* fix(skills): scan nested subdirectories for grouped skill layouts
Previously, skill discovery only checked immediate children of the
skills root for SKILL.md files. Skills organized in subdirectories
(e.g. ~/.openclaw/skills/coze/koze-retrieval/SKILL.md) were silently
ignored.
Now, when an immediate child directory does not contain a SKILL.md,
its own children are checked one level deeper. This supports grouped
skill layouts while keeping the scan depth bounded (max 2 levels) to
avoid unbounded filesystem traversal.
The existing per-source skill count limits and containment checks
still apply to nested discoveries.
Fixes#56915
* test(skills): cover nested grouped skill discovery
* fix(skills): cache contained-path checks and cap nested scans
- Reuse skillDirRealPath captured during the collection phase so the load
loop no longer re-runs resolveContainedSkillPath on the same directory.
- Apply the per-root candidate cap (and the matching warning log) when
descending into nested grouped skill directories, matching the outer
scan's behavior.
Addresses Greptile P2 feedback on PR #72534.
* fix(skills): load grouped skill directories under skills roots
* fix(clownfish): address review for ghcrawl-156697-autonomous-smoke (1)
---------
Co-authored-by: Otto Deng <otto@ottodeng.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Co-authored-by: Otto Deng <ottodeng2@github.local>
The skills doc was 409 lines of nested bullet lists describing
precedence, allowlist rules, gating fields, installer specs, and
config overrides. Heavy reference content but no Mintlify structure.
Restructure for scan-first reading without losing reference detail:
- Convert 'Locations and precedence' from a numbered list + arrow
string into a 6-row precedence table.
- Convert 'Per-agent vs shared skills' bullet/paragraph mix into a
scope/path/visibility table.
- Move agent-allowlist rules into an AccordionGroup so the example
config is the headline and the rules collapse on demand.
- Convert ClawHub install/update/sync bullets into a 3-row command
table.
- Convert SKILL.md frontmatter optional keys (homepage, user-invocable,
disable-model-invocation, command-dispatch, command-tool,
command-arg-mode) into ParamField definitions.
- Convert metadata.openclaw fields (always, emoji, homepage, os,
requires.bins, requires.anyBins, requires.env, requires.config,
primaryEnv, install) into ParamField definitions.
- Move installer-selection rules and per-installer details (Go, download)
into an AccordionGroup so the gating section reads as the canonical
schema plus collapsible operational notes.
- Convert skills.entries config-override rules (enabled, apiKey, env,
config, allowBundled) into ParamField definitions.
- Surface security caveats as a Warning callout up top instead of a
bullet list.
- Move 'Looking for more skills?' into the trailing Related list and
drop the dangling --- separator.
- Sentence-case headings (Format, Gating, Config overrides, Token
impact) and the Related entries (Creating skills, Skills config,
Slash commands).
- Drop the redundant 'Skill Workshop' Title-Case heading variant.
- Add sidebarTitle 'Skills' for explicit nav.
Skill source paths, frontmatter parser rules, gating semantics,
installer selection logic, sandboxing notes, env-injection scope,
snapshot/refresh behaviour, remote-node behaviour, and token-impact
formula are unchanged. Pure restructure plus Mintlify components.
Add cross-linking Related sections to tool pages that were dead ends:
- exec, exec-approvals, browser, pdf, skills, lobster
Each page now links to 2-4 related topics for navigation continuity.
