skill-improvement — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-improvement (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill captures knowledge gained during a working session and feeds it back into the relevant skill — keeping skills accurate and up to date without manual maintenance.
Trigger this skill whenever, during a session, you observe any of the following:
is worth capturing, even if the user didn't mention it
Don't wait to be asked. If you notice something, surface it.
The skills git repo is at: ~/Projects/claude-code-skills/ Skills source lives at: ~/Projects/claude-code-skills/skills/ The ~/.claude/skills/ directory contains symlinks into the above.
When you detect an improvement opportunity, pause and tell the user:
"I noticed something worth capturing in the [skill-name] skill: [one-sentence description of the gap or fix]. Want me to propose a patch?"
Keep it brief. Don't write the patch yet.
If the user says yes (or "go ahead", "sure", etc.), draft the minimal change to SKILL.md:
Then ask:
"Does this look right, or would you like to adjust anything before I commit it?"
Once the user approves (explicit "yes", "looks good", "commit it", etc.):
cd ~/Projects/claude-code-skills
# Create a branch
git checkout -b skill/<skill-name>/<short-kebab-description>
# Apply the change to the actual skill file
# (edit ~/Projects/claude-code-skills/skills/<skill-name>/SKILL.md)
# Stage and commit
git add skills/<skill-name>/SKILL.md
git commit -m "skill(<skill-name>): <short description of what was fixed/added>
Context: <one sentence about what session/task revealed this gap>"
# Report back
git log -1 --onelineBranch naming convention: skill/<skill-name>/<what-changed> Examples:
skill/zetic-melange/fix-npu-init-orderskill/pdf-reading/add-scanned-doc-handlingskill/skill-improvement/clarify-trigger-conditionsCommit message format:
skill(<name>): <imperative short description>
Context: <what revealed the gap>After committing, tell the user:
"Branchskill/<name>/<desc>is ready. Review withgit diff main skill/<name>/<desc>in~/Projects/claude-code-skills, then merge when you're happy with it."
Do capture:
Don't capture:
If several gaps were found, handle them one at a time — one branch per logical change. Don't batch unrelated fixes into one commit.
Sometimes a gap spans multiple skills or belongs in a new skill. In that case:
This skill is about targeted patches to existing skills based on real session observations. For creating a new skill from scratch, or doing a major rewrite with evals, use the skill-creator skill instead. The two can hand off to each other: if a patch grows large enough to warrant a full eval cycle, say so and suggest switching to skill-creator.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.