agentleFS
Sign inStart free
MSiccDevMSiccDev/ai-context-kit/skills/validate-project-instructions/SKILL.md

validate-project-instructions

Skill12 starsChanged 4 months agoMITView on GitHub

Validate project-context AGENTS.md files for required sections, session-state model completeness, role quality, and scoring compliance.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Use this skill to validate project-context AGENTS.md files.

    line 17
  2. Distinctive:

    Use this skill when reviewing project context quality prior to active use.

    line 18
  3. Distinctive:

    Do not use this skill for user-context instruction validation.

    line 19
  4. Very specific:

    Run validation phases from references/phase-checks.md.

    line 27
  5. Very specific:

    Check for <!-- spec_version: ...

    line 28
  6. Distinctive:

    Keep findings specific and actionable.

    line 49
  7. Distinctive:

    Keep validation language provider-neutral.

    line 51
  8. Distinctive:

    Do not rewrite source files automatically.

    line 52

≈ “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

Validate Project Context AGENTS

Purpose

Validate project-context AGENTS.md files with structured checks for required sections, session-state controls, role definitions, and core required-section completeness based on a deterministic scoring rubric.

When To Use

  • Use this skill to validate project-context AGENTS.md files.
  • Use this skill when reviewing project context quality prior to active use.
  • Do not use this skill for user-context instruction validation.

Required Inputs

  • Target project-context AGENTS.md path.
  • Expected section model and command reference expectations.
  • Any strictness preferences for warnings vs required fixes.

Workflow

  1. Run validation phases from references/phase-checks.md.
  2. Check for <!-- spec_version: ... --> comment: flag as WARNING if absent (pre-existing files may predate this requirement); flag as WARNING if present but older than 1.5.0.
  3. Generate report using references/report-contract.md.
  4. Apply deterministic scoring from references/scoring.md.
  5. Classify findings into critical/warning/enhancement buckets.
  6. Produce project-specific remediation guidance.

Output Expectations

  • Structured markdown report with five validation phases.
  • Clear status for critical issues vs warnings.
  • Numeric score and grading band.
  • Concrete example fixes for major gaps.
  • Report schema follows references/report-contract.md.
  • Scoring and grade bands follow references/scoring.md.

Resources

  • Phase checks: references/phase-checks.md
  • Report contract: references/report-contract.md
  • Scoring model: references/scoring.md
  • Example target: ../../AGENTS.md

Constraints And Safety

  • Keep findings specific and actionable.
  • Preserve project terminology when proposing fixes.
  • Keep validation language provider-neutral.
  • Do not rewrite source files automatically.

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.

Check your setup, free