skill-manage
skill-manage implements approved lifecycle operations on the canonical Mnemon skill library, including creating new skills, updating existing skill content, and moving skills between active, stale, and archived states. Use this skill only after explicit user approval or host policy authorization, ensuring changes apply to the skill library canonical state rather than host runtime behavior directly.
git clone --depth 1 https://github.com/mnemon-dev/mnemon /tmp/skill-manage && cp -r /tmp/skill-manage/harness/internal/assets/loops/skill/skills/skill-manage ~/.claude/skills/skill-manageSKILL.md
# skill-manage Use this skill only after a proposal has been approved by the user or by an explicit host policy. ## Boundary This skill submits approved skill declarations to Local Mnemon. It does not edit host skill directories or canonical files directly. New active skills become host-visible after Local Mnemon accepts the declaration and the host projection refreshes. ## Allowed MVP Operations - submit an approved active skill declaration - submit approved `SKILL.md` content drafted by `skill-author` - submit a replacement declaration for an existing skill - submit lifecycle status changes: `active`, `stale`, or `archived` - submit metadata or usage notes needed by the lifecycle ## Procedure 1. Read the approved proposal and confirm the intended operation. 2. Check `MNEMON_SKILL_LOOP_PROTECTED_SKILLS`; do not modify protected skills unless the approval explicitly covers the exception. 3. Keep skill ids hyphen-case: lowercase letters, numbers, and `-`. Preserve a non-conforming id only when an external host compatibility boundary requires it. 4. Submit the smallest approved declaration through Local Mnemon: <!-- mnemon:payload-contract --> 5. Do not edit the host skill surface directly. Let Local Mnemon and Prime regenerate mirrors. 6. Record the submitted declaration in the proposal or usage log when useful. ## Safety If the proposal is ambiguous, risky, or conflicts with current repository state, stop and ask for approval instead of guessing.
Analyze Mnemon harness eval reports, classify outcomes, and extract improvement evidence.
Turn stable Mnemon harness eval findings into scoped project, loop, adapter, docs, or eval asset improvements.
Design a scenario-driven Mnemon harness eval with target, hypothesis, HostAgent, loop configuration, evidence, and rubric.
Execute or supervise a planned Mnemon harness eval run in an isolated HostAgent workspace.
Manage project-scoped Mnemon goal state, evidence, verification, completion, blockers, and host goal links.
Read scoped memory from Local Mnemon when GUIDE.md indicates that prior memory may help the current task.
Submit durable memory candidates to Local Mnemon when GUIDE.md indicates that a stable fact, preference, decision, or continuity item should be kept.
Draft or revise high-quality SKILL.md content for approved or proposed Mnemon skill changes.