agentleFS
CsHengCsHeng/agent-skills/skills/sync-truth/SKILL.md

sync-truth

Skill3 starsChanged 8 days agoMITView on GitHub

Update stable project docs and durable operational facts to match already verified behavior when the user asks or an approved change includes it. Not for restructuring documentation ownership, layout, or search boundaries, which belongs to organize-docs, or for read-only explanation, which belongs to analyze-project.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Update long-lived project truth from verified change evidence.

    line 8
  2. Very specific:

    Read-only project explanation goes to analyze-project, implementation review to review-change, closure without truth updates to …

    line 15
  3. Distinctive:

    Start from the verified change evidence and update the stable facts that current implementation and verification support.

    line 20
  4. Distinctive:

    Verify links, commands, generated references, terminology, and repository documentation checks, then state the updated truth, its evidence, …

    line 22
  5. Very specific:

    Update facts from evidence, and record a goal, discretion, or boundary mismatch as a finding for the decision that owns it …

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Sync Truth

Update long-lived project truth from verified change evidence.

Use This Skill When

  • a verified change has real truth impact and the user request or approved change scope authorizes the documentation mutation
  • stable documentation or durable operational facts no longer match the implementation

Read-only project explanation goes to analyze-project, implementation review to review-change, closure without truth updates to close-change, and restructuring of documentation ownership, layout, or search boundaries to organize-docs.

Workflow

  1. Identify the smallest stable truth roots affected by verified behavior, separating long-lived truth from stage artifacts, generated output, and historical notes.
  2. Start from the verified change evidence and update the stable facts that current implementation and verification support; keep stage artifacts as history.
  3. Compose organize-docs when ownership, truth roots, search boundaries, stage placement, canonical terminology, or prose structure need adjustment, or when stable decision truth is created, promoted, superseded, compacted, or retired.
  4. Verify links, commands, generated references, terminology, and repository documentation checks, then state the updated truth, its evidence, and any remaining mismatch.

Rules

  • Update facts from evidence, and record a goal, discretion, or boundary mismatch as a finding for the decision that owns it (development-standards Goals, Discretion, And Risk).
  • Record external paths, secrets, settings contents, or transient machine state only when the user named them a durable public contract.
  • Documentation authority covers documentation only.

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.