agentleFS
markoblogomarkoblogo/abvx-agent-skills/skills/pipeline-readiness-gate/SKILL.md

pipeline-readiness-gate

Skill16 starsChanged 5 months agoMITView on GitHub

Choose and run a compact pre-implementation, post-implementation, or ship-readiness gate for agent work. Use when a task needs ordered review lenses, proof gates, or release confidence without adopting a heavy multi-agent pipeline runtime.

The file

Show its rules and text

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use before code changes:

    line 25
  2. Distinctive:

    Use after a phase:

    line 34
  3. Distinctive:

    Run the repo's narrow verification commands.

    line 36
  4. Very specific:

    Use minimal-diff-builder or overengineering-review for scope drift.

    line 37
  5. Very specific:

    Use test-driven-execution or test review when behavior changed.

    line 38
  6. Very specific:

    Use delivery-baseline-audit against declared deliverables.

    line 39
  7. Distinctive:

    Use before publication, PR merge, release, or public docs update:

    line 43
  8. Very specific:

    Run delivery-preflight-gate push-gate mode when remote publication is in scope.

    line 45
  9. Very specific:

    Run confidence-fragility-review on claims and release notes.

    line 46
  10. Very specific:

    Run authorized-security-router first for security-sensitive surfaces.

    line 47
  11. Distinctive:

    Do not invent a pipeline engine.

    line 62
  12. Distinctive:

    Do not run every skill when one gate answers the question.

    line 63
  13. Distinctive:

    Do not block implementation on low-risk advisory findings.

    line 64
  14. Distinctive:

    Keep runtime state in the external harness, not in this skill.

    line 65

≈ “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

Pipeline Readiness Gate

Apply a small ordered gate instead of a large multi-agent runtime.

Use When

  • a plan needs review before implementation;
  • an implementation needs validation before the next phase;
  • a branch or artifact needs a ship gate;
  • SET or another orchestrator provides a handoff bundle with recommended review lenses.

Gate Modes

Pre-Implementation

Use before code changes:

  1. doc-grounded-grilling when requirements are unclear.
  2. assumption-excavation on the plan/spec/bundle.
  3. architecture-deepening-review for structural fit when architecture is affected.
  4. Proceed only when critical assumptions and architecture risks are surfaced.

Post-Implementation

Use after a phase:

  1. Run the repo's narrow verification commands.
  2. Use minimal-diff-builder or overengineering-review for scope drift.
  3. Use test-driven-execution or test review when behavior changed.
  4. Use delivery-baseline-audit against declared deliverables.

Ship

Use before publication, PR merge, release, or public docs update:

  1. Run delivery-preflight-gate push-gate mode when remote publication is in scope.
  2. Run confidence-fragility-review on claims and release notes.
  3. Run authorized-security-router first for security-sensitive surfaces.
  4. Finish with delivery-baseline-audit.

Output Shape

Include:

  • selected gate mode;
  • lenses used or skipped;
  • verification commands;
  • blockers;
  • PROCEED, REVISE, or HOLD decision.

Guardrails

  • Do not invent a pipeline engine.
  • Do not run every skill when one gate answers the question.
  • Do not block implementation on low-risk advisory findings.
  • Keep runtime state in the external harness, not in this skill.

Provenance

Adapted from the pre-implementation, post-implementation, and ship pipeline ordering in aself101/agents-and-pipelines, narrowed for ABVX skill orchestration.

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.