Install
$ agentstack add skill-firstp1ck-pi-coding-agent-forge-skill-bank-manager ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Skill Bank Manager
Use this skill when the user asks to audit, inventory, improve, merge, prune, or evaluate the local Pi skill ecosystem.
Lifecycle policy
For create/update/merge/prune/enable/publish decisions, read the bundled package policy at ../../../../references/SKILL-LIFECYCLE-POLICY.md when available. Do not rely on a separate workspace-local copy.
Tools
skillbank_audit— read-only full audit; writes/tmp/pi-skill-bank-audit.mdby default.skillbank_find_overlap— reports likely duplicate skill scopes from names/descriptions.skillbank_prune_plan— emits merge/update/prune recommendations as a plan only.skillbank_run_tests— defaults to a read-only test plan; only executes tests whenrun=trueis explicit.
Workflow
- Run
skillbank_auditfirst. - Read the generated report path before making claims about the local skill bank.
- Treat missing
tests/,scripts/,references/, and validation metadata as signals, not automatic failures. - Review overlap groups critically; token overlap can produce false positives for related but distinct skills.
- Do not edit, remove, merge, or prune skills unless the user explicitly approves a follow-up implementation step.
Verification
For package development from this skill directory:
(cd ../.. && npm test)
bun ../../scripts/skillbank-audit.ts /tmp/pi-skill-bank-audit.md
pi --version
Manual evidence checks should use the target environment's selected agent directory/settings file, not a maintainer-specific config. For isolated tests, set PI_CODING_AGENT_DIR to a temporary fixture directory before running the audit.
Safety Boundaries
- The audit tools are read-only with respect to skill/package files.
- Writing Markdown reports to
/tmpor a user-provided output path is allowed. - Prune/merge recommendations are never permission to mutate files.
skillbank_run_testsmay execute package scripts only whenrun=true; keep it in plan mode by default.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Firstp1ck
- Source: Firstp1ck/pi-coding-agent-forge
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.