docs(skills): stop directing the agent to install, update or remove skills (#7102)

A third-party skill-trust grader (DeltaVerdict D5) fails any skill text
that has the agent modify its own skills, even when disclosed or gated on
the user. Reword the skill lifecycle, plugin, CLI and scaffold text so it
states facts the agent can relay (skills are versioned with the CLI; the
person installs and updates them, and which command does it) instead of
commands for the agent to run. Every agent-run `init` example passes
--skip-skills, since init otherwise installs missing core skills; the
plugin header, plugin-cli and sfx messages are person-addressed; the
person's install commands are marked as theirs; /style-sampling joins
the on-demand lists. Regenerate skills-manifest.json and update the
pinned reverse init regex.

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Wenbo Zhu
2026-11-04 10:17:14 +00:00
committed by GitHub
co-authored by Claude Opus 5.5
parent e04b722a99
commit 6857bb08e8
17 changed files with 57 additions and 57 deletions
+1 -1
View File
@@ -43,7 +43,7 @@ test("reverse builds the project with init --video and asks for the run's total
const start = read("references/start.md");
assert.match(
start,
/`npx hyperframes init <project> --video <video> --keep-original --skip-transcribe`/,
/`npx hyperframes init <project> --video <video> --keep-original --skip-transcribe --skip-skills`/,
);
assert.match(
start,