Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Run the same host-compat gate CI uses on skills/ before opening a skill PR.
The check is for Codex and Cursor copies, not Claude-only runtime quality.
skills/.agents/skills/ or .cursor/skills/validate-skill-host-compat.js findingsCanonical skills live in skills/. Codex loads .agents/skills/. Cursor loads a
smaller .cursor/skills/ subset. CONTRIBUTING documents that sync as manual.
validate-skills.js only checks that SKILL.md exists and that name /
description are usable YAML. tests/ci/codex-skill-surface.test.js only
sees .agents/skills/. This script is the cross-tree gate:
bash / sh / zsh fences
($CLAUDE_SESSION_ID, $CLAUDE_SKILL_DIR, $CLAUDE_PLUGIN_ROOT,
$CLAUDE_PROJECT_DIR, $ARGUMENTS) fail. Codex leaves those tokens
as literal text. In a Codex copy, rewrite $CLAUDE_PROJECT_DIR to
$(pwd) or an explicit path.name, description, metadata, license,
and allowed-tools. origin: ECC may stay on the canonical skills/
copy and must be stripped on the Codex copy.agents/openai.yaml that has a skills/ directory must
have .agents/skills/<name>/. Cursor copies are optional; when present,
name: must match the directory.--strict-checklist.validate-skills.js frontmatter WARN default is unchanged (#1663).
From the repo root:
node scripts/ci/validate-skill-host-compat.jsPrint counts without failing:
node scripts/ci/validate-skill-host-compat.js --inventoryPromote checklist warnings:
node scripts/ci/validate-skill-host-compat.js --strict-checklistSlash command:
$skill-host-compat
$skill-host-compat --inventoryCodex and Cursor projections must resolve Claude-only substitutions in executable blocks. Canonical Claude-scoped examples remain valid. POSIX $1 and ${1} parameters are ambiguous and require review rather than failing this gate. This fence is the
forbidden pattern; do not use these unresolved projection examples:
echo "$CLAUDE_SESSION_ID"
ls "$CLAUDE_SKILL_DIR"
node "$CLAUDE_PLUGIN_ROOT/scripts/setup.js" $ARGUMENTS
cd "$CLAUDE_PROJECT_DIR"Do not add version: or origin: to a Codex copy under .agents/skills/.
Do not treat a passing validate-skills.js run as Codex-safe. Do not require
every skills/ entry to have a Cursor copy.
origin: ECC if the CONTRIBUTING template calls for it.origin, version, and argument-hint on the Codex copy.npx, ecc, or a resolved
root). Rewrite $CLAUDE_PROJECT_DIR in Codex copies to $(pwd) or an
explicit path. Keep valid Claude-scoped forms in canonical instructions; resolve host variables in the target projection.npm test when the change is a new skill.--inventory to see checklist warning volume without failing the tree.skill-comply — runtime behavioral traces, not host-portabilityskill-stocktake — holistic audit of installed ~/.claude/skillsskill-scout — search existing skills before creating a new oneaffaan-m/ECC
d2ef268
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.