closes EntityProcess#1224

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Closes EntityProcess#1229.

- skills get <name> --ref <file>: load a single reference without --full.
  Searches references/, templates/, agents/, then the skill root. Auto-
  appends .md if the caller passed a bare name. --ref is incompatible
  with --all and takes precedence over --full.
- readSkill --full now also collects agents/ alongside references/ and
  templates/, so agent role definitions ship together with the skill.
- Drop scripts/ and assets/ from every bundled skill. Scripts already
  duplicated CLI behavior (onboard-agentv.sh ↔ agentv init,
  trajectory.html / eval_review.html ↔ agentv studio); lint_eval.py
  is replaced by an inline structural checklist in agentv-eval-review's
  SKILL.md until a dedicated 'agentv eval lint' lands.
- Refresh the affected SKILL.md files: agentv-onboarding now invokes
  agentv init directly (no platform script), agentv-eval-review
  inlines the deterministic checks the deleted lint script performed,
  and every skill documents 'skills get --ref <file>' / 'skills path'
  for selective reference loading.
- Tests: extend the skills unit test fixture to exercise agents/ and
  bare-root files; assert findRefFile lookup order, .md auto-append,
  and miss path.
…er pattern

Skills are now sourced from <repo-root>/skills-data/ instead of
apps/cli/skills/. This mirrors agent-browser's top-level skill-data/
layout and keeps user-authored content out of the CLI workspace.

- git mv apps/cli/skills → skills-data
- tsup.config.ts: srcSkillsDir now resolves to ../../skills-data
- skills-resolver in src/commands/skills/index.ts learns a third
  candidate name (skills-data/) so dev-mode source runs
  (bun apps/cli/src/cli.ts skills …) keep working without first
  building. Order at each ancestor: dist/skills/ → skills-data/ →
  skills/ (legacy fallback).
- Build output stays at dist/skills/, so the npm tarball is unchanged.
- Verified: bun run build, dist/skills/ populated, node dist/cli.js
  skills list / get --ref / path all return expected content. Source
  mode (no dist) also resolves via skills-data/.
Drop agentv-eval-review, agentv-eval-writer, agentv-governance,
agentv-trace-analyst from skills-data/ and plugin stubs.

Update eval suite:
- skill-selection: 8 tests → 3 (only agentv-bench selection + no-false-positive)
- skill-invocation: update fixture references
- output-correctness: remove tests for dropped skills
- fixtures: update skills-list-all.txt, skills-get-nonexistent.txt
- README: update fixture generation commands

These skills remain in the repo for reference but are not shipped
in the npm package.
- Remove misleading 'legacyCandidate' / 'distCandidate' / 'repoRootCandidate' names
- Simplify to two checks: skills/ (production) and skills-data/ (source)
- Add AGENTV_SKILLS_DIR env var override (matches agent-browser's pattern)
- Fix misleading comment that said 'dist/skills/ is a sibling' then checked
  path.join(dir, 'dist', 'skills') which would be dist/dist/skills
- Rename skills-data/ → skill-data/ (match agent-browser's naming)
- Rewrite findSkillsDir to match agent-browser's find_package_root:
  1. AGENTV_SKILLS_DIR env var (like AGENT_BROWSER_SKILLS_DIR)
  2. ../ relative to binary (npm/bun install)
  3. Walk up to find skill-data/ (dev runs from source)
- Update tsup.config.ts: copy skill-data/ → dist/skill-data/
- Update file header comments to reflect new paths

No more 'legacyCandidate' / 'distCandidate' confusion. The resolution
logic now mirrors agent-browser exactly.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants