agentleFS
Sign inStart free
Marwan-Ahmed-devMarwan-Ahmed-dev/vibecode-pro-max/.agents/skills/vc-generate-context/SKILL.md

vc:generate-context

Skill0 starsChanged 3 months agoMITView on GitHub

Generate or update the kit's authoritative repository context at process/context/all-context.md. Use when repo context is missing, stale, or contradicted by code.

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 4 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

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

    Use this skill to maintain process/context/all-context.md, the broad portable project knowledge layer shared by Codex and Claude.

    line 11
  2. Very specific:

    Read references/generate-context.md for the full context contract.

    line 17
  3. Very specific:

    Read process/context/all-context.md when present to identify relevant grouped context files.

    line 21
  4. Distinctive:

    If routing or grouped context changed, also run:

    line 29
  5. Very specific:

    Treat process/context/ as durable cross-agent knowledge.

    line 36
  6. Very specific:

    Treat process/context/all-context.md as the durable routing protocol.

    line 37
  7. Distinctive:

    Do not store agent-specific mechanics here unless they affect project workflow.

    line 38
  8. Very specific:

    Do not rewrite grouped context docs.

    line 39
  9. Distinctive:

    Prefer concise, factual, path-specific documentation.

    line 40
  10. Very specific:

    Use pnpm terminology for package management.

    line 41
  11. Distinctive:

    Treat validation failures as blockers before presenting context as refreshed.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Generate Context

Use this skill to maintain process/context/all-context.md, the broad portable project knowledge layer shared by Codex and Claude. Use process/context/all-context.md as the context router before reading grouped docs.

Optional input: a package, app, feature, context group, or architectural area to refresh first.

Workflow

  1. Read references/generate-context.md for the full context contract.
  2. Determine mode:
    • Full scan when process/context/all-context.md is missing.
    • Delta update when it exists.
  3. Read process/context/all-context.md when present to identify relevant grouped context files.
  4. Inspect current repo state, active plans, feature folders, package scripts, tooling, important architecture files, and relevant process/context/**/*.md docs.
  5. Produce exactly one updated file: process/context/all-context.md.
  6. Include scan timestamp, repo HEAD if available, changes since last update, open questions, and source references.
  7. Validate the generated context:
    node .claude/skills/vc-generate-context/scripts/validate-all-context.mjs
  8. If routing or grouped context changed, also run:
    node .claude/skills/vc-audit-context/scripts/validate-context-discovery.mjs

Rules

  • Treat process/context/ as durable cross-agent knowledge.
  • Treat process/context/all-context.md as the durable routing protocol; do not replace it with generated prose.
  • Do not store agent-specific mechanics here unless they affect project workflow.
  • Do not rewrite grouped context docs; if they are stale or mis-grouped, flag audit-context.
  • Prefer concise, factual, path-specific documentation.
  • Use pnpm terminology for package management.
  • Treat validation failures as blockers before presenting context as refreshed.

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.

Reviews can't be read right now.

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.

Check your setup, free