validate-provenance.sh assumed `Research doc:` names a research sources.md whose H2 headings are the source slugs, but 29 corpus entries named topic docs and 6 values were not a single path, so checks 7 and 8 reported INFO for 36 entries and nothing ever failed. `Research doc:` now takes exactly one path. An entry with no registry writes `none` plus one `- **Basis:** <path>` bullet per path; each Basis path is existence-checked unless annotated `(removed in <sha>)`. - Check 7 FAILs when a resolved registry lacks the slug, when the value is a topic doc, or when it is a list. An unresolvable path stays INFO. - Check 8 is retired: one registry serves many skills, so requiring every registry slug in each skill's sources.md is unsatisfiable. - The Research doc and Basis parsers accept the inline, bullet and header-plus-bullets spellings, so a differently spelled field is no longer read as absent. Refs: #121 ADR: 0028 Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EGHFJextYtVQseaHPDDhxB
4.4 KiB
source_keys
| source_keys | |
|---|---|
|
File Structure and Internal Consistency Reference
Upstream source: agentskills.io — specification (optional directories, file references).
Read this when judging the file-structure and internal-consistency dimensions.
Permitted directories
Only four: scripts/, references/, assets/, tests/. The specification permits additional
directories; this house does not, because an unlisted directory is content no auditor and no host
knows to look at. Flag any other directory as a FAIL.
scripts/holds only executable code an agent can run, and the sourced libraries those entry points load. Alib-*.shthat is never invoked on its own belongs here beside the entry point that sources it — it is executable code, not documentation, so do not flag it for failing to run standalone. Test files (.bats,*_test.*,test_*.sh) there are a FAIL — they belong intests/.- No non-spec files at the skill root: no
META.md, no stray config outside the four directories. - An optional directory that exists must hold real content, not an unfilled placeholder README.
Cross-plugin path references
A plugin is copied to a cache on install, and a path that climbs out of the skill directory stops
resolving there. Flag a path in SKILL.md, scripts/, references/ or assets/ when it
resolves outside the skill directory — an absolute repo path
(plugins/<plugin>/skills/<other>/ and its APM-native equivalent .apm/skills/<other>/), a
plugin-root path (docs/, bin/), or a ../ chain that leaves the skill root.
Resolve before flagging, twice over:
- Resolve the path.
$SKILL_DIR/../assets/templatesclimbs one level from ascripts/directory and lands back inside the same skill, so it resolves in a cache install and is not a finding. A bare../is not the defect; leaving the skill is. - Skip fenced code blocks. A path inside a fenced block is an example, and rubrics quote outside paths deliberately as negative examples of what not to write. Flag a fenced path only when the surrounding prose presents it as the form to copy.
Referring to another skill's file. There is one sanctioned spelling, and it is possessive:
skill-author's references/contract.md. Write the skill by name and let the reader
resolve it — do not spell the repo path. The full path is the thing this section forbids, and
references/contract.md on its own is a hard ERROR from the gate, which
requires an unqualified references/ pointer to exist in the skill's OWN directory. The
possessive form is the only spelling both rules accept; the gate recognises it and skips the
on-disk check. Flag any other spelling of a cross-skill reference.
Two directories are exempt, and the exemptions are structural rather than discretionary:
references/sources.md. ItsResearch doc:andBasis:fields are development-time provenance pointers, not runtime references. AResearch doc:path that does not resolve after install is expected, sovalidate-provenance.shdoes not treat an absent path as a FAIL — it emits an INFO naming the slug and stating that check 7 did not run for it. Flagging them as broken references would make every correctly-provenanced skill fail. Where the path DOES resolve, it is checked:Research doc:names exactly one Research registry (asources.mdwhose H2 headings are the source slugs), and a slug missing from it, a topic document in its place, or a list of paths is a FAIL. An entry with no registry writesResearch doc: noneplusBasis:repo paths, which are existence-checked unless annotated(removed in <sha>).tests/. Test files are dev-only and may reference repo-level infrastructure such as a sharedtests/test_helper/. The exemption is conditional on the dependency being declared: iftests/exists andtests/README.mdis absent or does not document it, that is a FAIL.
Internal consistency
The skill has to agree with itself. Two checks:
SKILL.md's steps match what the scripts actually do — the arguments, the exit codes, and the output shape it tells the agent to expect.- Placeholder READMEs inside
scripts/,tests/andassets/say the same thing about each directory thatSKILL.mddoes.
The FAIL and SUGGESTION criteria for this dimension live in references/skill-finding-criteria.md,
which Step 3 loads on every run.