agentleFS
mblaubergmblauberg/provenant/skills/improve/SKILL.md

improve

Skill1 starsChanged yesterdayMITView on GitHub

Use to learn from runs and incidents, evaluate agents or prompts, or audit and write skills.

76 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use deploy-platform, setup-platform and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • agno-agiSkill

    deploy-platform

    Deploy this AgentOS using its own provider instructions, configure JWT verification, and verify the public service. Use for first deployment, redeployment, or production configuration changes.

    Also in 4 projects that use this

  • agno-agiSkill

    setup-platform

    Set up this AgentOS from a fresh clone — confirm Docker, configure .env, boot the containers, prove the MCP endpoint live, connect the AgentOS UI, then build the user's first agent. Use when the user asks to set up the platform, get started, or bring this repo up on a new machine.

    Also in 4 projects that use this

  • MicrosoftSkill

    create-agent

    Create a new MCS2 Copilot Studio agent and PAC-connected local workspace with `pac copilot init`, then optionally add modern instructions, skills, tools, knowledge, and settings before synchronizing it. Use when the user asks to create, scaffold, initialize, or build a Copilot Studio agent.

    Also in 5 projects that use this

  • HeshamFSSkill

    loop

    Run a command or check on a recurring interval

    Also in 5 projects that use this

  • admin-remixSkill

    workspace

    Google Workspace administration - manage users, groups, email, Drive, calendars, and devices through natural conversation. Triggers on: Google Workspace, G Suite, user management, group management, admin tasks, offboarding, onboarding, email forwarding, Drive permissions, suspended users, organizational units, ChromeOS devices, audit logs, admin reports.

    Also in 3 projects that use this

  • AmirofcodesSkill

    goal

    Use when the user starts, manages, or asks about an OpenClaw goal mode with /goal. Enforces a bounded goal contract, visible progress blocks, proof requirements, stop conditions, and honest limitation language when no runtime goal-loop plugin is active.

    Also in 4 projects that use this

  • +3 more from agno-agi

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 74 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read available telemetry, review and repair history, escaped defects, PR threads, human corrections and test-suite health.

    line 13

“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Improve

Change process on evidence, choosing the best-supported remedy for the observed cause. A clean routine cycle returns no change.

Retrospect

Read available telemetry, review and repair history, escaped defects, PR threads, human corrections and test-suite health. Mark absent evidence unknown, never success inferred from a clean final answer. Use provenant help telemetry to choose the cost, value and trace views. A suite that only grows is a finding.

Cluster failures by cause (spec, test, skill, instructions, routing, tool, context, authority) and propose per cluster the best-evidenced change with its rationale, owner, destination and success measure. Turn a representative failure into a deterministic test or fixture before claiming improvement. improved needs a passing regression gate and comparable later runs; underpowered or confounded evidence is inconclusive. For comparisons across releases, experiments or instructions in local Claude, Codex and lane histories, use the history audit.

Evaluate

For a stochastic system, prefer an execution oracle (hidden tests, type checks) and grade with a model only what execution cannot establish, blind to the arm. Freeze the task set, splits, criteria, arms, seeds and repetitions before looking at results, and keep search, acceptance and held-out splits apart. For a skill, compare the candidate with no skill and the previous version. Record the actual model, harness, effort, cost and failures per arm, and report raw numerators and denominators so another agent can recompute the result. A result describes its tested distribution, not general safety.

Skills

A skill earns its place with the few rules a capable agent would otherwise get wrong; everything else is cost paid on every load. Audit read-only with skill audit; write or revise under a grant with skill author. Run the task without the skill first and keep only the lines that change the result.

Output

Proposal-first. Apply changes under explicit authority or through deliver. Finish with a table: finding, evidence, cause, change, regression gate, destination, status (promote, experiment, defer, reject). File actionable findings through tracker even when no regression is attributable, and promote durable conclusions to their owner rather than a parallel diary.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.