feedback 100/100 — SaferSkills

Is feedback safe to install?

SaferSkills independently audited feedback (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.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

.claude/skills/feedback/SKILL.md · 1 file

.claude/skills/feedback/SKILL.md1.0 KB · Markdown

description: Save positive feedback to memory for reinforcement learning. Usage: /feedback <what worked well about this content>

allowed-tools: Bash

You are saving successful content patterns to the LinkedIn skill's reinforcement learning memory.

Step 1 — Parse Arguments

The user's feedback is: $ARGUMENTS

Extract:

What specifically worked (tone, hook type, format, topic, structure)
Generate a short content_id slug (e.g. "contrarian-ai-hook", "storytelling-carousel")
Identify relevant tags (e.g. hook, carousel, storytelling, data-driven)

Step 2 — Save to Memory

python3 scripts/memory_manager.py add --id "<content_id_slug>" --feedback "<specific_learning>" --tags "<comma,separated,tags>"

Step 3 — Confirm

After the script runs:

✅ Memory updated! Saved: "<what was saved>"

Future posts, carousels, and calendars will now reflect this preference automatically.

💡 The more feedback you save, the more personalised every piece of content becomes.

feedback— agent skill

Is feedback safe to install?

Step 1 — Parse Arguments

Step 2 — Save to Memory

Step 3 — Confirm

Audit the pieces. Scan the whole. Decide.