AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Lesson Propose

skill-zhjai-agent-lessonbook-lesson-propose · by zhjai

Use at task wrap-up, after a mistake, or on a postmortem to turn the correction journal and observations into review PROPOSALS — classify each candidate lesson by target tier (working-only / approved-lesson / policy / gate-candidate) and write a proposal note, without self-approving. Use when wrapping up, after something went wrong, or when a correction should persist. Do not grant a lesson autho…

↗ Repository
— No reviews yet
0 installs
39 views
0.0% view→install

Install

$ agentstack add skill-zhjai-agent-lessonbook-lesson-propose

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-zhjai-agent-lessonbook-lesson-propose)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Lesson Propose? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Lesson Propose

The worker proposes lessons; it never promotes them. Promotion (candidate → control/approved_lessons/ or rules.md) is a human git action, not a tool the worker can call.

When to use

  • Task wrap-up, postmortem, or when a correction/drift note should outlive this task.

Procedure

  1. Read state/tasks//correction_journal.md and any session observations.
  2. For each keeper, write a candidate into state/tasks//candidate_lessons.md, tagged with a target tier:
  • working-only — relevant to this task only; stays in state/.
  • approved-lesson-candidate — recurring; propose into control/approved_lessons/.
  • policy-candidate — stable, cross-task; propose into control/rules.md.
  • gate-candidate — binary, machine-checkable; a human may translate it into an agent-completion-gate check (this skill does NOT touch the gate).
  1. Each candidate carries: the lesson, evidence (cite the journal entry), applies_when, and not_authoritative_until_reviewed: true.
  2. Leave everything in candidate_lessons.md (pending). Do not move anything into control/ yourself.

Outputs

  • candidate_lessons.md with tier-tagged proposals + evidence.
  • A short summary the human can review and promote in git.

Do not

  • Do not write to control/approved_lessons/ or control/rules.md — read-only to the worker; promotion is a reviewed action.
  • Do not edit any agent-completion-gate manifest. Surfacing a gate-candidate is a suggestion to a human, not an action.
  • Do not mark a lesson "enforced" without a corresponding rule/gate actually carrying it.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

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.

More in AI & ML