Skill library

Skills describe repeatable work: review a design, check a release or hand work to another agent. Keep your own procedures in the account library and assign them to the projects that need them. The free starter templates provide editable starting points; they do not run automatically.

Create and assign

Open Skills in the signed-in workspace. Create a skill with a title, short summary and complete procedure, or copy a starter template into your library. Assign it explicitly to a project. The same skill can serve several projects; another account cannot access your library.

Edits create preserved revisions. Assigned projects see the current active version on their next read. Archiving removes the skill from agent discovery; restoring makes it available again where still assigned. Review changes before saving them: this release does not provide a separate approval stage or pinned per-project versions for skills.

Limits: 50 active and 200 retained skills per account, up to 10 assignments per project. Titles allow 120 characters, summaries 400 and procedures 16,000.

Discover, then load

The agent’s normal memory_read response contains skill summaries and exact revisions, without the full procedures. memory_list_skills refreshes that catalog for the verified project. memory_get_skill retrieves a selected active, assigned skill using project_id and skill_id.

Standards remain the project rulebook and are included in full. Skills are selected procedures for a relevant task. Neither overrides the user’s instructions, grants additional access or authorizes an action. Clients still need the tools required to carry out a procedure.

An agent can save an authorized execution log as a separate project note, including skill ID and revision, checks actually performed, findings, changes and the remaining next step. The log is reported evidence, not independent proof that a check ran. Memford does not execute workflows or verify an agent’s work itself.

Example: improve a design

The design-review template asks for independent AI assessments of usability, visual design and accessibility. It specifies at most three improvement rounds, a target of eight out of ten in each area and no critical unresolved issue. Reviewers must support findings with concrete observations. Scores describe AI assessments, not human jury votes, formal accessibility certification or permission to deploy.

Keep connected agents informed

The setup guide adds a small discovery convention: at relevant session or work start, compare the capabilities.revision in the memory response with the last seen revision. Read memory_features, or the public feature guide, when that revision is unknown or changed. The guide and MCP manifest share one source of truth.

Supporting clients can receive existing project-resource change hints after assigned skills change, then read the catalog again. Product capability changes are discovered on the next read or reconnect, not through a guaranteed background push. Tool availability and inserting retrieved context into a running conversation depend on the client.

Existing installations need the new discovery convention added once. Updated startup adapters deliver the catalog and capability hint, but an already installed adapter does not update itself. Disconnected clients cannot discover new features. New capabilities never silently activate paid services, install code or expand permissions.

GitHub import and synchronization, public community publishing and automatic workflow execution are not part of this release.